• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    Method for video evaluation of the heart rate and / or the respiratory rate of a baby (B), especially in twilight or nocturnal conditions, in a device comprising a video camera (2) and an infrared illumination source (3) ), the method comprising the steps of: A1- illuminating the baby with the infrared source, A2- capturing video images of the baby, B1- determining the position of the head (T) of the baby by an ellipse search forming a contour of the head, B2- identify an area of interest (7) centered on an eluted ellipse (6), C- evaluate, by plethysmographic analysis on the area of interest, the heart rate (HR) and / or the respiratory rate (RR) of the baby, and associated system.
    公开号:FR3023699A1
    申请号:FR1456996
    申请日:2014-07-21
    公开日:2016-01-22
    发明作者:Amaury Dumoulin；Guillaume Mathias；Eric Carreel
    申请人:WiThings SA；
    IPC主号:
    专利说明:

    [0001] The present invention relates to video surveillance devices and methods for monitoring a baby, in particular so as to be able to monitor a baby who sleeps in his cradle, under twilight conditions or nocturnal, that is, in partial or total darkness; the present invention also relates to methods of interaction between a baby and his parent or supervisor. More specifically, the invention relates to a method and a device for monitoring certain vital parameters of the baby, in particular the heart rate and the respiratory rate. US8094013 discloses a device of this type; however, according to this document, it is necessary to attach a strap around the body of the baby, which in practice proves tedious, and which is not appropriate if the baby is already asleep. W02013170035 also discloses a device of this type; However, it is necessary to install a catching cushion under the body of the baby, which is not appropriate if the baby is already asleep, and the system is ineffective if the baby moves outside the sensitive area of the baby. cousin. The present invention is intended in particular to overcome at least in part the disadvantages of the prior art. For this purpose, according to a first general aspect of the invention, there is provided a method of video evaluation of the heart rate and / or the respiratory rate of a baby under twilight or nocturnal conditions, in a device comprising a a video camera and an infrared illumination source, the method comprising the steps of: Al- illuminating the baby with the infrared source, A2- capturing video images of the baby, Bl- determining the position of the baby's head by searching for contours forming an ellipse 5 coinciding substantially with the contour of the head, B2- identifying an area of interest centered on the ellipse, C- evaluating, by a photo-plethysmographic analysis on the area of interest, the rhythm heart and / or the baby's breathing pattern. With these provisions, there is provided a method which does not require any contact with the baby for its implementation, and which can therefore be installed even if the baby is already installed in his cradle falling asleep. In addition, such a method is compatible with movements, positional changes, reversal of the baby, and the device which implements the method has no direct interaction with the baby, being based on video surveillance and advantageous analysis. captured images, and it is easy to install. In various embodiments of the aforementioned invention, one or more of the following arrangements may be furthermore employed. The method may further include a step of identifying a significant movement of the baby, in which case the photo-plethysmographic analysis step C- is suspended; so that erroneous results are avoided in the case where the baby changes position or makes a significant movement which does not allow to continue the photo-plethysmographic analysis correctly. The method may further comprise a step of identifying a return to a stable state without significant movement of the baby (after cessation of movement), in which case steps B1-B2 are performed again, and step C-d photo-plethysmographic analysis is reset with the new area of interest established in step B2; so that the method allows to again determine the position of the baby's head and can start the photo-plethysmographic analysis again. The images are preferably captured in color and the photo-plethysmographic analysis is preferably based on the red component of the video images; whereby the red component of the video signal provides the most relevant indication under dark or night conditions under infrared illumination for photoplethysmographic analysis. A random thresholding image convolution method can preferably be used in step B1 to search for outlines or portions of contours in the image. ; It is thus possible to extract contour portions efficiently in the analyzed image. In step B1-, candidate ellipses are formed from the identified contours portions, and a selection filter is applied to the candidate ellipses to retain only one elliptical ellipse coinciding with the contour of the baby's head; an exhaustive and systematic method is thus proposed to extract from the contour portions of the candidate ellipses, and to choose among these ellipses the most relevant that can correspond to the baby's head. In step C-, for the determination of the heart rate, the light signal averaged spatially over the area of interest is applied to a digital bandpass assigned terminals [0.75 Hz - 3.5 Hz] to obtain a signal filtered; thus advantageously eliminates the DC component of the signal and all the disturbing signals having a frequency higher than the upper limit of the digital filter, here 3.5 Hz, which is advantageous for extracting the heart rate. A validity criterion relating to the relevance of the filtered signal is defined to selectively validate or not to validate the heart rate information, the validity criterion being based on the signal-to-noise ratio; whereby the method delivers the heart rate information only if it has been reliably obtained, and in the opposite case the output of the heart rate information is disabled. R9 The captured images can be cut into a matrix of sub-images of identical size; so that the treatments can be successively applied to the sub-images which requires less computing capacity and less resources. Preferably, in step B1, sub-images having a neutral content, that is to say without any significant color or intensity variation on the surface of the subimage, are eliminated and eliminated after step B2 sub-images located outside said elected ellipse; so that it avoids dealing with sub-images without interest, and that we obtain a shorter processing time on the complete image. The invention also relates to a device for evaluating the heart rate and / or the respiratory rate of a baby under twilight or nocturnal conditions comprising a video camera, an infrared illumination source, and a computing unit, in wherein the infrared source is configured to illuminate the baby, the video camera is configured to capture video images of the baby, and the computing unit is configured to implement the method as described above. Advantageously, the device may further comprise a wireless communication interface for transmitting the baby's heart rate and / or breathing rate data to a remote entity; thus, information about the baby's vital rhythms can be displayed on a smartphone screen remote from the cradle where the baby sleeps. According to a second aspect of the invention, which can be combined with the previous one, or made independent of the previous one, there is provided a device having the general function of monitoring a baby, and which further comprises a volatile organic compound sensor ( sensor called 'VOC') which provides an indication of the quality of the ambient air in the living room. Such a sensor can detect several organic gases, such as butane, propane, octane, methanol, ethanol, propanol, butanol and even aromatic compounds such as benzene, ethylbenzene, toluene. The baby's monitoring device can record, over one or more periods of time, the concentration of organic compounds captured by the sensor, and transmit it either in real time or in deferred form to a remote entity of the Smartphone type. A device having the general function of monitoring a baby, comprising a computing unit, a communication interface and a volatile organic compound sensor, is thus proposed, said computing unit being configured to record the concentration of organic compounds delivered by the device. sensor of volatile organic compounds, and transmit it to a remote entity of the Smartphone type. In a variant, the computing unit stores the concentration data of organic compounds in a memory, in order to transmit them to the smartphone on a regular basis. In addition, an alert threshold can be provided in the computing unit of the monitoring device, which makes it possible to send an alert immediately when the concentration of volatile organic compounds exceeds a predetermined threshold, and to immediately alert the Smartphone carrier. According to a third aspect of the invention, which can be combined with the previous ones, or made independent of the above, there is provided a method of detecting crying of the baby. Specifically, the computing unit records the audio signals from the microphone, and proceeds to a digital processing, to identify a sound signature characteristic of a baby cry. A device having the general function of monitoring a baby, comprising a calculating unit, a communication interface and a microphone, is thus proposed, said calculating unit being configured to analyze the received sound signals received from the microphone, to carry out a spectral or statistical analysis of the sound signal for processing by a parameterized algorithm capable of discerning the crying of babies and where appropriate to send a high-level alert information (SMS type or equivalent message) to an entity Remote type Smartphone. The detection algorithm may be calibrated on reference sound signatures which may be derived for example from a general library of signals. The reference sound signatures may also come from previous recordings made on the same device, or preferably also about the same crying baby. This improves the relevance of detection by learning. According to a fourth aspect of the invention, which can be combined with the previous ones, or rendered independent of the previous ones, a monitoring device and a method are proposed which make it possible to accompany the baby's sleep phase, by means of a piloting a mood light and spreading soft music.
    [0002] Specifically, the monitoring device includes a computing unit, a microphone and a detection function for detecting the heart rate and / or movements of the baby. The detection function can be performed by video monitoring and heart rate determination as explained in the first aspect of the invention. The detection function can also be performed as an alternative or in combination with the previous one by a sensor which takes the form of a baby's motion detection web, this web being adapted to be interposed between the baby and the mattress of the bed. The baby's sleep phase may for example be determined when the heart rate becomes more regular and slower with no significant movement of the baby.
    [0003] A method of accompanying the baby's sleep phase is thus proposed, which includes a step of monitoring certain vital parameters such as the baby's heart rate and movement (s), a step of identifying the beginning of the phase of the baby. asleep in which certain vital parameters substantially corresponding to predetermined parameters of a falling asleep phase, a step of activating a decreasing intensity light atmosphere and a step of activating a decreasing intensity sound environment. . The vital parameters are detected, either through video surveillance and in particular the identification of the heart rate and movements of the baby's head, either through the use of a sensing ribbon sensor. According to a fifth aspect of the invention, which can be combined with the previous ones, or made independent of the previous ones, there is provided a monitoring device which furthermore comprises a detection sheet intended to be interposed between the baby is the mattress, this mat being intended to capture the baby's movements both macroscopic and microscopic. It is thus possible to determine the baby's breathing rhythm, by analysis and signal processing. A device having the general function of monitoring a baby, comprising a calculating unit, a microphone, and a detection sheet designed to be interposed between the baby and the mattress to capture the baby's movements, is thus proposed. calculus being adapted to determine the baby's breathing rate from the sound information picked up by the microphone and motion information captured by the sensing mat.
    [0004] The detection sheet may be formed by a thin pneumatic bladder, alternatively this detection sheet may be formed by piezoelectric gauge elements. In addition, the device may be equipped with a communication interface which makes it possible to transmit the respiratory rate data to a remote device of the Smartphone type. According to a sixth aspect of the invention, which can be combined with the foregoing, or rendered independent of the foregoing, there is provided a method for producing stimuli imitating the heart beat of the mother to the baby by sonic means using the loudspeaker, and / or through the detection web which can be provided with an active pneumatic device capable of generating pressure pulsations similar to heart beats. Other aspects, objects and advantages of the invention will appear on reading the following description of an embodiment of the invention, given by way of non-limiting example. The invention will also be better understood with reference to the accompanying drawings, in which: FIG. 1 is a general view of a cradle in which a baby is to be monitored by a method according to the invention, FIG. 3 shows a block diagram of the device of FIG. 2, FIG. 4 represents an example of an image captured by the camera, FIG. 5 illustrates the construction of portions of FIG. outline, 20 - Figure 6 illustrates the ellipse selection and the area of interest. FIG. 7 illustrates an example of a filtered signal. FIG. 8 shows a flow diagram illustrating the method; FIG. 9 illustrates a variant of the monitoring device with detection sheet. In the different figures, the same references designate identical or similar elements. Figure 1 shows a baby B lying in a cradle 13. In the context of the present invention, a baby is defined as an infant or a child under 10 years of age. We are particularly interested in the case where the baby is put in his cradle for a nap or for the night. Typically, in this configuration, the general lighting level in the room will be low or very low, it is called penumbra conditions or night conditions, partial or total darkness.
    [0005] A video surveillance assembly, marked 10, comprises in the illustrated example a video surveillance device 1 which will be discussed in detail below, a fixing foot 12 and a clamp 11. In the example illustrated, the clamp fixation is fixed on a side edge of the cradle or more generally of the bed. It is noted that in the surveillance set to be also attached to the crosshead of the bed or to the crossbeam of the bed. The video surveillance device 1 can be fixed on another support, on the wall, on a bed canopy, etc .; however, it is advantageous that the position of the video surveillance device is relatively stable with respect to the bed or cradle 13. As illustrated in more detail in FIG. 2, the video surveillance device 1 comprises a video camera 2, which in the illustrated example has a wide angle of view ie a solid angle of at least 90 ° aperture or even more so that the camera can capture images of the entire useful area of the cradle. In addition, the monitoring device comprises light-emitting diodes 3 (LEDs) which can emit in the infrared band, thus forming an infrared illumination source. In the illustrated example the LEDs 3 are arranged all around the camera lens, but it could be otherwise, the camera and infrared lighting functions could be physically dissociated. The video surveillance device 1 further comprises a computing unit 4 with a memory space 40, and an electric battery 28, or alternatively a mains power supply unit. The video surveillance device 1 further preferably comprises a wireless communication interface 42 configured to be able to exchange data with a remote entity such as a smartphone 22. The video surveillance device 1 may further include a microphone 9 enabling to capture sounds and a sound generator in the form of a small speaker 19. 10 There may further be a light source 23 for a light ambient lighting whose intensity can be controlled by the monitoring device , an air quality sensor 37 and auxiliary sensors 27 for capturing, for example, the temperature and / or the humidity. The video surveillance device 1 may further comprise one or more keys 18 intended to be actuated by a user (for example for setting the device, starting and stopping), as well as a small display 15 enabling to display states or parameters of the device (in which case the keys 18 may be tactile). Furthermore, the device may comprise a connector 74, and holes 9 'in front on the lower face 25 to improve sound pickup by the microphone. Advantageously according to the present invention, the camera 2 periodically captures video images 5 of the baby B. The capture frequency of the images will be a few hertz or 30 tens of hertz, preferably greater than 8 Hz. It should be noted that in the context of the invention the same camera is used to capture the images of day and capture the images in the dark.
    [0006] It can be provided a two-position optical filter, a day position and a night position. The device controls the excitation of the infrared LEDs 3 either permanently or temporally in agreement and coherence with the image capture. The infrared LEDs are arranged so as to illuminate substantially all the solid angle of vision of the video camera. Advantageously according to this version, the image analysis processing method 10 will focus on determining the position of the head T of the baby. For this, a step B1 identified in the method consists in searching for contours or contour portions in one or more successive images captured by the camera. In the illustrated example, the images are captured in color, and under the conditions of darkness or darkness under infrared illumination, it will be possible preferably to choose in particular to work on the red component of each image (among the red components, green and blue of the 'RGB' reference). However, we can also work on the green component or on a parametric mix of colors. For each image, a statistical threshold spatial convolution process or a mean correlation computation of the red component or the parameterized mixture of colors is performed. This makes it possible to locate and store curve portions 61, 62, 63, 64 where the spatial gradient of the signal is highest, which corresponds in practice to portions of contours in the image. The identification of these contour portions can be confirmed by the sequential analysis of several successive images; if on these several images we find at the same place similar contour portions, then the determination is confirmed. In the opposite case, it may be a macroscopic movement of the baby, and this case will be explained later. When the sequential analysis of several successive images has confirmed the presence of several contour portions, a next step is taken, during which several contour portions are associated and their meeting is compared to an elliptical shape (ellipse) on which could be said said several portions of contours. A relevancy criterion is established for quantifying the match of the meeting of the contour portions 62, 64 with the candidate ellipse. Of course, if in the analyzed image we find a continuous contour that forms a closed circle or ellipse, then the relevance criterion will take the maximum value; but often in practice, the analysis of the image only restores certain parts of the candidate ellipse, and it is then necessary to reconstitute the ellipse and to assign it a relevance criterion value. This step, labeled B2, can further identify several candidate ellipses, in which case a selection filter is applied to the candidate ellipses to retain only one elliptical ellipse 6 which coincides with the baby's T-head contour. This filter can use the size of the ellipse, its major axis / minor axis ratio, and also the contour proportion actually revealed by the previous step. It should be noted that the presented method could also work to detect two (or more) baby heads in a cradle where there would be two babies, in which case the filtering would not be limited to identifying a single candidate ellipse but two ellipses. But in the typical case of a single head to be detected, the selection of such an eluted ellipse 6 makes it possible on the one hand to eliminate from the subsequent analysis all the image zones situated outside the ellipse, and on the other hand to define an area of interest centered on the ellipse. Once the area of interest has been determined, and subject to the absence of significant movement of the baby (see below), then step C of the process is carried out, this step corresponds to a photoplethysmographic analysis aimed at determine the baby's vital rhythms, especially the heart rate, but also the respiratory rate.
    [0007] Advantageously, it is possible to determine a first zone of interest 7 intended for evaluation of the heart rate, and a second zone of interest which may be distinct from the first, intended for the evaluation of the respiratory rhythm.
    [0008] Preferably, for the determination of the heart rate, firstly, on the spatially averaged luminous signal on the first area of interest, a sliding window offset calculation is applied in order to eliminate the DC component of the signal. Thus, a signal referenced 80 is obtained in FIG. 7, which remains relatively noisy but no longer contains a DC component. Then, on the signal 80, a digital band pass filter (known per se) assigned terminals [0.75 Hz - 3.5 Hz] is applied to obtain a filtered signal 81. This eliminates the parasitic signals outside the band of interesting frequencies. The resulting filtered signal 81 is then subject to a peak detection step. This treatment makes it possible to reveal the peaks 86 (only the first ones are marked with crosses in FIG. 7). The time interval between each consecutive peak 86 makes it possible to calculate the heart rate which is illustrated on the curve 82. Optionally, it is possible to define a validity criterion relating to the relevance of the filtered signal 8, to selectively validate or not to validate the signal. heart rate information. This validity criterion may be based on the signal-to-noise (S / N) ratio of the signal 81. A filtered and correct signal is shown at frame 83. If the validity criterion validates the heart rate value from step C, this value can be stored in memory and / or can be transmitted to a remote device 22 of the Smartphone type connected by a wireless link to the monitoring device 1. Step C is performed almost continuously, repeated periodically, for example a measurement every 5 seconds or every 10 seconds, knowing that in order to carry out each measurement, the device may optionally increase the image acquisition frequency on the area of interest. In parallel with step C, the method monitors that the baby remains substantially immobile, i.e., the contour portions identified in step B1 remain substantially stable. A particular case is managed by the method according to the invention: it is a significant (macroscopic) movement of the baby. In this case, the baby's head moves, and the determination of the position of the head must be repeated. The detection of a significant movement of the baby can be performed by analyzing the position of the contour portions and their evolution as a function of the successive images. As an alternative to the supplement, one can also use the information provided by the microphone 9, because a macroscopic movement of the baby will generate sound signals received by the microphone. Those skilled in the art understand that plethysmographic analysis can no longer provide a valid result while the baby is performing significant movements. However, it is intended to monitor the evolution of these movements (this constitutes the step marked D) to identify a return to a stable state without significant movement of the baby, in which case the steps B1-B2 are performed again. Step C- photo-plethysmographic analysis is resumed with the new zone 15 of interest 7 established in step B2. The treatments mentioned above can be performed on the entire captured image 5; however, alternatively, a slicing of the image may be used to limit the resources required for calculation and the necessary memory space. For example, the captured image 5 can be cut into a matrix of sub-images 50, each sub-image 50 being of the same size to facilitate processing; in the illustrated example, the captured image is cut in 5x5 under images. This has the advantage that some sub-images with a neutral or flat content 50a (i.e. without significant color or intensity variation on the surface of the sub-image) can be eliminated during the detection. in step B1. A criterion for eliminating irrelevant subframes 50 may be based on a low light intensity and / or a small variation on the analyzed area. It is also possible to eliminate, after the choice of the elected ellipse 6, all the sub-images with neutral or flat content 50a located outside the ellipse, or even outside the area of interest 7. Of course, if the method finds contour portions 5 straddling several sub-images, a new treatment is performed on the meeting of sub-image in question. It should be noted that the first zone of interest, for the heart rate, will preferentially target the baby's forehead, while for the second zone of interest, for the respiratory rhythm, the entire face may be part of the zone. interest. With reference to FIG. 8, since the steps B1-B2 made it possible to identify an area of interest, the transition 96 initializes the plethysmographic analysis (C-), and this is repeated (ref 95). as long as the baby stays still. If the latter makes a movement, then the plethysmographic analysis is suspended 97,98 and the macroscopic movement monitoring step (step D) puts the plethysmographic process on hold until a return to a stable state, illustrated by the transition 99. Then, the method starts again steps B1-B2, then goes on step C-. Advantageously, the plethysmographic analysis can work even if the baby's head is seen from behind. Advantageously according to the invention, even if the position of the baby changes a lot during his sleep, and even if the baby turns, the detection of the position of the head by the proposed method allows to monitor continuously the vital parameters of the baby . It should also be noted that the installation of the device does not require special precautions, the automatic detection of the head of the baby being possible even if the framing of the camera is not perfect compared to the cradle. Regarding the determination of the respiratory rate, step C must be adapted, for example the terminals of the digital band pass filter are three times lower.
    [0009] The criteria for analyzing the filtered signal for the detection of the respiratory rhythm, as well as the criteria for validating the resulting signal, in this case resort to an iteration mechanism. It should be noted that the method of detecting the baby's head as disclosed above can also function by day with natural lighting, and not only under the condition of an obscure light environment. Moreover, in the illustrated example, a single CCD camera allows detection day and night; but according to one possible variant, the video surveillance device comprises on the one hand a conventional CCD camera for day vision, and on the other hand an infrared or thermometric thermal camera for night vision. According to a complementary aspect, the video surveillance device 1 further comprises a sensor 37 of volatile organic compounds (so-called 'COV' sensor). Such a sensor makes it possible to detect several organic gases, such as butane, propane, octane, methanol, ethanol, propanol, butanol and even aromatic compounds such as benzene, ethylbenzene or toluene. . The baby monitor can record over one or more periods of time, the concentration of organic compounds, and transmit it either in real time or in deferred form to the smartphone 22. The VOC sensor 37 in question is an ion detector using the photoionization of molecules contained in a sample of air captured in the room where the cradle of the baby is located. It thus delivers a level of concentration of organic compounds that amalgamates all the organic compounds present.
    [0010] In a complementary aspect, the microphone 9 included in the device 1 continuously analyzes the ambient noise. The dynamics and the energy of the signal are observed and when they exceed adaptive thresholds, a crying recognition starts.
    [0011] This mechanism preferably uses short (10 to 100 ms) and carries out a thorough analysis. From this information, a classifier calculates the probability that the extract will have this effect, the computation unit 4 keeps in sound signatures type of spectral baby crying (these are reference values). In addition, it can be provided, as shown in Figure 9, to provide a detection web 72 forming a motion sensor. This detection sheet 72 is installed on the mattress of the bed and the baby B is installed over it, in other words the detection sheet 72 is interposed between the baby B and the mattress. The detection sheet may comprise a signal shaping interface 77 and is connected to the monitoring device 1 by a flexible connection 73, either electrical or pneumatic or mixed. This link 73 is connected to the device in the connector 74. The signal processing may be performed by the formatting interface 77 or even directly or partly by the monitoring device itself. In the example illustrated, the detection sheet is formed by a thin pneumatic bladder and spectral sequences of crying. To memory of the form allows to detect the movements of the baby by ballistography. Alternatively, the detection sheet may also be formed by a plurality of piezoelectric or piezo-resistive gauges.
    [0012] In the case of the detection sheet 72 is formed by a pneumatic bladder, one can have a pneumatic pump (not shown) configured on the one hand to generate a mean pressure of measurement in the sheet, and secondly to generate pulsations tires that are used to reproduce, for the baby, pulsations similar to the heartbeats of his own mother that the baby could feel during pregnancy. Advantageously according to an optional aspect of the device, the calculation unit 4 can be configured to detect the beginning of a sleep phase of the baby B for example by means of the monitoring of the cardiac rhythm and / or the monitoring of the respiratory rate and / or monitoring baby's movements. In fact, to help the baby fall asleep more easily, it is a question of diffusing a luminous atmosphere by means of the ambient lighting 23 and a soft music by means of the loudspeaker 19, both of them. preference decreasing in intensity. The beginning of the sleep phase, to trigger the light and sound sequence, can be detected by the video determination of the heart rate as explained above. When the heart rate 82 becomes more regular and slower, then the control unit 4 triggers the light and sound sequence. In an advantageous aspect, a particular sound sequence can be provided that reproduces the heartbeats of the baby's mother that the baby heard during pregnancy.
    [0013] Alternatively, the computing unit uses not only the heart rate information but also the respiratory rate information detected for example by means of the microphone 9 and / or the aforementioned detection web 72. The calculating unit 4 can also use the video detection of the movements of the head T of the baby, by means of the method of detecting contours as explained above. When the calculating unit 4 has triggered the sound and light sequence of sleep assistance, and if the baby starts to move or cry again, then the sequence may be extended or restarted at its beginning. If the sound and light sequence is completed with no change in heart rate and no movement of the baby, then the monitoring device completely turns off the mood lighting and goes into night surveillance mode. According to a particular aspect, from the selection of the area of interest (position of the head), the video surveillance device 20 can record in memory a plurality of images of the baby's face, taken at sufficiently long intervals of time. away, to form a slide show of baby's evolution and growth. In one aspect, the video surveillance device may be configured to take larger images than the baby's only cradle, thereby generating alerts to the parent and / or supervisor by sending full images of the room in which is located the crib and from the motion detection, display the image of (s) person (s) present (s) with baby. In a particular aspect, the video surveillance device can record the highlights of the day and / or night; in other words, to record images of the events that occurred previously; for example from the detection of a movement outside the baby, record images and sound every time a person enters or leaves the room, from the detection of crying, record images and sound every time the baby starts to cry, whenever environmental parameters change significantly, every time the baby smiles, etc.
    [0014] According to a particular aspect, the video surveillance device can generate an alert transmitted to a remote device, smartphone or other, in case of detection of abnormal conditions, for example environment parameters that exceed predetermined thresholds, abnormally quiet environment abnormally agitated about noise, motion, pollutant detection, etc. Finally, in a particular aspect, the video surveillance device may be equipped with a simultaneous bidirectional audio link, ie a full-duplex link direction, which allows the parent (s) and the baby to exchange words. or auditory signals really at the same time.
    权利要求:
    Claims (4)
    [0001]
    REVENDICATIONS1. A method for video evaluation of the heart rate and / or the respiratory rate of a baby (B) under twilight or nocturnal conditions in a device (1) comprising a video camera (2) and an infrared illumination source ( 3), the method comprising the steps of: Al- illuminating the baby with the infra-red source, A2- capturing video images (5) of the baby, B- determining the position of the baby's head (T) by searching for contours inserting on an ellipse substantially coinciding with the contour of the head, B2- identify an area of interest (7) centered on an ellipse elected (6), C- evaluate, by a photo-plethysmographic analysis on the area of interest heart rate (HR) and / or the baby's respiratory rate (RR).
    [0002]
    The method of claim 1, further comprising a step of identifying a significant movement (D) of the baby, in which case the photoplethysmographic analysis step C is suspended.
    [0003]
    The method of claim 2, further comprising a step of identifying a return to a stable state without significant movement of the baby, in which case steps B1-B2 are performed again, step C- photoplethysmographic analysis is resumed with the new area of interest established in step B2. 30
    [0004]
    4. Method according to one of claims 1 to 3, wherein the images (5) are captured in color and the photo-plethysmographic analysis is based on the red component of the video images. Method according to one of claims 1 to 4, in which step B1 is used a statistical thresholding image convolution method for searching contours or contour portions in the image (5, 50). 6. Method according to one of claims 1 to 5, wherein in step B1 is formed from the identified contour portions of the candidate ellipses, and a selection filter is applied to the candidate ellipses to retain only a single elected ellipse (6) which coincides with the outline of the baby's head. 7. Method according to one of claims 1 to 6, wherein in step C, is applied, on the light signal spatially averaged over the area of interest (7), a digital bandpass filter affected by the limits [ 0.75 Hz - 3.5 Hz] to obtain a filtered signal (81). The method of claim 7, wherein a validity criterion relating to the relevance of the filtered signal (81) is defined, for selectively validating or not validating heart rate information (FC), the validity criterion being based on the signal-to-noise ratio. 9. The method according to one of claims 1 to 8, wherein the captured images (5) are cut into a matrix of sub-images (50) of identical size. 10. The method of claim 9, wherein in step B1 are eliminated sub-images having a neutral content that is to say without significant color or intensity variation on the surface of the sub-image. (50), and after sub-B2 the sub-imagines outside of said ellipse are eliminated. 11. Apparatus for video evaluation of a baby's heart rate and / or breathing rate under twilight or night conditions including a video camera (2), an infrared illumination source (3), and a calculating unit ( 4), wherein the infrared source is configured to illuminate the baby, the video camera is configured to capture video images (5) of the baby, and the computing unit is configured to implement the method according to one of the Claims 1-10. The device of Claim 11, comprising a wireless communication interface for transmitting the heart rate (HR) data and / or the baby's respiratory rate (RR) to a remote entity (22).
    类似技术:
    公开号 | 公开日 | 专利标题
    FR3023699A1|2016-01-22|METHOD AND DEVICE FOR MONITORING A BABY AND INTERACTING
    EP0388422B1|1993-06-23|Process and device for monitoring human respiration
    EP3463051A1|2019-04-10|Connected device for behavioural monitoring of an individual and for detecting and/or preventing an anomaly
    WO2017105720A1|2017-06-22|Electroencephalography | camera control
    US8902164B2|2014-12-02|Optical finger mouse, mouse control module and physiology detection method thereof
    FR3028741B1|2019-06-14|DEVICE FOR MEASURING THE HEART RATE OF THE DRIVER OF A VEHICLE
    FR2896398A1|2007-07-27|DEVICE FOR OCULAR STIMULATION AND DETECTION OF BODILY REACTIONS
    EP0597032B1|1998-01-07|Biological wake-up device to be programmed according to sleep episodes
    US20160249852A1|2016-09-01|Information processing apparatus, information processing method, and program
    US10813593B2|2020-10-27|Using visual context to timely trigger measuring physiological parameters
    US10621424B2|2020-04-14|Multi-level state detecting system and method
    FR3048542A1|2017-09-08|DEVICE AND METHOD FOR PERSONALIZED MONITORING OF A DRIVER OF A MOTOR VEHICLE
    EP0681447A1|1995-11-15|Device for the determination of physiological information and corresponding use
    CN106974626A|2017-07-25|Monitoring of pulse robot
    FR3070851B1|2019-09-20|SYSTEM FOR DETECTING AND ALERT PERSONNEL CARING FOR THE RISK OF DECOMPENSATION OR HOSPITALIZATION OF A PATIENT
    EP3073900B1|2017-08-23|Method for constructing an activity index, device, and computer program therefore
    FR3103611A1|2021-05-28|Method and device for monitoring the activity of a person with loss of autonomy
    CN107209391A|2017-09-26|A kind of head-mounted display apparatus and its display methods
    WO2021234174A1|2021-11-25|Method for detecting coughing by inertial measurement
    WO2020089539A1|2020-05-07|Method, device and system for predicting an effect of acoustic stimulation of the brain waves of an individual
    FR3109519A1|2021-10-29|Apparatus for detecting and interrupting an episode of sleep apnea
    FR3064463A1|2018-10-05|METHOD FOR DETERMINING AN ENSEMBLE OF AT LEAST ONE CARDIO-RESPIRATORY DESCRIPTOR OF AN INDIVIDUAL DURING ITS SLEEP AND CORRESPONDING SYSTEM
    FR3051341A1|2017-11-24|MEDICAL WIRELESS DEVICE FOR ACQUIRING SKIN VIDEOS BIMODALITY WITH LIGHT CONTROL
    FR3113368A1|2022-02-18|METHOD AND SYSTEM FOR DETECTING DROWSY IN AN INDIVIDUAL
    CA3147510A1|2021-01-21|Method and system for testing cognition by processing the reaction of a subject to stimuli
    同族专利:
    公开号 | 公开日
    EP2977973B1|2018-06-06|
    EP2977973A1|2016-01-27|
    EP2976998A1|2016-01-27|
    US10694956B2|2020-06-30|
    EP3321909A1|2018-05-16|
    US20160015277A1|2016-01-21|
    EP2976998B1|2018-06-06|
    US10441178B2|2019-10-15|
    FR3023699B1|2016-09-02|
    US20160015278A1|2016-01-21|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    CN102309315A|2011-09-07|2012-01-11|周翊民|Non-contact type optics physiological detection appearance|
    WO2013093686A1|2011-12-20|2013-06-27|Koninklijke Philips Electronics N.V.|Apparatus and method for monitoring a sleeping person|
    WO2013164724A1|2012-05-01|2013-11-07|Koninklijke Philips N.V.|Device and method for extracting information from remotely detected characteristic signals|
    WO2013166341A1|2012-05-02|2013-11-07|Aliphcom|Physiological characteristic detection based on reflected components of light|
    US20140155759A1|2012-12-04|2014-06-05|Koninklijke Philips N.V.|Device and method for obtaining vital sign information of a living being|
    US20140180132A1|2012-12-21|2014-06-26|Koninklijke Philips Electronics N.V.|System and method for extracting physiological information from remotely detected electromagnetic radiation|
    FR2623388A1|1987-11-23|1989-05-26|Bertin & Cie|METHOD AND DEVICE FOR MONITORING THE BREATHING OF AN INDIVIDUAL|
    US7483733B2|1999-07-26|2009-01-27|Cardiosense, Ltd.|Non-invasive method and apparatus to detect and monitor early medical shock, and related conditions|
    CA2435543A1|2001-02-06|2002-08-15|Hill-Rom Services, Inc.|Infant incubator with non-contact sensing and monitoring|
    US20030109790A1|2001-12-06|2003-06-12|Medtronic Physio-Control Manufacturing Corp.|Pulse detection method and apparatus using patient impedance|
    US7872670B2|2002-04-22|2011-01-18|Sanyo Electric Co., Ltd.|Camera performing photographing in accordance with photographing mode depending on object scene|
    US7402167B2|2003-03-03|2008-07-22|Mikhail Nemenov|Portable laser and process for producing controlled pain|
    US20050212950A1|2004-03-26|2005-09-29|Chinon Kabushiki Kaisha|Focal length detecting method, focusing device, image capturing method and image capturing apparatus|
    JP2006203841A|2004-12-24|2006-08-03|Sharp Corp|Device for processing image, camera, device for outputting image, method for processing image, color-correction processing program and readable recording medium|
    US20070217199A1|2006-03-17|2007-09-20|Light Dimensions, Inc.|Light-based dermal enhancing apparatus and methods of use|
    US7611472B2|2006-10-13|2009-11-03|Guixian Lu|Apnea monitor|
    KR100851977B1|2006-11-20|2008-08-12|삼성전자주식회사|Controlling Method and apparatus for User Interface of electronic machine using Virtual plane.|
    US20080136958A1|2006-12-11|2008-06-12|Pentax Corporation|Camera having a focus adjusting system and a face recognition function|
    US20080294012A1|2007-05-22|2008-11-27|Kurtz Andrew F|Monitoring physiological conditions|
    KR20100040302A|2007-07-26|2010-04-19|페이즈 지샨|Improvements to responsive units|
    WO2009116965A1|2008-03-18|2009-09-24|Thomson Licensing|Method and apparatus for adaptive feature of interest color model parameters estimation|
    US8094013B1|2009-03-31|2012-01-10|Lee Taek Kyu|Baby monitoring system|
    US8755854B2|2009-07-31|2014-06-17|Nellcor Puritan Bennett Ireland|Methods and apparatus for producing and using lightly filtered photoplethysmograph signals|
    US9020622B2|2010-06-17|2015-04-28|Evo Inc.|Audio monitoring system and method of use|
    US20130165809A1|2010-07-29|2013-06-27|Digisense Ltd.|Monitoring physiological condition of a subject|
    US20120220969A1|2011-02-25|2012-08-30|Seungjin Jang|Health monitoring apparatus and method|
    WO2013170035A1|2012-05-09|2013-11-14|Technophysics Solutions, Corporation|System and method for attachment free motion, respiration, heartbeat, and video monitoring|
    US9671482B2|2012-10-18|2017-06-06|Samsung Electronics Co., Ltd.|Method of obtaining image and providing information on screen of magnetic resonance imaging apparatus, and apparatus thereof|
    US10044844B2|2012-12-17|2018-08-07|Stephen Brian Parker|Child/user mobile device manager|
    WO2014098690A1|2012-12-21|2014-06-26|Sca Hygiene Products Ab|Method and system for detecting urine and/or feces|
    US9215428B2|2013-01-07|2015-12-15|Dorel Juvenile Group, Inc.|Child-monitoring system|
    KR102195897B1|2013-06-05|2020-12-28|삼성전자주식회사|Apparatus for dectecting aucoustic event, operating method thereof, and computer-readable recording medium having embodied thereon a program which when executed by a computer perorms the method|
    US9674323B1|2013-08-29|2017-06-06|Variable, Inc.|Modular multi-functional device, method, and system|
    CN103680057A|2013-12-06|2014-03-26|闻泰通讯股份有限公司|Method and system for using electronic device to monitor cry of baby|
    US9671383B2|2014-01-27|2017-06-06|Sensor Technologies, Llc|Gas-monitoring apparatus for detecting bowel movements and method of use|
    EP3108392A1|2014-02-18|2016-12-28|Tria Beauty, Inc.|Internet connected dermatological devices and systems|US10708550B2|2014-04-08|2020-07-07|Udisense Inc.|Monitoring camera and mount|
    JP5866539B1|2014-11-21|2016-02-17|パナソニックＩｐマネジメント株式会社|Communication system and sound source reproduction method in communication system|
    GB201601143D0|2016-01-21|2016-03-09|Oxehealth Ltd|Method and apparatus for health and safety monitoring of a subject in a room|
    GB201601140D0|2016-01-21|2016-03-09|Oxehealth Ltd|Method and apparatus for estimating heart rate|
    GB201601217D0|2016-01-22|2016-03-09|Oxehealth Ltd|Signal processing method and apparatus|
    EP3455839A4|2016-05-08|2020-02-12|UdiSense Inc.|Monitoring camera and mount|
    USD854074S1|2016-05-10|2019-07-16|Udisense Inc.|Wall-assisted floor-mount for a monitoring camera|
    US10357117B2|2016-07-13|2019-07-23|Chigru InnovationsPrivate Limited|Rocking cradle|
    US10539268B2|2016-07-13|2020-01-21|Chigru InnovationsPrivate Limited|Oscillation systems|
    US9867597B1|2016-07-13|2018-01-16|Withings|Method and system to notify female fertility period|
    US10447972B2|2016-07-28|2019-10-15|Chigru InnovationsPrivate Limited|Infant monitoring system|
    GB201615899D0|2016-09-19|2016-11-02|Oxehealth Ltd|Method and apparatus for image processing|
    WO2018087528A1|2016-11-08|2018-05-17|Oxehealth Limited|Method and apparatus for image processing|
    GB201706449D0|2017-04-24|2017-06-07|Oxehealth Ltd|Improvements in or realting to in vehicle monitoring|
    US10939833B2|2017-05-01|2021-03-09|Samsung Electronics Company, Ltd.|Determining artery location using camera-based sensing|
    US10399409B2|2017-05-16|2019-09-03|GM Global Technology Operations LLC|System and method for reducing volatile organic compounds within a vehicle|
    CN107260173B|2017-06-30|2019-05-10|大连理工大学|A kind of breath measuring method based on camera Yu spherical marker|
    USD855684S1|2017-08-06|2019-08-06|Udisense Inc.|Wall mount for a monitoring camera|
    CN107682665B|2017-09-13|2021-04-16|维沃移动通信有限公司|Monitoring method and mobile terminal|
    US10921763B1|2017-10-25|2021-02-16|Alarm.Com Incorporated|Baby monitoring using a home monitoring system|
    TW201918219A|2017-11-07|2019-05-16|財團法人資訊工業策進會|System and method for identifying baby needs|
    US10760804B2|2017-11-21|2020-09-01|Emerson Climate Technologies, Inc.|Humidifier control systems and methods|
    US10874332B2|2017-11-22|2020-12-29|Udisense Inc.|Respiration monitor|
    GB2571125A|2018-02-19|2019-08-21|Chestnut Mobile Ltd|Infant monitor apparatus|
    ES2860528T3|2018-02-23|2021-10-05|Stanislaw Napiorkowski|Baby Monitor Set|
    GB201803508D0|2018-03-05|2018-04-18|Oxehealth Ltd|Method and apparatus for monitoring of a human or animal subject|
    US10593184B2|2018-03-05|2020-03-17|Google Llc|Baby monitoring with intelligent audio cueing based on an analyzed video stream|
    US20190279481A1|2018-03-07|2019-09-12|Google Llc|Subject detection for remote biometric monitoring|
    US20190319316A1|2018-04-11|2019-10-17|Astronics Advanced Electronic Systems Corp.|Method and System for Detecting Volatile Organic Compounds within a Battery Assembly|
    WO2019204779A1|2018-04-20|2019-10-24|Emerson Climate Technologies, Inc.|Indoor air quality and occupant monitoring systems and methods|
    US11153482B2|2018-04-27|2021-10-19|Cubic Corporation|Optimizing the content of a digital omnidirectional image|
    US10706705B2|2018-10-03|2020-07-07|Paula Holt|Baby cloud|
    CN109730659B|2018-12-29|2021-12-21|广东三水合肥工业大学研究院|Intelligent mattress based on microwave signal monitoring|
    USD900429S1|2019-01-28|2020-11-03|Udisense Inc.|Swaddle band with decorative pattern|
    USD900431S1|2019-01-28|2020-11-03|Udisense Inc.|Swaddle blanket with decorative pattern|
    USD900428S1|2019-01-28|2020-11-03|Udisense Inc.|Swaddle band|
    USD900430S1|2019-01-28|2020-11-03|Udisense Inc.|Swaddle blanket|
    CN110349371B|2019-03-15|2020-12-11|青田县君翔科技有限公司|Safety monitoring type wireless communication system|
    DE102019119980A1|2019-07-30|2021-02-04|Winzig Stiftung|Method and apparatus for amplifying signals from infants and young children|
    EP3948210A1|2020-06-11|2022-02-09|Nanobio Detection Systems Llc|Systems and methods for detection of volatile organic compounds|
    US10949948B1|2020-06-21|2021-03-16|Alexandru Kuzmin|Closed form method and system for large image matting|
    CN112201007A|2020-10-10|2021-01-08|珠海格力电器股份有限公司|Alarm method and device for infant sleep|
    CN112598887A|2020-11-20|2021-04-02|合肥镭智光电科技有限公司|Novel play by detection device|
    法律状态:
    2015-06-30| PLFP| Fee payment|Year of fee payment: 2 |
    2016-01-22| PLSC| Publication of the preliminary search report|Effective date: 20160122 |
    2016-07-22| PLFP| Fee payment|Year of fee payment: 3 |
    2017-06-13| PLFP| Fee payment|Year of fee payment: 4 |
    2018-03-30| CD| Change of name or company name|Owner name: NOKIA TECHNOLOGIES (FRANCE), FR Effective date: 20180227 |
    2018-05-18| TP| Transmission of property|Owner name: NOKIA TECHNOLOGIES OY, FI Effective date: 20180404 |
    2018-06-12| PLFP| Fee payment|Year of fee payment: 5 |
    2019-07-29| PLFP| Fee payment|Year of fee payment: 6 |
    2020-07-24| PLFP| Fee payment|Year of fee payment: 7 |
    2021-06-28| PLFP| Fee payment|Year of fee payment: 8 |
    优先权:
    申请号 | 申请日 | 专利标题
    FR1456996A|FR3023699B1|2014-07-21|2014-07-21|METHOD AND DEVICE FOR MONITORING A BABY AND INTERACTING|FR1456996A| FR3023699B1|2014-07-21|2014-07-21|METHOD AND DEVICE FOR MONITORING A BABY AND INTERACTING|
    EP17206100.4A| EP3321909A1|2014-07-21|2015-07-17|Method and device for monitoring a baby and for interaction|
    EP15177357.9A| EP2976998B1|2014-07-21|2015-07-17|Method and device for monitoring a baby and for interaction|
    US14/805,063| US10441178B2|2014-07-21|2015-07-21|Monitoring device with volatile organic compounds sensor and system using same|
    US14/804,873| US10694956B2|2014-07-21|2015-07-21|Method and device for monitoring a baby for interaction|
    EP15177627.5A| EP2977973B1|2014-07-21|2015-07-21|Monitoring device with volatile organic compounds sensor and system using same|
    [返回顶部]