METHOD AND SYSTEM FOR GENERATING A USER'S HAND MODEL

专利摘要:
method and system for generating a user's hand model. the present invention relates to a system and method related to a chained execution to generate a computer model of a target user, which includes a model of the user's hands and fingers (18), captured by an image sensor (20) in a nui system. the computer model represents a better estimate of the position and orientation of a user's hand or hands (18). the hand model generated can be used by a game or other application to determine things like gestures and user control actions (18).
公开号:BR112013031118B1
申请号:R112013031118-5
申请日:2012-06-04
公开日:2021-04-13
发明作者:Albert Robles；Daniel Osborn；Shawn Wright；Nahil Sharkasi；Dave Hill；Daniel McCulloch；Anthony Ambrus；Kyungsuk David Lee；Andrew Campbell；David Haley；Brian Mount
申请人:Microsoft Technology Licensing, Llc；
IPC主号:

专利说明:

BACKGROUND
[0001] In the past, computing applications such as computer games and multimedia applications used controllers, remote controls, keyboards, mice, or the like to allow users to manipulate game characters or other aspects of an application. More recently, computer games and multimedia applications have begun to employ cameras and gesture recognition software mechanisms to provide a natural user interface ("NUI"). With NUI, raw data of articulation and user gestures are detected, interpreted and used to control game characters or other aspects of an application.
[0002] One of the challenges of an NUI system is to distinguish a person in the field of view from an image sensor, and to correctly identify the positions of their body parts including hands and fingers within the field of view. Routines are known to track arms, legs, heads and torso. However, given the subtle detail and wide variety of user hand positions, conventional systems are not able to satisfactorily recognize and track a user's body including finger and hand positions. SUMMARY
[0003] This document discloses systems and methods for recognizing and tracking user skeletal joints, which include hand and finger positions with an NUI system. In examples, hand and finger position tracking can be used by NUI systems to trigger events such as selecting, engaging, or holding and dragging objects on a screen. A variety of other gestures, control actions and applications can be enabled by this technology to recognize and track hand and finger positions and movements. By determining states of a user's hand and fingers, a user's interactivity with an NUI system can be increased, and simpler and more intuitive interfaces can be presented to a user.
[0004] In one example, the present description refers to a method for generating a model of a user's hand that includes one or more fingers for a natural user interface, which comprises: (a) receiving image data from a user who interacts with the natural user interface; and (b) analyzing the image data to identify the hand in the image data, in which said step (b) includes the steps of: (b) (1) analyzing depth data of the image data captured in said step ( a) segment the image data into hand data, and (b) (2) extract a form descriptor by applying one or more filters to the hand image data identified in said step (b) (1), the one or more filters analyze image data from the hand as compared to image data outside a hand boundary to discern a shape and orientation of the hand.
[0005] In an additional example, the present description refers to a system for generating a model of a user's hand that includes one or more fingers for a natural user interface, in which the system comprises: a skeleton recognition mechanism to recognize a user's skeleton from received image data; an image segmentation mechanism that segments one or more regions of the body into a region that represents a user's hand; and a descriptor extraction mechanism for extracting representative data from a hand that includes one or more fingers and a hand orientation, the descriptor extraction mechanism applies a plurality of filters to analyze pixels in the region that represents the hand, in which each filter in the plurality of filters determines a position and orientation of the hand, in which the descriptor extraction mechanism combines the results of each filter to arrive at a better estimate of the position and orientation of the hand.
[0006] In another example, the present description refers to a computer-readable storage medium that does not consist of a modulated data signal, in which the computer-readable storage medium has computer-readable instructions for programming a processor to perform a method for generating a model of a user's hand that includes one or more fingers for a natural user interface, where the method comprises: (a) receiving image data from a user who interacts with the natural user interface; (b) analyzing the image data to identify the hand in the image data; and (c) comparing the image data of the identified hand against predefined hand positions to determine whether the user performed one of the following predefined hand gestures or control actions: (c) (1) counting on the user's fingers, (c) (2) performing an "OK" gesture, (c) (3) pressing a virtual button, (c) (4) squeezing the thumb and a finger together, (c) (5) writing or drawing, ( c) (6) sculpt, (c) (7) manipulate puppet, (c) (8) turn a button or combination lock, (c) (9) shoot with a firearm, (c) (10) perform a shake gesture, (c) (l 1) perform a gesture where a finger can be used on an open palm to move and navigate through virtual space, and (c) (12) move fingers in a scissor motion to control the legs of a virtual character.
[0007] This Summary is provided to introduce a selection of concepts in a simplified way which are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed object, nor is it intended to be used as an aid in determining the scope of the claimed object. In addition, the claimed object is not limited to implementations that address any or all of the disadvantages noted elsewhere in this description. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] FIGURE 1A illustrates an example modality of a target tracking, analysis and recognition system.
[0009] FIGURE 1B illustrates an additional example modality of a target tracking, analysis and recognition system.
[00010] FIGURE 1C illustrates an even further example of a target tracking, analysis and recognition system.
[00011] FIGURE 2 illustrates an example of a capture device that can be used in a target tracking, analysis and recognition system.
[00012] FIGURE 3 shows an exemplary model of body used to represent a human target.
[00013] FIGURE 4 shows a substantially front view of an exemplary skeleton model used to represent a human target.
[00014] FIGURE 5 shows a skewed view of an exemplary skeleton model used to represent a human target.
[00015] FIGURE 6 shows a flowchart of a chained execution to track a target according to a modality of the present technology.
[00016] FIGURE 7 illustrates an example method for determining a state of a user's hand according to an embodiment of the present description.
[00017] FIGURE 8 is a flow chart of the operation of an image segmentation mechanism according to one embodiment of the present description.
[00018] FIGURE 9 is a flow chart of the operation of a pixel classification filter according to an embodiment of the present description.
[00019] FIGURE 10 is a decision tree for the operation of a pixel classification filter according to an embodiment of the present description.
[00020] FIGURES 11A and 11B illustrate the fingertip identification using a pixel classification filter according to an embodiment of the present description.
[00021] FIGURE 12 illustrates finger identification using a pixel rating filter according to an embodiment of the present description.
[00022] FIGURE 13 illustrates a part of a hand identified using a pixel classification filter according to an embodiment of the present description.
[00023] FIGURE 14 illustrates the identification of hand and finger using a pixel classification filter according to an embodiment of the present description.
[00024] FIGURE 15 is a flow chart of the operation of a curvature analysis filter according to one embodiment of the present description.
[00025] FIGURE 16 illustrates hand and finger identification using a curvature analysis filter according to an embodiment of the present description.
[00026] FIGURE 17 illustrates open and closed hand analysis using a depth histogram filter according to an embodiment of the present description.
[00027] FIGURE 18 is a flow chart of a supervisor filter to classify a hand position based on hand filters.
[00028] FIGURE 19A illustrates an example modality of a computational environment that can be used to interpret one or more gestures in a target tracking, analysis and recognition system.
[00029] FIGURE 19B illustrates another example modality of a computational environment that can be used to interpret one or more gestures in a target tracking, analysis and recognition system. DETAILED DESCRIPTION
[00030] The modalities of the present technology will now be described with reference to Figures 1A to 19B, which in general refer to a chained execution to generate a computer model of a target user, which includes a model of the hand of the hands and fingers of the target. captured by an image sensor in an NUI system. The computer model can be generated once per frame of captured image data, and represents a better estimate of the position, which includes the pose, of a user during the captured frame. The hand model generated for each frame can be used by a game application or another to determine things such as gestures and user control actions. The hand model can also be re-emphasized in the chained execution to aid in future model determinations.
[00031] Initially with reference to Figures 1A to 2, the hardware to implement the present technology includes a target tracking, analysis and recognition system 10 that can be used to recognize, analyze, and / or track a human target such as user 18. Tracking, analysis and target recognition system modalities 10 include a computational environment 12 to run a game or other application. The computing environment 12 can include hardware components and / or software components in such a way that the computing environment 12 can be used to run applications such as gaming and non-gaming applications. In one embodiment, the computing environment 12 may include a processor such as a standardized processor, a specialized processor, a microprocessor, or the like that can execute instructions stored on a computer-readable storage device to perform processes described in this document.
[00032] System 10 additionally includes a capture device 20 for capturing image and audio data related to one or more users and / or objects detected by the capture device. In the modalities, the capture device 20 can be used to capture information related to body and hand movements and / or gestures and speech of one or more users, information that is received by the computational environment and used to present, interact with and / or control aspects of a game application or another. Examples of computational environment 12 and capture device 20 are explained in more detail below.
[00033] Tracking, analysis and target recognition system modalities 10 can be connected to an audio / visual (A / V) device 16 that has a display 14. Device 16 can, for example, be a television, a phone, a monitor for a computer, a high-definition television (HDTV), or similar that can provide visual and / or audio of a game or application to a user. For example, the computing environment 12 may include a video adapter such as a graphics card and / or an audio adapter such as a sound card that can provide audio / visual signals associated with the game or other application. The A / V device 16 can receive the audio / visual signals from the computing environment 12 and can then provide the visual and / or audio of the game or application associated with the audio / visual signals to the user 18. According to a modality , the audio / visual device 16 can be connected to the computing environment 12 via, for example, an S-Video cable, a coaxial cable, an HDMI cable, a DVI cable, a VGA cable, a component video cable, or the like.
[00034] In the modalities, the computational environment 12, the A / V device 16 and the capture device 20 can cooperate to present an avatar or character on screen 19 on display 14. For example, Figure 1A shows a user 18 playing a football game application. The user's movements are tracked and used to animate the movements of avatar 19. In the modalities, avatar 19 mimics the movements of user 18 in real-world space so that user 18 can perform movements and gestures that control movements and actions of avatar 19 on display 14.
[00035] As explained above, movement estimation routines such as skeleton mapping systems may not have the ability to detect a user's subtle gestures, such as, for example, the movement of a user's hand. For example, a user may wish to interact with the NUI 10 system by walking and controlling a user interface 21 with his hand as shown in Fig. 1B. A user may alternatively attempt to perform various gestures, such as, for example, opening and / or closing his hand as shown as 23 and 25 in Fig. 1C.
[00036] Consequently, the systems and methods, described below in this document, are aimed at determining a state of a user's hand. For example, the action of closing and opening the hand can be used by these systems to trigger events such as selecting, engaging, or holding and dragging objects, for example, object 27 (Fig. 1C), on the screen. These actions would otherwise correspond to pressing a button when using a controller. This refined interaction without the use of control can be used as an alternative to approaches based on waving or waving, which can be non-intuitive or complicated. A variety of other gestures, control actions and applications can be enabled by this technology to recognize and track hand movements, some of which are described in further detail below. By determining states of a user's hand as described below, a user's interactivity with the system can be increased and simpler and more intuitive interfaces can be presented for a user.
[00037] Figures 1A and 1B include static background objects 23, such as a floor, chair and floor plan. These are objects within the field of view (FOV) captured by the capture device 20, but do not change from frame to frame. In addition to the floor, chair and floor plan shown, static objects can be any objects captured by the image cameras on the capture device 20. Additional static objects within the scene can include any walls, ceiling, windows, doors, wall decorations, etc.
[00038] Suitable examples of a system 10 and components thereof are found in the following copending patent applications, all of which are specifically incorporated herein by reference: U.S. Patent Application Serial No. 12 / 475.094, entitled " Environment and / or Target Segmentation ", filed on May 29, 2009; US Patent Application Serial No. 12 / 511,850, entitled "Auto Generating a Visual Representation", filed on July 29, 2009; US Patent Application Serial No. 12 / 474,655, entitled "Gesture Tool", filed on May 29, 2009; US Patent Application Serial No. 12 / 603,437, entitled "Pose Tracking Pipeline", filed on October 21, 2009; US Patent Application for Serial No. 12 / 475,308, entitled "Device for Identifying and Tracking Multiple Humans Over Time", filed on May 29, 2009, US Patent Application for Serial No. 12 / 575,388, entitled "Human Tracking System", filed on October 7, 2009; US Patent Application Serial No. 12 / 422,661, entitled "Gesture Recognizer System Architecture", filed on April 13, 2009; and US Patent Application Serial No. 12 / 391,150, entitled "Standard Gestures", filed on February 23, 2009.
[00039] Fig. 2 illustrates an example modality of the capture device 20 that can be used in the tracking, analysis and target recognition system 10. In an example modality, the capture device 20 can be configured to capture video that has a depth image that can include depth values using any suitable technique including, for example, flight time, structured light, stereo image, or the like. According to one embodiment, the capture device 20 can organize the calculated depth information into "Z layers," or layers that can be perpendicular to a Z axis that extends from the depth camera along its line of sight . The X and Y axes can be defined as being perpendicular to the Z axis. The Y axis can be vertical and the X axis can be horizontal. Together, the X, Y and Z axes define the real-world 3-D space captured by the capture device 20.
[00040] As shown in Fig. 2, the capture device 20 can include an image camera component 22. According to an example embodiment, the image camera component 22 can be a depth camera that can capture the image depth of a scenario. The depth image can include a two-dimensional (2-D) pixel area of the captured scene where each pixel in the 2-D pixel area can represent a depth value such as a length or distance in, for example, centimeters, millimeters, or similar object in the scene captured from the camera.
[00041] As shown in Fig. 2, according to an example embodiment, the imaging camera component 22 may include an IR light component 24, a three-dimensional (3D) camera 26, and an RGB camera 28 that can be used to capture the depth image of a scene. For example, in flight time analysis, the IR light component 24 of the capture device 20 can emit infrared light over the scene and can then use sensors (not shown) to detect back-scattered light from the surface of one or more more targets and objects in the scene using, for example, the 3D 26 camera and / or the RGB 28 camera.
[00042] In some embodiments, pulsed infrared light can be used in such a way that the time between an output light pulse and a corresponding input light pulse can be measured and used to determine a physical distance from the capture device 20 to a particular location on targets or objects in the scenario. In addition, in other example embodiments, the phase of the outgoing light wave can be compared to the phase of the incoming light wave to determine a phase change. The phase shift can then be used to determine a physical distance from the capture device 20 to a particular location on targets or objects.
[00043] According to another example modality, the flight time analysis can be used to indirectly determine a physical distance from the capture device 20 to a particular location on targets or objects by analyzing the intensity of the light beam reflected over time through Various techniques include, for example, filled pulse pulse imaging.
[00044] In another example embodiment, the capture device 20 can use a structured light to capture depth information. In this analysis, standardized light (that is, light displayed as a known pattern such as a grid pattern or a stripe pattern) can be projected onto the scene using, for example, the IV 24 light component. hitting the surface of one or more targets or objects in the scenario, the pattern may become deformed in response. This deformation of the pattern can be captured, for example, by the 3D camera 26 and / or the RGB camera 28 and can then be analyzed to determine a physical distance from the capture device 20 to a particular location on targets or objects.
[00045] According to another embodiment, the capture device 20 may include two or more physically separate cameras that can view a scenario from different angles, to obtain stereo visual data that can be resolved to generate depth information. In another example embodiment, the capture device 20 can use data from point cloud techniques and target scanning to detect user characteristics. Other sensor systems can be used in additional modalities, such as, for example, an ultrasonic system capable of detecting the x, y and z axes.
[00046] The capture device 20 can additionally include a handset 30. The handset 30 can include a transducer or sensor that can receive and convert sound into an electrical signal. According to one embodiment, the handset 30 can be used to reduce feedback between the capture device 20 and the computational environment 12 in the target tracking, analysis and recognition system 10. Additionally, the handset 30 can be used to receive signals from audio that can also be provided by the user to control applications such as game applications, non-game applications, or the like that can be performed by the computational environment 12.
[00047] In an example embodiment, the capture device 20 can additionally include a processor 32 which can be in operational communication with the image camera component 22. Processor 32 can include a standardized processor, a specialized processor, a microprocessor, or similar that can execute instructions that may include instructions to receive the depth image, determine whether a suitable target can be included in the depth image, convert the appropriate target into a skeleton representation or model of the target, or any other suitable instruction.
[00048] Capture device 20 may additionally include a memory component 34 that can store instructions that can be executed by processor 32, images or image frames captured by the 3D camera or RGB camera, or any other suitable information, images, or similar. According to an example embodiment, memory component 34 may include random access memory (RAM), read-only memory (ROM), cache, Flash memory, a hard disk, or any other suitable storage component. As shown in Fig. 2, in one embodiment, the memory component 34 can be a separate component in communication with the image camera component 22 and the processor 32. According to another embodiment, the memory component 34 can be integrated into processor 32 and / or the imaging camera component 22.
[00049] As shown in Fig. 2, the capture device 20 can be in communication with the computing environment 12 via a communication link 36. The communication link 36 can be a wired connection that includes, for example, a USB connection, a Firewire connection, an Ethernet cable connection, or similar and / or a wireless connection such as a wireless 802.11b, g, a, or n connection. According to one embodiment, the computational environment 12 can provide a timing for the capture device 20 which can be used to determine when to capture, for example, a scenario via the communication link 36.
[00050] Additionally, the capture device 20 can provide the depth information and images captured, for example, by the 3D camera 26 and / or by the RGB camera 28. With the aid of these devices, the partial skeleton model can be developed according to according to the present technology, with the resulting data supplied to the computational environment 12 through the communication link 36.
[00051] Computational environment 12 may additionally include a gesture recognition mechanism 190 for recognizing gestures as explained below. According to the present system, the computational environment 12 can additionally include a skeleton recognition mechanism 192, an image segmentation mechanism 194, a descriptor extraction mechanism 196 and a classifier mechanism 198. Each of these software mechanisms is described in more detail below.
[00052] Fig. 3 shows a non-limiting visual representation of an example 70 body model generated by the skeleton recognition mechanism 192. Body model 70 is a machine representation of a modeled target (eg user 18 of the Figures 1A and 1B). The body model can include one or more data structures that include a set of variables that collectively define the target modeled in the language of a game or other application / operating system.
[00053] A target model can be configured in a variety of ways without departing from the scope of this description. In some examples, a model may include one or more data structures that represent a target as a three-dimensional model that includes rigid and / or deformable shapes, or parts of the body. Each part of the body can be characterized as a mathematical primitive, examples of which include, but are not limited to, spheres, anisotropic spheres, cylinders, anisotropic cylinders, smooth cylinders, boxes, beveled boxes, prisms, and the like.
[00054] For example, the body model 70 of Fig. 3 includes body parts bp1 to bp14, each of which represents a different part of the modeled target. Each part of the body is a three-dimensional shape. For example, bp3 is a rectangular prism that represents the left hand of a modeled target, and bp5 is an octagonal prism that represents the left arm of the modeled target. Body model 70 is exemplary in that a body model can contain any number of body parts, each of which can be any machine-intelligible representation of the corresponding part of the modeled target.
[00055] A model that includes two or more parts of the body can also include one or more joints. Each joint can allow one or more parts of the body to move relative to one or more other parts of the body. For example, a model that represents a human target may include a plurality of rigid and / or deformable body parts, where some body parts may represent a corresponding anatomical body part of the human target. In addition, each part of the model's body may include one or more structural members (ie "bones" or parts of the skeleton), with joints located at the intersection of adjacent bones. It should be understood that some bones may correspond to anatomical bones in a human target and / or some bones may not have corresponding anatomical bones in the human target.
[00056] Bones and joints can collectively make up a skeleton model, which can be a constituent element of the body model. In some embodiments, a skeleton model can be used in place of another type of model, such as model 70 in Fig. 3. The skeleton model can include one or more members of the skeleton for each part of the body and an articulation between adjacent members of the skeleton. The exemplary skeleton model 80 and exemplary skeleton model 82 are shown in Figures 4 and 5, respectively. Fig. 4 shows a skeleton model 80 as viewed from the front, with joints j1 through j33. Fig. 5 shows a skeleton model 82 as viewed from a skewed view, also with joints j1 through j33. A skeleton model can include more or less joints without departing from the spirit of this description. Additional modalities of the present system explained hereinafter operate using a skeleton model that has 31 joints.
[00057] The body part models and skeleton models described above are non-limiting examples of model types that can be used as machine representations of a modeled target. Other models are also within the scope of this description. For example, some models may include polygonal meshes, fragments, NURBS, subdivision surfaces, or other high-order surfaces. A model can also include surface textures and / or other information to more accurately represent clothing, hair, and / or other aspects of a modeled target. A model can optionally include information that belongs to a current pose, one or more past poses, and / or a physical model. It should be understood that a variety of different models that can be posed are compatible with the tracking, analysis and target recognition system described in this document.
[00058] Chained software runs to generate skeleton models of one or more users within a capture device FOV 20 are known. Such a system is revealed, for example, in the US Patent Application Serial No. 12 / 876,418, entitled "System For Fast, Probabilistic Skeletal Tracking", filed on September 7, 2010, the content of which is incorporated entirely by reference in this document. Under certain conditions, for example, where a user is close enough to the capture device 20 and at least one of the user's hands is distinguishable from another background noise, a chained software run may additionally be able to generate hand models to the hand and / or fingers of one or more users within the FOV.
[00059] Fig. 6 is a flowchart of a chained software run to recognize and track a user's hand and / or fingers. In step 200, the chained run receives a depth image from the capture device 20. A depth image of a part of a user is illustrated in Fig. 7 at 302. Each pixel in the depth image includes depth information, for example , as illustrated in Fig. 7 by a gray scale gradient. For example, at 302, the user's left hand is closest to the capture device 20, as indicated by the darker region of the left hand. The capture device or depth camera captures images of a user within an observed scenario. As described below, a user's depth image can be used to determine distance information from user regions, user scale information, curvature, and user skeleton information.
[00060] In step 204, the skeleton recognition mechanism 192 of the chained execution estimates a user skeleton model as described above to obtain a virtual skeleton from a depth image obtained in step 200. For example, in Fig. 7, a virtual skeleton 304 is shown as estimated from the depth image shown at 302 of the user.
[00061] In step 208, the chained execution segments a hand or hands of the user through the image segmentation mechanism 194 of the chained execution. In some examples, the image segmentation mechanism 194 may additionally segment one or more regions of the body in addition to the hands. Segmenting a user's hand includes identifying a region of the depth image corresponding to the hand, where identification is based at least partially on the skeleton information obtained in step 204. Fig. 7 illustrates an example of segmenting the depth image of a user in different regions 306 based on the estimated skeleton 304, as indicated by the differently shaped regions. Fig. 7 shows the localized region of the hand 308 corresponding to the user's elevated right hand.
[00062] Hands or body regions can be segmented or located in a variety of ways and can be based on identified joints selected in the skeleton estimate described above. As an example, the detection and location of the hand in the depth image can be based on the estimated joints of the wrist and / or tip of the hand of the estimated skeleton. For example, in some modalities, hand segmentation in the depth image can be performed using a topographic search of the depth image around the joints of the hand, which are located close to the tip location in the depth image as candidates for the tips of the depths. fingers. The image segmentation mechanism 194 then segments the rest of the hand taking into account a body size scale factor as determined from the estimated skeleton, as well as depth discontinuities to limit identification.
[00063] As another example, a flood fill approach can be used to identify regions of the depth image corresponding to a user's hand. In a flood fill approach, the depth image can be searched from a starting point and a starting direction, for example, the starting point can be the wrist joint and the starting direction can be an elbow direction. for the wrist joint. Close pixels in the depth image can be punctuated iteratively based on the projection in the initial direction as a way to give preference to points away from the elbow and towards the tip of the hand, while depth consistency restrictions such as depth discontinuities can be used to identify limit or extreme values of a user's hand in the depth image. In some examples, distance limit values can be used to limit the depth map search in either the positive or negative direction from the initial direction based on fixed or scaled values based, for example, on an estimated user size.
[00064] As yet another example, a bounding sphere or other form of appropriate bounding, positioned based on joints of the skeleton (for example, wrist or fingertip joints), can be used to include all pixels in the depth image to a depth discontinuity. For example, a window can be slid over the bounding sphere to identify discontinuities in depth that can be used to establish a boundary in the hand region of the depth image.
[00065] The boundary shape method can also be used to place a boundary shape around a center of the palm that can be identified iteratively. An example of this iterative delimitation method is revealed in a presentation by David Tuft, entitled "Kinect Developer Summit at GDC 2011: Connect to XBOX 360", attached to this document as Annex 1, and in a publication by K. Abe, H. Saito, S. Ozawa, entitled "3D drawing system via hand motion recognition from cameras", IEEE International Conference on Systems, Man, and Cybernetics, vol. 2, 2000, whose publication is incorporated in its entirety in this document by reference.
[00066] In general, this method involves several iterative steps to refute pixels from the model. At each step, the method refutes pixels outside the sphere or otherwise centered on the hand. Then, the method scraps pixels far away from the tip of the hand (vector along the arm). Then the method performs a limit detection step to detect the hand limit and remove disconnected islands. Example steps for this method are shown in the flowchart of Fig. 8. In step 224, a boundary shape is generated around a center of the hand given by the hand joint data from the skeleton recognition mechanism 192. The shape of The boundary is large enough to cover the entire hand and is three-dimensional. In step 226, pixels outside the boundary form are scrapped.
[00067] It may happen that a user's hand is close to his body, or the user's second hand, in the depth image, and the data from those other parts of the body will be included initially in the segmented image. The labeling of the connected component can be performed to label different centroides in the segmented image. The centroid, which is most likely the hand, is selected, based on its size and the location of the hand joint. Unselected centroides can be scrapped. In step 230, pixels that are very far from the tip of the hand along a vector of the linked arm can also be scrapped.
[00068] The skeleton data from the skeleton recognition mechanism 192 may be noisy, so the data for the hand is further refined to identify the center of the hand. This can be done by iterating over the image and measuring the distance of each pixel to the boundary of the hand silhouette. The image segmentation mechanism 194 can then perform a weighted average for the figure from the maximum / minimum distance. That is, in step 232, for each pixel in the segmented image of the hand, a maximum distance along the x and y axes is identified for a hand silhouette boundary, and a minimum distance along the x and y axes for a silhouette hand boundary is identified. identified. The distance to the limit is taken as a weight, and a weighted average of the minimum distance determined is then taken by all the measured pixels to calculate the probable position of the center of the hand within the image (step 234). Using the new center, the process can be repeated iteratively until the change in the center of the palm from the previous iteration is within tolerance.
[00069] In some approaches, segmentation of hand regions can be performed when a user raises the hand outward or above or in front of the torso. In this way, the identification of hand regions in the depth image can be less ambiguous since the hand regions can be distinguished from the body more easily. The images of the hand are particularly clear when a palm of the user's hand is oriented towards the capture device 20, at which point, the traces of that hand can be detected as a silhouette. Strokes can be noisy, but a silhouetted hand allows for some informed decisions about what a hand is doing, based on, for example, detecting gaps between fingers and seeing the overall shape of the hand and mapping it using a variety of different approaches . Detecting those spaces and other features allows for the recognition of particular fingers and a general direction of where that finger is pointing.
[00070] It should be understood that the hand segmentation examples described above are presented for the purpose of example and are not intended to limit the scope of this description. In general, any method of segmenting the hand or body part can be used alone or in combination with one another and / or one of the example methods described above.
[00071] Continuing with the chained execution of Fig. 7, step 210 involves extracting a shape descriptor for the region, for example, the depth image region that corresponds to a hand as identified in step 208. The shape descriptor in step 210 it is extracted by the descriptor extraction mechanism 196, and can be any suitable representation of the region of the hand that is used to classify the region of the hand. In some embodiments, the shape descriptor can be a vector or a set of numbers used to encode or describe the shape of the hand region.
[00072] The descriptor extraction mechanism 196 can use any of a variety of filters in step 210 to extract a shape descriptor. A filter can be referred to as a pixel classifier, which will now be described with reference to the flowchart in Fig. 9, the decision tree in Fig. 10 and the illustrations in Figures 11 to 14. In step 240, a pixel is selected in the foreground of the segmented image. These are the pixels that are believed, at least nominally, to be part of the user's hand. A box of predefined size is taken around the selected pixel, with the selected pixel in the center. In modalities, the box size can be selected to be 1.5 times the width of a standard finger. A "normalized finger" is the user's finger that has been adjusted to a normalized size based on the size of the skeleton model and a detected distance from the user to the capture device 20. The following steps are performed successively for each pixel that is nominally believed that is part of the hand.
[00073] In step 242, the filter pixel classifier determines how many boundaries of the box are intersected. An intersection is where the image changes from a foreground (in the hand) to a background (not in the hand). For example, Fig. 11A shows a finger 276, a selected pixel 278 on the finger, and the box described above 280 around the pixel in a radius r. The box is intersected at two points along a single boundary; at points 281a and 281b. Points 281a, 281b are where the image changes from the foreground (finger) to the background. All pixels 278 that have two points of intersection with boundaries of their respective boxes 280 are considered fingertips (or part of the joint or arm as explained below) for the purposes of defining centroides of the hand as explained below.
[00074] In step 246, the pixel classifier filter determines whether the intersections are at the same or different limits. As seen in Fig. 1 IB, a finger can intersect box 280 along two adjacent boundaries instead of along the same boundary. This information will be used to determine the direction in which the finger is pointed as explained below.
[00075] Unlike a fingertip, a pixel that intersects your 280 box at four points will be considered a finger for the purpose of defining centroides of the hand as explained below. For example, Fig. 12 shows an example where the selected pixel 278 is sufficiently distal from the fingertip, that there are four points of intersection 281a, 281b, 281c and 281d with box 280.
[00076] In step 242 of the flowchart of Fig. 9, and in 264 of the decision tree of Fig. 10, the pixel classifier filter checks how many box limits 280 are intersected. If no boundary is intersected, the selected pixel is considered to be within the user's palm at 265. That is, because box size 280 is selected so that at least two boundaries are intersected if the pixel is located on a finger or fingertip, if the pixel is in the hand, and no boundary is intersected, the pixel is considered to be in the palm. If two boundaries are intersected, the filter goes to 266 to check whether the vertices of the non-intersected boundaries are solid (in the hand) or empty (background) as explained below. If four boundaries are intersected at 267, a finger is considered as explained above. If the boundaries of a 280 box are intersected six times out of 268, this is considered an invalid reading and is discarded (step 250).
[00077] Again with reference to 266, where two limits are intersected, this could be a fingertip, but it could also be a space between two adjacent fingers. Therefore, the pixel classifier filter checks the vertices of the non-intersecting limits (step 248). Where the vertices of non-intersecting boundaries are solid, this means that the box lies at hand at those vertices and the points of intersection define a valley between adjacent fingers. In contrast, where the vertices of non-intersecting boundaries are empty (as shown in the illustration associated with 266), this means that the box is located in background pixels at those vertices and the points of intersection define a part of the hand.
[00078] If the vertices are empty, the pixel classifier filter checks at 269 whether the distance, referred to as chord length, between the points of intersection is less than the maximum width of a finger (step 252). That is, where there are two points of intersection, this could be a fingertip as shown in Fig. 11A. However, the pixel could also be a part of the arm or part of the hand, such as the joint, as shown in Fig. 13. If so, the length of chord 282 could be greater than the maximum width of a finger. If so, the pixel 278 for which box 280 is being examined is said to be located on the arm or joint at 271 (Fig. 10).
[00079] In addition to identifying a fingertip or finger, an intersection of two points or four points can also reveal a direction in which the fingertip / finger is pointing. For example, in Fig. 11A, there were two intersections smaller than the maximum width of a finger, so it was determined that pixel 278 is located at a fingertip. However, given this intersection, the direction in which the fingertip is pointing can be inferred. The same can be said for the finger shown in Fig. 12. Fig. 11A shows the finger 276 pointing upwards. But the 276 fingertip may also be pointing upward in other directions. Information from other points near point 278 at the fingertip 276 can be used to obtain additional inferences about the direction.
[00080] Fig. 11B shows an intersection of two points, which provides additional inferences about the direction in which the finger / fingertip is pointing. That is, the direction can be inferred from the ratio of the distances to the shared vertex. In other words, the chord length between points 281a and 281b defines the hypotenuse of a triangle that also includes the sides between points 281a, 281b and the shared vertex. It can be inferred that the finger is pointing in a direction perpendicular to the hypotenuse.
[00081] It may happen that a hand is held with two fingers together, three fingers together, or four fingers together. Therefore, after the above steps are performed using box 280 for each pixel in hand, the process can be repeated using box 280 that is slightly larger than the maximum width of two fingers together, and then repeated again using box 280 that is slightly larger than the maximum width of three fingers together, etc.
[00082] Once the pixel classifier filter data is collected, the pixel classifier filter then tries to build a hand model of the data in step 258 (Fig. 9). There are small regions, or centroides identified such as, for example, regions that are a fingertip, and a region that is a palm, and a notion of the center of the palm from the segmentation of the hand. The classifier mechanism 198 then examines finger centroides not classified as fingertips, but due to the fact that they intersected at four points, they are classified as fingers. Directional orientation has also been identified for finger and fingertip regions. If a finger centroid aligns with a fingertip centroid, and they are in the correct relative location with each other, the algorithm connects those centroides as belonging to the same finger.
[00083] Next, the orientation of the finger region is used to project where the joint of that finger is believed to be, based on the size of the skeleton and how large a finger is believed to be. The size, position and orientations of any valleys identified between fingers can also be used to confirm the given hand model. Then, the projected position of the joint is connected to the palm. As a result of termination, the pixel classifier mechanism determines a hand model of the skeleton 284, two examples of which are shown in Fig. 14. The model, which can be referred to as a "reduced skeleton model of the hand tracking segments. related to the fingertips, joints that connect the hand and finger, and a central bone for the palm ", includes centroides of fingertips connected to the centroid of fingers, connected centroides of articulation, connected to a centroid of the palm. Data with respect to known geometry and possible positions of a hand from the known position of the arm can also be used to check or dispute the determined positions of the centroid positions of the fingertip, finger, joint and / or palm, as well as to discard centroid data that can be determined not to be part of a hand.
[00084] The above will build a hand model even if one or more parts of the hand are missing from the model. For example, a finger may have been covered, or too close to the user's body or the other hand to be detected. Or the user may not have a finger. The pixel rating filter will build a hand model using the finger and hand positions it detects.
[00085] Another filter that can be performed in addition to or in place of the pixel classification filter can be referred to as a curvature analysis filter. This filter focuses on the curvature along the boundaries of the segmented hand's silhouette to determine peaks and valleys in an attempt to differentiate fingers. With reference to the flowchart in Fig. 15, in step 286, starting with a first pixel, the eight surrounding pixels are examined to determine which is the next pixel in the hand. Therefore, each pixel is assigned a value between 0 and 7 for the connectivity between that pixel and the next. A chain of these numbers is built around the silhouette of the hand which provides the limits of the hand. These values can be converted to angles and contours around the hand in step 288 to provide a graph of contours and peaks of the hand, as shown in Fig. 16. These steps for generating contours and peaks of the hand are described, for example, in a publication by F. Leymarie, MD Levine, entitled "Curvature morphology", Computer Vision and Robotics Laboratory, McGill University, Montreal, Quebec, Canada, 1988, which is incorporated by reference in this document.
[00086] The peaks around the silhouette hand are identified in step 289, and each is analyzed with respect to various characteristics of the peak. A peak can be defined by a start point, a peak and an end point. These three points can form a triangle as explained below. The various characteristics of a peak that can be examined include, for example: - width of a peak; - maximum height of a given peak; - average height of curvature samples within a peak; - peak shape ratio (maximum height / average height); - peak area; - hand to peak distance; - elbow to hand direction (x, y and z); - product of crossing the peak direction and the direction of the arm (how small is the angle between the direction of the arm and the direction of the peak); and - product of crossing the vector between the starting point and the maximum point of the peak, and the vector between the maximum point and the end point.
[00087] This information can be performed using various machine learning techniques in step 290, such as, for example, a support vector machine, to differentiate between fingers and hand. Support vector machines are known and described, for example, in C. Cortes and V. Vapnik, entitled Support-Vector Networks, Machine Learning, 20 (3): 273 to 297, September 1995, and Vladimir N. Vapnik, titled The Nature of Statistical Learning Theory. Springer, New York, 1995, both of which are incorporated in their entirety by reference in this document. In the modalities, data with noise can be regularized using a Markov Hidden Model to maintain the state of the hands and filter without noise.
[00088] The filters described above can be referred to as silhouette filters in which they examine the data related to the silhouette of a hand. An additional filter that can be used is a histogram filter and is referred to as a depth filter in which it uses depth data to build a hand model. This filter can be used in addition to or in place of the filters described above, and can be particularly useful when a user has his hand pointed towards the image capture device 20.
[00089] In the histogram filter, a histogram of distances in the region of the hand can be constructed. For example, this histogram can include fifteen containers, where each container includes the number of points in the hand region whose distance in the Z direction (depth) from the point closest to the camera is within a certain distance range associated with that container. For example, the first container in this histogram may include the number of points in the hand region whose distance to the centroid of the hand is between 0 and 0.40 cm, the second container includes the number of points in the hand region whose distance to the centroid of the hand is between 0.40 and 0.80 centimeters, and so on. In this way, a vector can be constructed to encode the shape of the hand. These vectors can be further standardized based on the estimated body size, for example.
[00090] In another example approach, a histogram can be constructed based on the distances and / or angles of points in the hand region for a joint, bone segment or plane of the user's estimated skeleton palm, for example, the elbow joint , wrist joint, etc. Fig. 17 illustrates two graphs indicative of the histograms determined for a closed hand and an open hand.
[00091] It should be understood that the sample form descriptor examples are exemplary in nature and are not intended to limit the scope of this description. In general, any descriptor suitable for a region of the hand can be used alone or in combination with another and / or one of the example methods described above. For example, shape descriptors, such as the histograms or vectors described above, can be mixed and matched, combined, and / or concatenated into larger vectors, etc. this can allow the identification of new patterns that were not identifiable by looking at them in isolation. These filters can be augmented by using historical frame data, which can indicate whether an identified finger, for example, deviates too much from that finger identified in a previous frame.
[00092] Fig. 18 shows a supervisor filter to combine the results of several filters described above. For example, the pixel classifier filter can be used to produce a model of the hand and fingers. Further up, the pixel classifier, the curvature analysis filter, the depth histogram filter, and possibly other hand filters not shown in Fig. 19 can be processed as described above, and further processed, for example, by filtering. temporal consistency (for example, a low-pass filter) and smoothing techniques to produce hand and finger positions. As mentioned above, the silhouette used in the various filters described in this document can be scaled to be invariable in hand size and distance from the sensor by knowing the user's distance to the camera and inferred hand size from their analyzed skeleton.
[00093] In addition to open or closed hand states, the present technology can be used to identify specific finger orientations, such as, for example, pointing in a particular direction with one or more fingers. The technology can also be used to identify various hand positions oriented at various angles within the Cartesian space x, y, z.
[00094] In the modalities, several post-classification filtering steps can be used to increase the accuracy of the hand and finger position estimates in step 216 (Fig. 6). For example, a temporal consistency filtering step can be applied to predicted hand and finger positions between consecutive depth image frames to smooth out predictions and reduce temporal instability, for example, due to spurious hand movements, sensor noise, or occasional classification errors. That is, a plurality of hand and finger positions based on a plurality of depth images from the capture device or sensor can be estimated and temporal filtering of the plurality of estimates can be performed to estimate the hand and finger positions.
[00095] In step 220, the threaded execution of Fig. 6 can provide an answer for each frame based on the estimated state of the hand. For example, a command can be provided for a console of a computer system, such as console 12 of computer system 10. As another example, an answer can be provided for a display device, such as display device 16. In this way, movements user estimates, which include estimated hand states, can be translated into commands for a console 12 of system 10, so that the user can interact with the system as described above. In addition, the method and processes described above can be implemented to determine state estimates of any part of a user's body, for example, mouth, eyes, etc. For example, a posture for a user's body part can be estimated using the methods described above.
[00096] The present technology allows a wide variety of interactions with an NUI system such as, for example, shown in Figures 1A to 1C. There is a wide variety of natural interactions that are based on hand / finger movements, or combine both large body movements and detailed hand control that are desirable to create new recognized gestures, more immersive experiences and compelling games. These uses and interactions include, but are not limited to, the following: - Providing high-fidelity cursor positions - by recognizing and accurately tracking a pointing user's finger, the NUI system can accurately determine where a user is pointing at screen with respect to positioning a cursor (Fig. 1B). - Directional finger sighting - In general, accurate recognition and tracking of a user's finger or fingers can be used in any of a variety of ways to improve control and interaction with an NUI system and a game application or other application running in the NUI system. The recognition of various hand configurations can be used as recognized gestures such as, for example, but not limited to, counting on the fingers, thumb up, thumb down, the "OK" sign, the horns sign (finger indicator and minimum pointing up), the "hang loose" sign, the Star Trek® "long life and prosperity" sign, a single raised finger, and others. Each of these can be used to control user interface interaction. - Virtual buttons (with tactile feedback) - Accurate recognition and tracking of individual fingers allows applications to use a variety of virtual buttons, further enhancing the NUI experience. - Thumb and finger control - taking the guidance and reliable detection of the thumb from the fingers, the hand can act as a controller - thumb orientation that controls the orientation of the controller, pressing the thumb by hand is recognized as a press button. - Push to select - precise recognition and tracking of individual fingers allows applications to use a pinch motion between thumb and other finger to perform some control function or application metric. - Single / multiple finger directions - Accurate recognition and tracking of individual fingers allows applications to use relative finger positions as a control metric or to perform some other application metric. - Writing, drawing, sculpting - precise recognition and tracking of individual fingers allows applications to interpret a user holding a pencil or brush, and how that pencil or brush moves as a result of movement of individual fingers. The recognition of these movements allows a user to form letters, cursive writing, sculpt and / or draw images. - Typing - accurate recognition and tracking of individual fingers allows applications to perform typing movements that are interpreted by the NUI system or application as keystrokes on a virtual keyboard to type characters and words on the screen or to provide control or application information for the NUI system or application. - Track hand rotations - Accurate recognition and tracking of individual fingers allows applications to accurately identify hand rotation. - Manipulate puppet - map the finger skeleton to a puppet animation control system. Alternatively, mapping a finger skeleton can be used to directly manipulate a virtual object in the same way that a physical puppet is manipulated on a physical string. - Rotate a button or combination lock - Accurate recognition and tracking of individual gods allows a user to select to rotate a virtual button or open a virtual lock combination. This combination lock can be used to provide or deny access to the secure network or stored resources. - Shooting with a firearm - using finger and hand detection as a firearm controller - the index finger determines the aim and press your thumb like a button to indicate firing. - Waving gesture - detecting and using a waving gesture with loose fingers for virtual interaction. - Open palm gesture - Using an open palm to display a map view that means a modal shift between first person and third person view. An index finger can be used on the open palm (similar to a mouse, or touch screen) to navigate and navigate through virtual space. - Leg control - Using the index and middle finger (with the hand pointing down) to control a character's legs, simulating running, jumping and kicking actions. This gesture can be combined with the open palm gesture to signify a modal shift between full-body interactions and the user interface, or navigation. For example, in an adventure and action game a player can use full body controls to engage in combat, then use an open palm gesture to switch to view the map and use a middle and index finger to simulate runs across terrain.
[00097] Other finger and hand interactions are contemplated.
[00098] Fig. 19A illustrates an example modality of a computational environment that can be used to interpret one or more positions and movements of a user in a target tracking, analysis and recognition system. The computing environment such as the computing environment 12 described above with respect to Figures 1A to 2 can be a multimedia console 600, such as a game console. As shown in Fig. 19 A, the multimedia console 600 has a central processing unit (CPU) 601 that has a level 1 cache 602, a level 2 cache 604, and a flash ROM 606. The level 1 cache 602 and a cache level 2 604 stores data and consequently reduces the number of memory access cycles, thereby improving processing speed and capacity. CPU 601 can be provided having more than one core, and therefore additional level 1 and level 2 caches 602 and 604. Flash ROM 606 can store executable code that is loaded during an initial phase of an initialization process when the multimedia console 600 is ON.
[00099] A graphics processing unit (GPU) 608 and a video encoder / video codec (encoder / decoder) 614 form a chained execution of video processing for high-speed, high-resolution graphics processing. The data is transported from the GPU 608 to the video encoder / video codec 614 over a bus. The chained execution of video processing provides data to an A / V (audio / video) port 640 for transmission to a television or other display. A memory controller 610 is connected to GPU 608 to facilitate access by the processor to various types of memory 612, such as, but not limited to, RAM.
[000100] The multimedia console 600 includes an I / O controller 620, a system management controller 622, an audio processing unit 623, a network interface controller 624, a first USB host controller 626, a second USB host controller 628 and a subset of front panel I / O 630 that are preferably implemented in a 618 module. USB controllers 626 and 628 serve as hosts for peripheral controllers 642 (1) and 642 (2), an adapter wireless 648, and an external memory device 646 (for example, flash memory, external CD / DVD ROM control, removable media, etc.). The network interface 624 and / or wireless adapter 648 provide access to a network (for example, the Internet, home network, etc.) and can be any of a wide variety of components, multiple wired or wireless adapters that include a Ethernet card, modem, Bluetooth module, cable modem, and the like.
[000101] 643 system memory is provided to store application data that is loaded during the initialization process. A 644 media controller is provided and may comprise a DVD / CD controller, hard drive, or other removable media controller, etc. The 644 media controller can be internal or external to the 600 multimedia console. Application data can be accessed through the 644 media controller for execution, playback, etc. via the multimedia console 600. The media controller 644 is connected to the I / O controller 620 via a bus, such as a Serial ATA bus or other high-speed connection (for example, IEEE 1394).
[000102] The system management controller 622 provides a variety of service functions related to ensuring the availability of the multimedia console 600. The audio processing unit 623 and an audio codec 632 form a threaded execution of corresponding audio processing with high fidelity and stereo processing. The audio data is transported between the audio processing unit 623 and the audio codec 632 via a communication link. The threaded audio processing run provides data to the A / V 640 port for playback by an external audio player or device that has audio capabilities.
[000103] The front panel I / O subset 630 supports the functionality of the power button 650 and the eject button 652, as well as any LEDs (light-emitting diodes) or other indicators exposed on the outer surface of the multimedia console 600. A 636 system power supply module supplies power to the components of the multimedia console 600. A fan 638 cools the circuits inside the multimedia console 600.
[000104] CPU 601, GPU 608, controller memory 610, and several other components within multimedia console 600 are interconnected via one or more buses, which include serial and parallel buses, a memory bus, a peripheral bus , and a processor bus or location using any of a variety of bus architectures. For example, these architectures may include a Peripheral Component Interconnect (PCI) bus, PCI Express bus, etc.
[000105] When multimedia console 600 is turned ON, application data can be loaded from system memory 643 into memory 612 and / or caches 602, 604 and executed on CPU 601. The application can have a graphical user interface which provides a consistent user experience when navigating to different types of media available on the multimedia console 600. In operation, applications and / or other media contained within the 644 media controller can be started or played from the 644 media controller to provide additional features for the 600 multimedia con-sole.
[000106] The multimedia console 600 can be operated as a standalone system by simply connecting the system to a television or other display. In this standalone mode, the multimedia console 600 allows one or more users to interact with the system, watch movies, or listen to music. However, with the integration of broadband connectivity made available through the network interface 624 or wireless adapter 648, the multimedia console 600 can be additionally operated as a participant in a larger network community.
[000107] When the multimedia console 600 is turned ON, a certain amount of hardware resources are reserved for the system to use by the multimedia console's operating system. These resources can include a memory reserve (for example, 16MB), CPU and GPU cycles (for example, 5%), network bandwidth (for example, 8 kbs), etc. Because these resources are reserved at system startup time, the reserved resources do not exist from the view of the application.
[000108] In particular, the memory reserve is preferably large enough to contain the boot core, competing system applications and controls. The CPU reserve is preferably constant so that if the reserved CPU usage is not used by the system's applications, an inactive task will consume any unused cycles.
[000109] With respect to the GPU reservation, the light messages generated by the system applications (for example, popups) are displayed using a GPU interrupt to schedule code to display popup in an overlay. The amount of memory required for an overlay depends on the size of the overlay area and the preferred scales of overlay with the screen resolution. Where a complete user interface is used by the competing system application, it is preferable to use a resolution regardless of the application's resolution. A scaler can be used to determine this resolution in such a way that the need to change the frequency and resynchronize the TV is eliminated.
[000110] After the multimedia console 600 boots and system resources are reserved, competing system applications run to provide system functionality. The system's functionality is encapsulated in a set of system applications that run within the reserved system resources described above. The core of the operating system identifies tasks that are system application tasks versus game application tasks. System applications are preferably scheduled to run on CPU 601 at predetermined times and intervals to provide a consistent system resource view for the application. Scheduling is to minimize cache disruption for the game application that runs on the console.
[000111] When a competing system application requires audio, audio processing is scheduled asynchronously to the game application due to time sensitivity. A multimedia console application manager (described below) controls the audio level of the game application (for example, mute, attenuated) when system applications are active.
[000112] Input devices (for example, 642 (1) and 642 (2) controllers) are shared by game applications and system applications. Input devices are not reserved resources, but are to be switched between system applications and the game application in such a way that each will have a device focus. The application manager preferably controls the input flow switching, without knowledge of the game application knowledge and a controller maintains status information with respect to focus switches. Cameras 26, 28 and capture device 20 can define additional input devices for the console 600.
[000113] Fig. 19B illustrates another example modality of a computational environment 720 which can be the computational environment 12 shown in Figures 1A to 2 used to interpret one or more positions and movements in a tracking, analysis and target recognition system. The computer system environment 720 is just one example of a suitable computing environment and is not intended to suggest any limitations as to the scope of use or functionality of the object currently disclosed. Neither the computational environment 720 should be interpreted as having any dependency or requirement related to any one or a combination of components illustrated in the exemplary Operating Environment 720. In some modalities, the various computational elements represented may include circuits configured to instantiate specific aspects of the present description. . For example, the term circuits used in the description may include specialized hardware components configured to perform function (s) by firmware or switches. In other example embodiments, the term circuits may include a general purpose processing unit, memory, etc., configured by software instructions that incorporate operable logic to perform the function (s). In example modalities where circuits include a combination of hardware and software, an implementer can write logic embedded in source code and the source code can be compiled into machine-readable code that can be processed by the general purpose processing unit. Since a person skilled in the art can assess that the state of the art has evolved to a point where there is little difference between hardware, software, or a hardware / software combination, selecting hardware versus software to perform specific functions is a choice of project left to an implementer. More specifically, a person skilled in the art can assess that a software process can be transformed into an equivalent hardware structure, and a hardware structure itself can be transformed into an equivalent software process. Therefore, the selection of a hardware implementation versus a software implementation is a design choice and left to the implementer.
[000114] In Fig. 19B, the computing environment 720 comprises a computer 741, which typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by a 741 computer and includes both volatile and non-volatile media, removable and non-removable media. System 722 memory includes computer storage media in the form of volatile and / or non-volatile memory such as ROM 723 and RAM 760. A basic 724 input / output system (BIOS), containing basic routines that help transfer information between elements within computer 741, such as during initialization, are typically stored in ROM 723. RAM 760 typically contains data modules and / or programs that are immediately accessible to and / or currently being operated by processing unit 759. A By way of example, and not limitation, Fig. 19B illustrates operating system 725, application programs 726, other program modules 727, and program data 728. Fig. 19B additionally includes a graphics processor unit (GPU) 729 that has an associated video memory 730 for high-speed, high-resolution graphics processing and storage. The GPU 729 can be connected to the system bus 721 through a graphical interface 731.
[000115] Computer 741 may also include other removable / non-removable, volatile / non-volatile computer storage media. By way of example only, Fig. 19B illustrates a 738 hard disk controller that reads or writes to non-removable, non-volatile magnetic media, a 739 magnetic disk controller that reads or writes to a removable, non-volatile 754 magnetic disk, and an optical disk controller 740 that reads or writes to a removable, non-volatile optical disk 753 such as a CD ROM or other optical media. Other removable / non-removable, volatile / non-volatile computer storage media that can be used in the Exemplary Operating Environment includes, but is not limited to, magnetic tape cassette, flash memory cards, digital versatile disks, digital video tape, Solid-state RAM, solid-state ROM, and the like. The hard disk controller 738 is typically connected to the system bus 721 via a non-removable memory interface such as interface 734, and magnetic disk controller 739 and optical disk controller 740 are typically connected to the system bus 721 by a removable memory interface, such as the 735 interface.
[000116] The controllers and their associated computer storage media discussed above and illustrated in Fig. 19B, provide storage of computer-readable instructions, data structures, program modules and other data for computer 741. In Fig. 19B, for example, hard disk controller 738 is illustrated as storing operating system 758, application programs 757, other program modules 756, and program data 755. It should be noted that these components can either be the same as or different from the system. operating system 725, application programs 726, other program modules 727, and program data 728. Operating system 758, application programs 757, other program modules 756, and program data 755 are given different numbers here to illustrate that, at a minimum , they are different copies. A user can enter commands and information on computer 741 via input devices such as a keyboard 751 and a pointing device 752, commonly referred to as a mouse (mouse), ball control or touch panel. Other input devices (not shown) may include a handset, joystick, game controller, satellite dish, digitizer, or similar. These and other input devices are generally connected to the processing unit 759 via a user input interface 736 which is coupled to the system bus, but can be connected by other interface and bus structures, such as a parallel port, port game or a universal serial bus (USB). Cameras 26, 28 and capture device 20 can define additional input devices for the 700 console. A monitor 742 or other type of display device is also connected to the system bus 721 via an interface, such as a video interface 732 In addition to the monitor, computers can also include other peripheral output devices such as loudspeakers 744 and printers 743, which can be connected via an output peripheral interface 733.
[000117] Computer 741 can operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 746. Remote computer 746 can be a personal computer, a server, a router, a networked PC , a peer device or other common network node, and typically includes many or all of the elements described above relating to computer 741, although only one storage memory device 747 has been illustrated in Fig. 19B. The logical connections depicted in Fig. 19B include a local area network (LAN) 745 and a wide area network (WAN) 749, but it can also include other networks. These networked environments are commonplace in offices, corporate computer networks, intranets and the Internet.
[000118] When used in a LAN network environment, computer 741 is connected to LAN 745 through a 737 network interface or adapter. When used in a WAN network environment, computer 741 typically includes a 750 modem or other means to establish communications over WAN 749, such as the Internet. Modem 750, which can be internal or external, can be connected to system bus 721 via user input interface 736, or another appropriate mechanism. In a networked environment, pictured program modules relating to the 741 computer, or parts of it, can be stored on the remote memory storage device. As an example, and not a limitation, Fig. 19B illustrates remote application programs 748 as residing in memory device 747. It will be appreciated that the network connections shown are exemplary and other means can be used to establish a communications connection between the computers.
[000119] The above detailed description of the inventive system has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the inventive system to the precise form revealed. Many modifications and variations are possible in light of the above teachings. The described modalities were chosen in order to better explain the principles of the inventive system and its practical application to thus allow other individuals skilled in the art to make better use of the inventive system in various modalities and with various modifications as they are suitable for the particular use contemplated. It is understood that the scope of the inventive system is defined by the appended claims.

权利要求:
Claims (17)
[0001]
1. Method for generating a model of a user's hand (18) including one or more fingers, characterized by the fact that it comprises the steps: (a) receiving (200) position data representing a position from a user (18) which interacts with a sensor (20), in which the position data includes at least one of depth and image data representing the user's hand (18); and (b) analyzing (204) the position data to identify the user's hand (18) in the position data, step (b) including the steps of: (b1) analyzing depth data of the position data captured in the step (a) to segment (208) the position data into hand data, and (b2) extract (210) a set of characteristic descriptors by applying (216) one or more filters to the hand image data identified in step ( b1), the one or more filters that analyze image data of the hand when compared to image data outside a hand boundary to discern characteristics of the hand that includes a shape and orientation of the hand.
[0002]
2. Method, according to claim 1, characterized by the fact that it still comprises the steps of executing an application that receives commands through the sensor mechanism (20), and affecting a control action in the application based on an identified hand position in step (b).
[0003]
3. Method, according to claim 1, characterized by the fact that it still comprises the steps of executing an application that receives commands through the sensor mechanism (20), and affecting an action in the application of games based on an identified hand position in step (b).
[0004]
4. Method, according to claim 1, characterized by the fact that step (b1) comprises the step of analyzing centroides built from the image data to locate a best candidate for a hand.
[0005]
5. Method, according to claim 4, characterized by the fact that step (b1) still comprises the step of analyzing the best candidate in a hand to determine a best candidate in the center of the hand.
[0006]
6. Method, according to claim 1, characterized by the fact that step (b2) comprises the steps of applying a pixel classifier that includes the steps of: selecting pixels within a hand shape descriptor limit, constructing a predetermined size box around each pixel, each box built on a plane of the shape descriptor, determining points of intersection with each box where the image data changes between a foreground point and a background point, and identify hand and fingers from the analysis of the intersection points of each box for each pixel examined.
[0007]
7. Method, according to claim 1, characterized by the fact that step (b2) comprises the steps of applying a curvature analysis filter that includes the steps of: selecting pixels along a limit of the shape descriptor of hand, examine a plurality of pixels surrounding a selected pixel, and assign (286) a value to the selected pixel that indicates which surrounding pixel is also along a shape descriptor boundary, convert (288) the values into angles and contours around the hand including peaks and valleys, and determining (289) which of the peaks represent fingers of the hand.
[0008]
8. Method according to claim 1, characterized by the fact that step (b2) comprises the step of applying a histogram filter including the step of building a distance histogram between a plurality of points in the shape descriptor and a capturing the image data.
[0009]
9. System (10) for generating a model of a user's hand (18) including one or more fingers, the system including a sensor mechanism (20) operationally coupled to a computational device, the system characterized by the fact that it comprises: a skeleton recognition mechanism (192) for recognizing at least a part of a user's skeleton (18) from received data that includes at least one of image and depth data; an image segmentation mechanism (194) that segments one or more regions of the body into a region that represents a user's hand (18); and a descriptor extraction mechanism (196) for extracting representative data from a hand that includes one or more fingers and a hand orientation, wherein the descriptor extraction mechanism (196) applies a plurality of filters to analyze pixels in the region representing the hand, where each filter in the plurality of filters determines a position and orientation of the hand, where the descriptor extraction mechanism (196) combines the results of each filter to arrive at a better estimate of the position and orientation of the hand .
[0010]
10. System according to claim 9, characterized by the fact that the plurality of filters of the descriptor extraction mechanism (196) includes one or more filters optimized to identify the position and orientation of the hand as a silhouette relative to a device capturing the received data.
[0011]
11. System according to claim 9, characterized by the fact that the plurality of filters of the descriptor extraction mechanism (196) includes one or more filters optimized to identify the position and orientation of the hand when pointed in the direction or away of a device capturing the received data.
[0012]
12. System according to claim 9, characterized by the fact that the plurality of filters of the descriptor extraction mechanism (196) includes a classifier mechanism (198) to analyze a hand as a silhouette relative to the sensor mechanism (20) , in which the classifier mechanism (198) selects pixels within a region that represents a user's hand (18), build a box of predetermined size around each pixel, each box built on a plane of the silhouette, determine points of intersection with each box where the image data changes between a foreground point and a background point, and identify hand and fingers from the analysis of the intersection points of each box at each pixel examined.
[0013]
13. System according to claim 12, characterized by the fact that the classifier mechanism (198) identifies a centroid that represents a fingertip where two points of intersection are identified in a box and a distance between the points of intersection is too small to represent a palm.
[0014]
14. System according to claim 13, characterized by the fact that a location of the two points of intersection on the same or different sides of a box indicates an orientation of the identified finger tips.
[0015]
15. System, according to claim 12, characterized by the fact that the classification mechanism identifies a centroid representing a finger where four points of intersection are identified in a box.
[0016]
16. System, according to claim 12, characterized by the fact that the classification mechanism identifies a centroid representing a palm where two intersection points are identified in a box and the distance between the intersection points is too large for represent a fingertip.
[0017]
17. System, according to claim 12, characterized by the fact that the box built around a given pixel is a first box of a first size, the pixel classifier mechanism still building a second box around the given pixel of a second size larger than the first size to detect a condition where the fingers are close together.

类似技术:

---

公开号 | 公开日 | 专利标题

---

BR112013031118B1|2021-04-13|METHOD AND SYSTEM FOR GENERATING A USER'S HAND MODEL

---

US8929612B2|2015-01-06|System for recognizing an open or closed hand

---

US8660310B2|2014-02-25|Systems and methods for tracking a model

---

TWI497346B|2015-08-21|Human tracking system

---

US8891827B2|2014-11-18|Systems and methods for tracking a model

---

CA2753051C|2017-09-12|Virtual object manipulation

---

US8176442B2|2012-05-08|Living cursor control mechanics

---

US8457353B2|2013-06-04|Gestures and gesture modifiers for manipulating a user-interface

---

US9344707B2|2016-05-17|Probabilistic and constraint based articulated model fitting

---

US20120162065A1|2012-06-28|Skeletal joint recognition and tracking system

---

US20100303302A1|2010-12-02|Systems And Methods For Estimating An Occluded Body Part

---

WO2010126841A2|2010-11-04|Altering a view perspective within a display environment

---

US20120311503A1|2012-12-06|Gesture to trigger application-pertinent information

同族专利:

---

公开号 | 公开日

---

JP6021901B2|2016-11-09|

---

US20120309532A1|2012-12-06|

---

JP2014524070A|2014-09-18|

---

EP2718900A2|2014-04-16|

---

WO2012170349A3|2013-01-31|

---

KR20140024421A|2014-02-28|

---

KR101956325B1|2019-03-08|

---

RU2013154102A|2015-06-10|

---

EP2718900A4|2015-02-18|

---

CA2837470A1|2012-12-13|

---

US8897491B2|2014-11-25|

---

AU2012268589B2|2016-12-15|

---

WO2012170349A2|2012-12-13|

---

MX2013014393A|2014-03-21|

---

RU2605370C2|2016-12-20|

---

CA2837470C|2019-09-03|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

US4711543A|1986-04-14|1987-12-08|Blair Preston E|TV animation interactively controlled by the viewer|

---

US4695953A|1983-08-25|1987-09-22|Blair Preston E|TV animation interactively controlled by the viewer|

---

US4630910A|1984-02-16|1986-12-23|Robotic Vision Systems, Inc.|Method of measuring in three-dimensions at high speed|

---

US4627620A|1984-12-26|1986-12-09|Yang John P|Electronic athlete trainer for improving skills in reflex, speed and accuracy|

---

US4645458A|1985-04-15|1987-02-24|Harald Phillip|Athletic evaluation and training apparatus|

---

US4702475A|1985-08-16|1987-10-27|Innovating Training Products, Inc.|Sports technique and reaction training system|

---

US4843568A|1986-04-11|1989-06-27|Krueger Myron W|Real time perception of and response to the actions of an unencumbered participant/user|

---

US4796997A|1986-05-27|1989-01-10|Synthetic Vision Systems, Inc.|Method and system for high-speed, 3-D imaging of an object at a vision station|

---

US5184295A|1986-05-30|1993-02-02|Mann Ralph V|System and method for teaching physical skills|

---

US4751642A|1986-08-29|1988-06-14|Silva John M|Interactive sports simulation system with physiological sensing and psychological conditioning|

---

US4809065A|1986-12-01|1989-02-28|Kabushiki Kaisha Toshiba|Interactive system and related method for displaying data to produce a three-dimensional image of an object|

---

US4817950A|1987-05-08|1989-04-04|Goo Paul E|Video game control unit and attitude sensor|

---

US5239463A|1988-08-04|1993-08-24|Blair Preston E|Method and apparatus for player interaction with animated characters and objects|

---

US5239464A|1988-08-04|1993-08-24|Blair Preston E|Interactive video system providing repeated switching of multiple tracks of actions sequences|

---

US4901362A|1988-08-08|1990-02-13|Raytheon Company|Method of recognizing patterns|

---

US4893183A|1988-08-11|1990-01-09|Carnegie-Mellon University|Robotic vision system|

---

JPH02199526A|1988-10-14|1990-08-07|David G Capper|Control interface device|

---

US5469740A|1989-07-14|1995-11-28|Impulse Technology, Inc.|Interactive video testing and training system|

---

US4925189A|1989-01-13|1990-05-15|Braeunig Thomas F|Body-mounted video game exercise device|

---

US5229756A|1989-02-07|1993-07-20|Yamaha Corporation|Image control apparatus|

---

JPH03103822U|1990-02-13|1991-10-29|

---

US5101444A|1990-05-18|1992-03-31|Panacea, Inc.|Method and apparatus for high speed object location|

---

US5148154A|1990-12-04|1992-09-15|Sony Corporation Of America|Multi-dimensional user interface|

---

US5534917A|1991-05-09|1996-07-09|Very Vivid, Inc.|Video image based control system|

---

JPH0519957A|1991-07-15|1993-01-29|Nippon Telegr & Teleph Corp <Ntt>|Information inputting method|

---

US5295491A|1991-09-26|1994-03-22|Sam Technology, Inc.|Non-invasive human neurocognitive performance capability testing method and system|

---

US6054991A|1991-12-02|2000-04-25|Texas Instruments Incorporated|Method of modeling player position and movement in a virtual reality system|

---

CA2101633A1|1991-12-03|1993-06-04|Barry J. French|Interactive video testing and training system|

---

US5875108A|1991-12-23|1999-02-23|Hoffberg; Steven M.|Ergonomic man-machine interface incorporating adaptive pattern recognition based control system|

---

DE69204045T2|1992-02-07|1996-04-18|Ibm|Method and device for optical input of commands or data.|

---

US5417210A|1992-05-27|1995-05-23|International Business Machines Corporation|System and method for augmentation of endoscopic surgery|

---

JPH07325934A|1992-07-10|1995-12-12|Walt Disney Co:The|Method and equipment for provision of graphics enhanced to virtual world|

---

US5999908A|1992-08-06|1999-12-07|Abelow; Daniel H.|Customer-based product design module|

---

US5320538A|1992-09-23|1994-06-14|Hughes Training, Inc.|Interactive aircraft training system and method|

---

IT1257294B|1992-11-20|1996-01-12|DEVICE SUITABLE TO DETECT THE CONFIGURATION OF A PHYSIOLOGICAL-DISTAL UNIT, TO BE USED IN PARTICULAR AS AN ADVANCED INTERFACE FOR MACHINES AND CALCULATORS.|

---

US5495576A|1993-01-11|1996-02-27|Ritchey; Kurtis J.|Panoramic image based virtual reality/telepresence audio-visual system and method|

---

US5690582A|1993-02-02|1997-11-25|Tectrix Fitness Equipment, Inc.|Interactive exercise apparatus|

---

JP2799126B2|1993-03-26|1998-09-17|株式会社ナムコ|Video game device and game input device|

---

US5405152A|1993-06-08|1995-04-11|The Walt Disney Company|Method and apparatus for an interactive video game with physical feedback|

---

US5454043A|1993-07-30|1995-09-26|Mitsubishi Electric Research Laboratories, Inc.|Dynamic and static hand gesture recognition through low-level image analysis|

---

US5423554A|1993-09-24|1995-06-13|Metamedia Ventures, Inc.|Virtual reality game method and apparatus|

---

US5980256A|1993-10-29|1999-11-09|Carmein; David E. E.|Virtual reality system with enhanced sensory apparatus|

---

JP3419050B2|1993-11-19|2003-06-23|株式会社日立製作所|Input device|

---

US5347306A|1993-12-17|1994-09-13|Mitsubishi Electric Research Laboratories, Inc.|Animated electronic meeting place|

---

JP2552427B2|1993-12-28|1996-11-13|コナミ株式会社|Tv play system|

---

US5577981A|1994-01-19|1996-11-26|Jarvik; Robert|Virtual reality exercise machine and computer controlled video system|

---

US5580249A|1994-02-14|1996-12-03|Sarcos Group|Apparatus for simulating mobility of a human|

---

US5597309A|1994-03-28|1997-01-28|Riess; Thomas|Method and apparatus for treatment of gait problems associated with parkinson's disease|

---

US5385519A|1994-04-19|1995-01-31|Hsu; Chi-Hsueh|Running machine|

---

US5524637A|1994-06-29|1996-06-11|Erickson; Jon W.|Interactive system for measuring physiological exertion|

---

JPH0844490A|1994-07-28|1996-02-16|Matsushita Electric Ind Co Ltd|Interface device|

---

US5563988A|1994-08-01|1996-10-08|Massachusetts Institute Of Technology|Method and system for facilitating wireless, full-body, real-time user interaction with a digitally represented visual environment|

---

US6714665B1|1994-09-02|2004-03-30|Sarnoff Corporation|Fully automated iris recognition system utilizing wide and narrow fields of view|

---

US5516105A|1994-10-06|1996-05-14|Exergame, Inc.|Acceleration activated joystick|

---

US5638300A|1994-12-05|1997-06-10|Johnson; Lee E.|Golf swing analysis system|

---

JPH08161292A|1994-12-09|1996-06-21|Matsushita Electric Ind Co Ltd|Method and system for detecting congestion degree|

---

US5594469A|1995-02-21|1997-01-14|Mitsubishi Electric Information Technology Center America Inc.|Hand gesture machine control system|

---

US5682229A|1995-04-14|1997-10-28|Schwartz Electro-Optics, Inc.|Laser range camera|

---

US5913727A|1995-06-02|1999-06-22|Ahdoot; Ned|Interactive movement and contact simulation game|

---

WO1996041304A1|1995-06-07|1996-12-19|The Trustees Of Columbia University In The City Of New York|Apparatus and methods for determining the three-dimensional shape of an object using active illumination and relative blurring in two images due to defocus|

---

US5682196A|1995-06-22|1997-10-28|Actv, Inc.|Three-dimensional video presentation system providing interactive 3D presentation with personalized audio responses for multiple viewers|

---

US5702323A|1995-07-26|1997-12-30|Poulton; Craig K.|Electronic exercise enhancer|

---

US6430997B1|1995-11-06|2002-08-13|Trazer Technologies, Inc.|System and method for tracking and assessing movement skills in multidimensional space|

---

US6073489A|1995-11-06|2000-06-13|French; Barry J.|Testing and training system for assessing the ability of a player to complete a task|

---

EP1059970A2|1998-03-03|2000-12-20|Arena, Inc,|System and method for tracking and assessing movement skills in multidimensional space|

---

US6308565B1|1995-11-06|2001-10-30|Impulse Technology Ltd.|System and method for tracking and assessing movement skills in multidimensional space|

---

US6098458A|1995-11-06|2000-08-08|Impulse Technology, Ltd.|Testing and training system for assessing movement and agility skills without a confining field|

---

US5933125A|1995-11-27|1999-08-03|Cae Electronics, Ltd.|Method and apparatus for reducing instability in the display of a virtual environment|

---

US5641288A|1996-01-11|1997-06-24|Zaenglein, Jr.; William G.|Shooting simulating process and training device using a virtual reality display screen|

---

CA2253626A1|1996-05-08|1997-11-13|Bruce R. Bacon|Real time simulation using position sensing|

---

US6173066B1|1996-05-21|2001-01-09|Cybernet Systems Corporation|Pose determination and tracking by matching 3D objects to a 2D sensor|

---

US5989157A|1996-08-06|1999-11-23|Walton; Charles A.|Exercising system with electronic inertial game playing|

---

RU2107328C1|1996-08-14|1998-03-20|Нурахмед Нурисламович Латыпов|Method for tracing and displaying of position and orientation of user in three-dimensional space and device which implements said method|

---

EP0959444A4|1996-08-14|2005-12-07|Nurakhmed Nurislamovic Latypov|Method for following and imaging a subject's three-dimensional position and orientation, method for presenting a virtual space to a subject, and systems for implementing said methods|

---

JP3064928B2|1996-09-20|2000-07-12|日本電気株式会社|Subject extraction method|

---

DE69626208T2|1996-12-20|2003-11-13|Hitachi Europ Ltd|Method and system for recognizing hand gestures|

---

US6009210A|1997-03-05|1999-12-28|Digital Equipment Corporation|Hands-free interface to a virtual reality environment using head tracking|

---

US6100896A|1997-03-24|2000-08-08|Mitsubishi Electric Information Technology Center America, Inc.|System for designing graphical multi-participant environments|

---

US5877803A|1997-04-07|1999-03-02|Tritech Mircoelectronics International, Ltd.|3-D image detector|

---

US6215898B1|1997-04-15|2001-04-10|Interval Research Corporation|Data processing system and method|

---

JP3077745B2|1997-07-31|2000-08-14|日本電気株式会社|Data processing method and apparatus, information storage medium|

---

US6188777B1|1997-08-01|2001-02-13|Interval Research Corporation|Method and apparatus for personnel detection and tracking|

---

US6289112B1|1997-08-22|2001-09-11|International Business Machines Corporation|System and method for determining block direction in fingerprint images|

---

US6720949B1|1997-08-22|2004-04-13|Timothy R. Pryor|Man machine interfaces and applications|

---

AUPO894497A0|1997-09-02|1997-09-25|Xenotech Research Pty Ltd|Image processing method and apparatus|

---

EP0905644A3|1997-09-26|2004-02-25|Matsushita Electric Industrial Co., Ltd.|Hand gesture recognizing device|

---

US6141463A|1997-10-10|2000-10-31|Electric Planet Interactive|Method and system for estimating jointed-figure configurations|

---

US6130677A|1997-10-15|2000-10-10|Electric Planet, Inc.|Interactive computer vision system|

---

US6101289A|1997-10-15|2000-08-08|Electric Planet, Inc.|Method and apparatus for unencumbered capture of an object|

---

AU9808298A|1997-10-15|1999-05-03|Electric Planet, Inc.|A system and method for generating an animatable character|

---

AU1099899A|1997-10-15|1999-05-03|Electric Planet, Inc.|Method and apparatus for performing a clean background subtraction|

---

US6072494A|1997-10-15|2000-06-06|Electric Planet, Inc.|Method and apparatus for real-time gesture recognition|

---

US6176782B1|1997-12-22|2001-01-23|Philips Electronics North America Corp.|Motion-based command generation technology|

---

US6181343B1|1997-12-23|2001-01-30|Philips Electronics North America Corp.|System and method for permitting three-dimensional navigation through a virtual reality environment using camera-based gesture inputs|

---

US6159100A|1998-04-23|2000-12-12|Smith; Michael D.|Virtual reality game|

---

US6077201A|1998-06-12|2000-06-20|Cheng; Chau-Yang|Exercise bicycle|

---

US6801637B2|1999-08-10|2004-10-05|Cybernet Systems Corporation|Optical body tracker|

---

US7121946B2|1998-08-10|2006-10-17|Cybernet Systems Corporation|Real-time head tracking system for computer games and other applications|

---

US7036094B1|1998-08-10|2006-04-25|Cybernet Systems Corporation|Behavior recognition system|

---

US6950534B2|1998-08-10|2005-09-27|Cybernet Systems Corporation|Gesture-controlled interfaces for self-service machines and other applications|

---

US20010008561A1|1999-08-10|2001-07-19|Paul George V.|Real-time object tracking system|

---

US7050606B2|1999-08-10|2006-05-23|Cybernet Systems Corporation|Tracking and gesture recognition system particularly suited to vehicular control applications|

---

US6681031B2|1998-08-10|2004-01-20|Cybernet Systems Corporation|Gesture-controlled interfaces for self-service machines and other applications|

---

IL126284A|1998-09-17|2002-12-01|Netmor Ltd|System and method for three dimensional positioning and tracking|

---

EP0991011B1|1998-09-28|2007-07-25|Matsushita Electric Industrial Co., Ltd.|Method and device for segmenting hand gestures|

---

US6661918B1|1998-12-04|2003-12-09|Interval Research Corporation|Background estimation and segmentation based on range and color|

---

US6147678A|1998-12-09|2000-11-14|Lucent Technologies Inc.|Video hand image-three-dimensional computer interface with multiple degrees of freedom|

---

WO2000036372A1|1998-12-16|2000-06-22|3Dv Systems, Ltd.|Self gating photosurface|

---

US6570555B1|1998-12-30|2003-05-27|Fuji Xerox Co., Ltd.|Method and apparatus for embodied conversational characters with multimodal input/output in an interface device|

---

US6363160B1|1999-01-22|2002-03-26|Intel Corporation|Interface using pattern recognition and tracking|

---

US7003134B1|1999-03-08|2006-02-21|Vulcan Patents Llc|Three dimensional object pose estimation which employs dense depth information|

---

US6299308B1|1999-04-02|2001-10-09|Cybernet Systems Corporation|Low-cost non-imaging eye tracker system for computer control|

---

US6503195B1|1999-05-24|2003-01-07|University Of North Carolina At Chapel Hill|Methods and systems for real-time structured light depth extraction and endoscope using real-time structured light depth extraction|

---

US6476834B1|1999-05-28|2002-11-05|International Business Machines Corporation|Dynamic creation of selectable items on surfaces|

---

US6873723B1|1999-06-30|2005-03-29|Intel Corporation|Segmenting three-dimensional video images using stereo|

---

US6738066B1|1999-07-30|2004-05-18|Electric Plant, Inc.|System, method and article of manufacture for detecting collisions between video images generated by a camera and an object depicted on a display|

---

US7113918B1|1999-08-01|2006-09-26|Electric Planet, Inc.|Method for video enabled electronic commerce|

---

US6663491B2|2000-02-18|2003-12-16|Namco Ltd.|Game apparatus, storage medium and computer program that adjust tempo of sound|

---

US6633294B1|2000-03-09|2003-10-14|Seth Rosenthal|Method and apparatus for using captured high density motion for animation|

---

US6624833B1|2000-04-17|2003-09-23|Lucent Technologies Inc.|Gesture-based input interface system with shadow detection|

---

EP1152261A1|2000-04-28|2001-11-07|CSEM Centre Suisse d'Electronique et de Microtechnique SA|Device and method for spatially resolved photodetection and demodulation of modulated electromagnetic waves|

---

US6640202B1|2000-05-25|2003-10-28|International Business Machines Corporation|Elastic sensor mesh system for 3-dimensional measurement, mapping and kinematics applications|

---

US6731799B1|2000-06-01|2004-05-04|University Of Washington|Object segmentation with background extraction and moving boundary techniques|

---

US6788809B1|2000-06-30|2004-09-07|Intel Corporation|System and method for gesture recognition in three dimensions using stereo imaging and color vision|

---

US7227526B2|2000-07-24|2007-06-05|Gesturetek, Inc.|Video-based image control system|

---

US7058204B2|2000-10-03|2006-06-06|Gesturetek, Inc.|Multiple camera control system|

---

US7039676B1|2000-10-31|2006-05-02|International Business Machines Corporation|Using video image analysis to automatically transmit gestures over a network in a chat or instant messaging session|

---

US6539931B2|2001-04-16|2003-04-01|Koninklijke Philips Electronics N.V.|Ball throwing assistant|

---

US7348963B2|2002-05-28|2008-03-25|Reactrix Systems, Inc.|Interactive video display system|

---

US7170492B2|2002-05-28|2007-01-30|Reactrix Systems, Inc.|Interactive video display system|

---

US8035612B2|2002-05-28|2011-10-11|Intellectual Ventures Holding 67 Llc|Self-contained interactive video display system|

---

US7259747B2|2001-06-05|2007-08-21|Reactrix Systems, Inc.|Interactive video display system|

---

US7710391B2|2002-05-28|2010-05-04|Matthew Bell|Processing an image utilizing a spatially varying pattern|

---

JP3420221B2|2001-06-29|2003-06-23|株式会社コナミコンピュータエンタテインメント東京|GAME DEVICE AND PROGRAM|

---

US7274800B2|2001-07-18|2007-09-25|Intel Corporation|Dynamic gesture recognition from stereo sequences|

---

US6937742B2|2001-09-28|2005-08-30|Bellsouth Intellectual Property Corporation|Gesture activated home appliance|

---

US7340077B2|2002-02-15|2008-03-04|Canesta, Inc.|Gesture recognition system using depth perceptive sensors|

---

JP2005526971A|2002-04-19|2005-09-08|アイイーイー インターナショナル エレクトロニクス アンド エンジニアリング エス．エイ．|Vehicle safety device|

---

US7489812B2|2002-06-07|2009-02-10|Dynamic Digital Depth Research Pty Ltd.|Conversion and encoding techniques|

---

US7576727B2|2002-12-13|2009-08-18|Matthew Bell|Interactive directed light/sound system|

---

JP4235729B2|2003-02-03|2009-03-11|国立大学法人静岡大学|Distance image sensor|

---

US8745541B2|2003-03-25|2014-06-03|Microsoft Corporation|Architecture for controlling a computer using hand gestures|

---

EP1477924B1|2003-03-31|2007-05-02|HONDA MOTOR CO., Ltd.|Gesture recognition apparatus, method and program|

---

WO2004107266A1|2003-05-29|2004-12-09|Honda Motor Co., Ltd.|Visual tracking using depth data|

---

US8072470B2|2003-05-29|2011-12-06|Sony Computer Entertainment Inc.|System and method for providing a real-time three-dimensional interactive environment|

---

US7620202B2|2003-06-12|2009-11-17|Honda Motor Co., Ltd.|Target orientation estimation using depth sensing|

---

WO2005041579A2|2003-10-24|2005-05-06|Reactrix Systems, Inc.|Method and system for processing captured image information in an interactive video display system|

---

CN100573548C|2004-04-15|2009-12-23|格斯图尔泰克股份有限公司|The method and apparatus of tracking bimanual movements|

---

US7308112B2|2004-05-14|2007-12-11|Honda Motor Co., Ltd.|Sign based human-machine interaction|

---

US7704135B2|2004-08-23|2010-04-27|Harrison Jr Shelton E|Integrated game system, method, and device|

---

KR20060070280A|2004-12-20|2006-06-23|한국전자통신연구원|Apparatus and its method of user interface using hand gesture recognition|

---

US7430312B2|2005-01-07|2008-09-30|Gesturetek, Inc.|Creating 3D images of objects by illuminating with infrared patterns|

---

US7379566B2|2005-01-07|2008-05-27|Gesturetek, Inc.|Optical flow based tilt sensor|

---

HUE049974T2|2005-01-07|2020-11-30|Qualcomm Inc|Detecting and tracking objects in images|

---

US7598942B2|2005-02-08|2009-10-06|Oblong Industries, Inc.|System and method for gesture based control system|

---

US7317836B2|2005-03-17|2008-01-08|Honda Motor Co., Ltd.|Pose estimation based on critical point analysis|

---

WO2006124935A2|2005-05-17|2006-11-23|Gesturetek, Inc.|Orientation-sensitive signal output|

---

AT412882T|2005-08-12|2008-11-15|Mesa Imaging Ag|HIGHLY SENSITIVE, FAST PIXEL FOR APPLICATION IN AN IMAGE SENSOR|

---

US20080026838A1|2005-08-22|2008-01-31|Dunstan James E|Multi-player non-role-playing virtual world games: method for two-way interaction between participants and multi-player virtual world games|

---

US7450736B2|2005-10-28|2008-11-11|Honda Motor Co., Ltd.|Monocular tracking of 3D human motion with a coordinated mixture of factor analyzers|

---

JP2007134913A|2005-11-09|2007-05-31|Matsushita Electric Ind Co Ltd|Method and device for selecting image|

---

US7701439B2|2006-07-13|2010-04-20|Northrop Grumman Corporation|Gesture recognition simulation system and method|

---

JP5395323B2|2006-09-29|2014-01-22|ブレインビジョン株式会社|Solid-state image sensor|

---

US7412077B2|2006-12-29|2008-08-12|Motorola, Inc.|Apparatus and methods for head pose estimation and head gesture detection|

---

US8144148B2|2007-02-08|2012-03-27|Edge 3 Technologies Llc|Method and system for vision-based interaction in a virtual environment|

---

US7729530B2|2007-03-03|2010-06-01|Sergey Antonov|Method and apparatus for 3-D data input to a personal computer with a multimedia oriented operating system|

---

TW200907764A|2007-08-01|2009-02-16|Unique Instr Co Ltd|Three-dimensional virtual input and simulation apparatus|

---

US7852262B2|2007-08-16|2010-12-14|Cybernet Systems Corporation|Wireless mobile indoor/outdoor tracking system|

---

US7970176B2|2007-10-02|2011-06-28|Omek Interactive, Inc.|Method and system for gesture classification|

---

CN101254344B|2008-04-18|2010-06-16|李刚|Game device of field orientation corresponding with display screen dot array in proportion and method|

---

KR100931403B1|2008-06-25|2009-12-11|한국과학기술연구원|Device and information controlling system on network using hand gestures|

---

JP2010072840A|2008-09-17|2010-04-02|Denso Corp|Image display method, image display device, and operation device using the same|

---

US8379987B2|2008-12-30|2013-02-19|Nokia Corporation|Method, apparatus and computer program product for providing hand segmentation for gesture analysis|

---

JP5177075B2|2009-02-12|2013-04-03|ソニー株式会社|Motion recognition device, motion recognition method, and program|

---

US8744121B2|2009-05-29|2014-06-03|Microsoft Corporation|Device for identifying and tracking multiple humans over time|

---

US8542252B2|2009-05-29|2013-09-24|Microsoft Corporation|Target digitization, extraction, and tracking|

---

US20110025689A1|2009-07-29|2011-02-03|Microsoft Corporation|Auto-Generating A Visual Representation|

---

US8843857B2|2009-11-19|2014-09-23|Microsoft Corporation|Distance scalable no touch computing|US20110254765A1|2010-04-18|2011-10-20|Primesense Ltd.|Remote text input using handwriting|

---

US8639020B1|2010-06-16|2014-01-28|Intel Corporation|Method and system for modeling subjects from a depth map|

---

CN103155003B|2010-10-08|2016-09-28|松下电器产业株式会社|Posture estimation device and posture estimation method|

---

US9857868B2|2011-03-19|2018-01-02|The Board Of Trustees Of The Leland Stanford Junior University|Method and system for ergonomic touch-free interface|

---

US8840466B2|2011-04-25|2014-09-23|Aquifi, Inc.|Method and system to create three-dimensional mapping in a two-dimensional game|

---

JP5670255B2|2011-05-27|2015-02-18|京セラ株式会社|Display device|

---

JP6074170B2|2011-06-23|2017-02-01|インテル・コーポレーション|Short range motion tracking system and method|

---

US11048333B2|2011-06-23|2021-06-29|Intel Corporation|System and method for close-range movement tracking|

---

JP5864144B2|2011-06-28|2016-02-17|京セラ株式会社|Display device|

---

US8854433B1|2012-02-03|2014-10-07|Aquifi, Inc.|Method and system enabling natural user interface gestures with an electronic system|

---

US9292089B1|2011-08-24|2016-03-22|Amazon Technologies, Inc.|Gestural object selection|

---

WO2013056431A1|2011-10-18|2013-04-25|Nokia Corporation|Methods and apparatuses for gesture recognition|

---

US9628843B2|2011-11-21|2017-04-18|Microsoft Technology Licensing, Llc|Methods for controlling electronic devices using gestures|

---

US9292767B2|2012-01-05|2016-03-22|Microsoft Technology Licensing, Llc|Decision tree computation in hardware utilizing a physically distinct integrated circuit with on-chip memory and a reordering of data to be grouped|

---

US8782565B2|2012-01-12|2014-07-15|Cisco Technology, Inc.|System for selecting objects on display|

---

US8836768B1|2012-09-04|2014-09-16|Aquifi, Inc.|Method and system enabling natural user interface gestures with user wearable glasses|

---

US9734393B2|2012-03-20|2017-08-15|Facebook, Inc.|Gesture-based control system|

---

US8933912B2|2012-04-02|2015-01-13|Microsoft Corporation|Touch sensitive user interface with three dimensional input sensor|

---

US10477184B2|2012-04-04|2019-11-12|Lifetouch Inc.|Photography system with depth and position detection|

---

US9477303B2|2012-04-09|2016-10-25|Intel Corporation|System and method for combining three-dimensional tracking with a three-dimensional display for a user interface|

---

US9747306B2|2012-05-25|2017-08-29|Atheer, Inc.|Method and apparatus for identifying input features for later recognition|

---

US9111135B2|2012-06-25|2015-08-18|Aquifi, Inc.|Systems and methods for tracking human hands using parts based template matching using corresponding pixels in bounded regions of a sequence of frames that are a specified distance interval from a reference camera|

---

US9098739B2|2012-06-25|2015-08-04|Aquifi, Inc.|Systems and methods for tracking human hands using parts based template matching|

---

US20140007019A1|2012-06-29|2014-01-02|Nokia Corporation|Method and apparatus forrelated user inputs|

---

US20140022171A1|2012-07-19|2014-01-23|Omek Interactive, Ltd.|System and method for controlling an external system using a remote device with a depth sensor|

---

US20140073383A1|2012-09-12|2014-03-13|Industrial Technology Research Institute|Method and system for motion comparison|

---

US9658695B2|2012-11-08|2017-05-23|Cuesta Technology Holdings, Llc|Systems and methods for alternative control of touch-based devices|

---

US9671874B2|2012-11-08|2017-06-06|Cuesta Technology Holdings, Llc|Systems and methods for extensions to alternative control of touch-based devices|

---

EP2924652A4|2012-11-22|2016-10-19|Fujitsu Ltd|Information processing device, body part determination program and body part determination method|

---

US10126820B1|2012-11-29|2018-11-13|Amazon Technologies, Inc.|Open and closed hand detection|

---

US9129155B2|2013-01-30|2015-09-08|Aquifi, Inc.|Systems and methods for initializing motion tracking of human hands using template matching within bounded regions determined using a depth map|

---

US9092665B2|2013-01-30|2015-07-28|Aquifi, Inc|Systems and methods for initializing motion tracking of human hands|

---

JP6048189B2|2013-02-08|2016-12-21|株式会社リコー|Projection system, image generation program, information processing apparatus, and image generation method|

---

US9201499B1|2013-02-11|2015-12-01|Amazon Technologies, Inc.|Object tracking in a 3-dimensional environment|

---

US9052746B2|2013-02-15|2015-06-09|Microsoft Technology Licensing, Llc|User center-of-mass and mass distribution extraction using depth images|

---

US8994652B2|2013-02-15|2015-03-31|Intel Corporation|Model-based multi-hypothesis target tracker|

---

US9275277B2|2013-02-22|2016-03-01|Kaiser Foundation Hospitals|Using a combination of 2D and 3D image data to determine hand features information|

---

US20140245200A1|2013-02-25|2014-08-28|Leap Motion, Inc.|Display control with gesture-selectable control paradigms|

---

US9135516B2|2013-03-08|2015-09-15|Microsoft Technology Licensing, Llc|User body angle, curvature and average extremity positions extraction using depth images|

---

US9092657B2|2013-03-13|2015-07-28|Microsoft Technology Licensing, Llc|Depth image processing|

---

US9159140B2|2013-03-14|2015-10-13|Microsoft Technology Licensing, Llc|Signal analysis for repetition detection and analysis|

---

US9142034B2|2013-03-14|2015-09-22|Microsoft Technology Licensing, Llc|Center of mass state vector for analyzing user motion in 3D images|

---

US9298266B2|2013-04-02|2016-03-29|Aquifi, Inc.|Systems and methods for implementing three-dimensionalgesture based graphical user interfacesthat incorporate gesture reactive interface objects|

---

KR101436050B1|2013-06-07|2014-09-02|한국과학기술연구원|Method of establishing database including hand shape depth images and method and device of recognizing hand shapes|

---

US9144744B2|2013-06-10|2015-09-29|Microsoft Corporation|Locating and orienting device in space|

---

US9934451B2|2013-06-25|2018-04-03|Microsoft Technology Licensing, Llc|Stereoscopic object detection leveraging assumed distance|

---

US9208566B2|2013-08-09|2015-12-08|Microsoft Technology Licensing, Llc|Speckle sensing for motion tracking|

---

KR102216124B1|2013-09-06|2021-02-16|삼성전자주식회사|Method and apparatus for processing images|

---

US9405375B2|2013-09-13|2016-08-02|Qualcomm Incorporated|Translation and scale invariant features for gesture recognition|

---

TWI499966B|2013-10-08|2015-09-11|Univ Nat Taiwan Science Tech|Interactive operation method of electronic apparatus|

---

RU2013148582A|2013-10-30|2015-05-10|ЭлЭсАй Корпорейшн|IMAGE PROCESSING PROCESSOR CONTAINING A GESTURE RECOGNITION SYSTEM WITH A COMPUTER-EFFECTIVE FIXED HAND POSITION RECOGNITION|

---

US20150139487A1|2013-11-21|2015-05-21|Lsi Corporation|Image processor with static pose recognition module utilizing segmented region of interest|

---

US9507417B2|2014-01-07|2016-11-29|Aquifi, Inc.|Systems and methods for implementing head tracking based graphical user interfacesthat incorporate gesture reactive interface objects|

---

US9619105B1|2014-01-30|2017-04-11|Aquifi, Inc.|Systems and methods for gesture based interaction with viewpoint dependent user interfaces|

---

JP6165650B2|2014-02-14|2017-07-19|株式会社ソニー・インタラクティブエンタテインメント|Information processing apparatus and information processing method|

---

WO2015126392A1|2014-02-20|2015-08-27|Hewlett-Packard Development Company, L.P.|Emulating a user performing spatial gestures|

---

US9436872B2|2014-02-24|2016-09-06|Hong Kong Applied Science and Technology Research Institute Company Limited|System and method for detecting and tracking multiple parts of an object|

---

US9618618B2|2014-03-10|2017-04-11|Elwha Llc|Systems and methods for ultrasonic position and motion detection|

---

RU2014113049A|2014-04-03|2015-10-10|ЭлЭсАй Корпорейшн|IMAGE PROCESSOR CONTAINING A GESTURE RECOGNITION SYSTEM WITH OBJECT TRACKING ON THE BASIS OF COMPUTING SIGNS OF CIRCUITS FOR TWO OR MORE OBJECTS|

---

US9739883B2|2014-05-16|2017-08-22|Elwha Llc|Systems and methods for ultrasonic velocity and acceleration detection|

---

US9424490B2|2014-06-27|2016-08-23|Microsoft Technology Licensing, Llc|System and method for classifying pixels|

---

US20160014395A1|2014-07-10|2016-01-14|Arete Associates|Data fusion processing to identify obscured objects|

---

KR101515845B1|2014-08-07|2015-05-04|스타십벤딩머신 주식회사|Method and device for gesture recognition|

---

US9811721B2|2014-08-15|2017-11-07|Apple Inc.|Three-dimensional hand tracking using depth sequences|

---

US9437002B2|2014-09-25|2016-09-06|Elwha Llc|Systems and methods for a dual modality sensor system|

---

US10459615B2|2014-12-11|2019-10-29|Rdi Technologies, Inc.|Apparatus and method for analyzing periodic motions in machinery|

---

US10062411B2|2014-12-11|2018-08-28|Jeffrey R. Hay|Apparatus and method for visualizing periodic motions in mechanical components|

---

CN104571510B|2014-12-30|2018-05-04|青岛歌尔声学科技有限公司|A kind of system and method that gesture is inputted in 3D scenes|

---

US10482670B2|2014-12-30|2019-11-19|Qingdao Goertek Technology Co., Ltd.|Method for reproducing object in 3D scene and virtual reality head-mounted device|

---

US9344615B1|2015-01-26|2016-05-17|International Business Machines Corporation|Discriminating visual recognition program for digital cameras|

---

KR101683189B1|2015-02-09|2016-12-06|선문대학교산학협력단|Paired-edge based hand detection method using depth image|

---

CN107533366B|2015-04-20|2020-07-03|三菱电机株式会社|Information display device and information display method|

---

US10254881B2|2015-06-29|2019-04-09|Qualcomm Incorporated|Ultrasonic touch sensor-based virtual button|

---

US10318798B2|2015-07-10|2019-06-11|Booz Allen Hamilton Inc.|Device and method for detecting non-visible content in a non-contact manner|

---

KR101639066B1|2015-07-14|2016-07-13|한국과학기술연구원|Method and system for controlling virtual model formed in virtual space|

---

US9995823B2|2015-07-31|2018-06-12|Elwha Llc|Systems and methods for utilizing compressed sensing in an entertainment system|

---

KR101745406B1|2015-09-03|2017-06-12|한국과학기술연구원|Apparatus and method of hand gesture recognition based on depth image|

---

US10120454B2|2015-09-04|2018-11-06|Eyesight Mobile Technologies Ltd.|Gesture recognition control device|

---

US10048765B2|2015-09-25|2018-08-14|Apple Inc.|Multi media computing or entertainment system for responding to user presence and activity|

---

US10962780B2|2015-10-26|2021-03-30|Microsoft Technology Licensing, Llc|Remote rendering for virtual images|

---

US10019072B2|2016-01-01|2018-07-10|International Business Machines Corporation|Imagined grid fingertip input editor on wearable device|

---

US10185400B2|2016-01-11|2019-01-22|Antimatter Research, Inc.|Gesture control device with fingertip identification|

---

US11033205B2|2016-02-12|2021-06-15|Tata Consultancy Services Limited|System and method for analyzing gait and postural balance of a person|

---

JP6538961B2|2016-03-04|2019-07-03|株式会社ソニー・インタラクティブエンタテインメント|Control device|

---

CN105903157B|2016-04-19|2018-08-10|深圳泰山体育科技股份有限公司|Electronic coach realization method and system|

---

US10303255B2|2016-05-31|2019-05-28|Atheer, Inc.|Method and apparatus for unified free space pose input system navigation|

---

EP3488324A1|2016-07-20|2019-05-29|Usens, Inc.|Method and system for 3d hand skeleton tracking|

---

JP6318202B2|2016-08-18|2018-04-25|株式会社カプコン|Game program and game system|

---

US9817511B1|2016-09-16|2017-11-14|International Business Machines Corporation|Reaching any touch screen portion with one hand|

---

US10572024B1|2016-09-28|2020-02-25|Facebook Technologies, Llc|Hand tracking using an ultrasound sensor on a head-mounted display|

---

WO2018074054A1|2016-10-19|2018-04-26|ソニー株式会社|Display control device, display control method, and program|

---

US11148033B2|2017-01-27|2021-10-19|The Johns Hopkins University|Rehabilitation and training gaming system to promote cognitive-motor engagement|

---

RU2662399C1|2017-03-17|2018-07-25|Алексей Александрович Тарасов|System and method for capturing movements and positions of human body and parts of human body|

---

US10627895B2|2017-03-21|2020-04-21|LenovoPte Ltd|Providing a virtual control|

---

CN107198878B|2017-05-18|2020-06-09|深圳市山弯科技有限公司|Method for realizing accurate positioning of gamepad double-rocker on screen|

---

JP6831475B2|2017-10-16|2021-02-17|株式会社ソニー・インタラクティブエンタテインメント|Information information systems, controller devices, and information processing equipment|

---

US11014242B2|2018-01-26|2021-05-25|Microsoft Technology Licensing, Llc|Puppeteering in augmented reality|

---

US10353579B1|2018-03-28|2019-07-16|Disney Enterprises, Inc.|Interpreting user touch gestures to generate explicit instructions|

---

CN108762505B|2018-05-29|2020-01-24|腾讯科技（深圳）有限公司|Gesture-based virtual object control method and device, storage medium and equipment|

---

US10635895B2|2018-06-27|2020-04-28|Facebook Technologies, Llc|Gesture-based casting and manipulation of virtual content in artificial-reality environments|

---

CN109271847A|2018-08-01|2019-01-25|阿里巴巴集团控股有限公司|Method for detecting abnormality, device and equipment in unmanned clearing scene|

---

KR102110760B1|2018-08-07|2020-05-15|매트릭스테크 주식회사|Apparatus for processing 3 dimension modelling data based on multi thread and operating method thereof|

---

CN110139115B|2019-04-30|2020-06-09|广州虎牙信息科技有限公司|Method and device for controlling virtual image posture based on key points and electronic equipment|

---

KR102319074B1|2019-12-11|2021-11-02|주식회사 시공테크|Hanging simulator system with 3-axis movement and the method thereof|

---

KR102280412B1|2020-05-21|2021-07-22|투비소프트|Electronic terminal device that performs control command execution and feedback output corresponding to a user's hand gesture and operating method thereof|

---

US20220005215A1|2020-07-01|2022-01-06|Samsung Electronics Co., Ltd.|Efficient encoding of depth data across devices|

---

CN113936233A|2021-12-16|2022-01-14|北京亮亮视野科技有限公司|Method and device for identifying finger-designated target|

法律状态:
2018-02-06| B25A| Requested transfer of rights approved|Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC (US) |

---

2018-12-11| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]|

---

2020-08-04| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]|

---

2021-02-09| B09A| Decision: intention to grant [chapter 9.1 patent gazette]|

---

2021-04-13| B16A| Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]|Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 04/06/2012, OBSERVADAS AS CONDICOES LEGAIS. |

优先权:

---

申请号 | 申请日 | 专利标题

---

US201161493850P| true| 2011-06-06|2011-06-06|

---

US61/493,850|2011-06-06|

---

US13/277,011|2011-10-19|

---

US13/277,011|US8897491B2|2011-06-06|2011-10-19|System for finger recognition and tracking|

---

PCT/US2012/040741|WO2012170349A2|2011-06-06|2012-06-04|System for finger recognition and tracking|

---