• 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:
    Disclosed is a method for measuring an antenna downtilt based on a multi-scale detection algorithm, including: capturing an image of an antenna using an unmanned aerial vehicle, and returning data to a server in real time; obtaining a ground truth box where the antenna is located by performing the multi-scale detection algorithm of a server; segmenting the ground truth box based on an antenna target segmentation algorithm of the server; and obtaining an antenna downtilt angle based on an antenna downtilt measurement algorithm of the server and determining whether the antenna properly functions. This method avoids the danger of tower worker climbing, is fast and accurate, saves labor costs and time, and ensures the measurement of an antenna downtilt to be smoother.
    公开号:EP3680608A1
    申请号:EP19856438.7
    申请日:2019-02-22
    公开日:2020-07-15
    发明作者:Yikui ZHAI；Yihang ZHI；Huixin GUAN；Ying Xu；Junying GAN；Tianlei Wang；Wenbo DENG；Qirui KE
    申请人:Wuyi University；
    IPC主号:G06T7-00
    专利说明:
    [0001] The present disclosure relates to the field of communication measurement, and more particularly, to a method for measuring an antenna downtilt based on a multi-scale detection algorithm. BACKGROUND
    [0002] At present, Antenna downtilt refers to included angle between an antenna on a signal tower and a vertical direction. The antenna downtilt is generally determined by making a comprehensive analysis on coverage area, terrain, site distribution of the area where the antenna is located, hanging height, and station spacing in combination with wireless communication environments such as regional population density. With the changes of urban population density, environment, and social development requirement for network optimization, it is required to timely detect an antenna downtilt angle to determine whether it is needed to adjust the angle. In this case, antenna downtilt information is particularly important. In most cases, it is difficult for network optimizers to obtain the antenna downtilt information. Traditional measurement methods require professional tower workers to measure the antenna downtilt on the tower. Therefore, the traditional measurement methods are labor-consuming and time-consuming, and are difficult to ensure safety if the antenna downtilt after network optimization is the same as that before the network optimization. SUMMARY
    [0003] To solve the above problems, an objective of embodiments of the present disclosure is to provide a method for measuring an antenna downtilt based on a multi-scale detection algorithm, so as to conveniently measure the antenna downtilt in combination of unmanned aerial vehicle and deep learning algorithm.
    [0004] In order to solve the above problems, technical solutions are provided as follows according to the embodiments of the present disclosure.
    [0005] There is provided a method for measuring an antenna downtilt based on a multi-scale detection algorithm, including: capturing an image of an antenna using an unmanned aerial vehicle; obtaining a ground truth box where the antenna is located by performing the multi-scale detection algorithm on the image of the antenna; segmenting the ground truth box based on an antenna target segmentation algorithm of a server; and obtaining an antenna downtilt angle based on an antenna downtilt measurement algorithm of the server.
    [0006] Further, the obtaining a ground truth box where the antenna is located based on the multi-scale detection algorithm of the server includes: obtaining predictive boxes through a basic convolutional network; and obtaining the ground truth box through a multi-scale convolutional network.
    [0007] Further, the obtaining predictive boxes through a basic convolutional network includes: processing the image of the antenna by a plurality of series-connected convolutional layers, wherein the image of the antenna is max-pooled each time the image of the antenna is processed by one of the plurality of the series-connected convolutional layers; outputting a feature map by processing the max-pooled image of the antenna by two fully-connected layers and multiple layers of convolution kernels of different scales; and generating, on the feature map, the predictive boxes taking a center of the feature map as an origin and being concentric.
    [0008] Preferably, the predictive boxes include two square predictive boxes and two rectangular predictive boxes.
    [0009] Further, the obtaining the ground truth box through a multi-scale convolutional network includes: outputting a class probability and an offset between a location of the antenna and the predictive box after processing the image of the antenna with the predictive boxes by two convolutional layers convoluted in parallel by two 3∗3 convolution kernels; connecting parameters of the class probability after performing a channel concat, and obtaining, by using a loss function, a candidate box with a class predictive value and a regression predictive value; and obtaining the ground truth box by performing local maximum searching on the candidate box based on a non-maximum suppression algorithm.
    [0010] Preferably, the loss function used by the multi-scale convolutional network is L x c l g = 1 NL conf x c + αL loc x l g ;
    [0011] The segmenting the ground truth box based on an antenna target segmentation algorithm of a server includes: constructing a minimum spanning tree by classifying pixels within the ground truth box of the image of the antenna whose color distances L0 are close into one class; and performing a regional fusion based on a determination result obtained by comparing an intra-class variation and an inter-class difference.
    [0012] Preferably, the color distance L0 isL 0 = r 1 − r 2 2 +g 1 − g 2 2 +b 1 − b 2 2,
    [0013] Preferably, the intra-class variation within one ground truth box is Int c = max e ∈ MST Ee ,
    [0014] Beneficial effects of the embodiments of the present disclosure are as below. In the method for measuring an antenna downtilt based on a multi-scale detection algorithm according to the embodiments of the present disclosure, an image of an antenna captured by an unmanned aerial vehicle is processed based on deep learning networks to directly obtain an antenna downtilt angle. A ground truth box where the antenna is located can be accurately detected through the multi-scale detection algorithm, thereby improving the precision of obtaining the ground truth box, and ensuring the measurement of the antenna downtilt to be more accurate. This method avoids the danger of tower worker climbing, is fast and accurate, saves labor costs and time, and ensures the measurement of the antenna downtilt to be smoother. BRIEF DESCRIPTION OF THE DRAWINGS
    [0015] The present disclosure is further described below with reference to the accompanying drawings and examples.FIG. 1 is an overall flowchart of a method for measuring an antenna downtilt based on a multi-scale detection algorithm according to an embodiment of the present disclosure; FIG. 2 is a structural diagram of a basic convolutional network according to an embodiment of the present disclosure; FIG. 3 is a schematic diagram of a predictive box according to an embodiment of the present disclosure; FIG. 4 is a structural diagram of a convolutional layer of a multi-scale convolutional network convoluted in parallel by two 3∗3 convolution kernels according to an embodiment of the present disclosure; and FIG. 5 is a schematic diagram of obtaining an antenna downtilt angle based on an antenna downtilt measurement algorithm according to an embodiment of the present disclosure. DETAILED DESCRIPTION
    [0016] Referring to FIG. 1, In an embodiment of the present disclosure, a method for measuring an antenna downtilt based on a multi-scale detection algorithm is disclosed, including: capturing an image of an antenna using an unmanned aerial vehicle; obtaining a ground truth box where the antenna is located by processing the image of the antenna using the multi-scale detection algorithm; segmenting the ground truth box based on an antenna target segmentation algorithm of a server; and obtaining an antenna downtilt angle based on an antenna downtilt measurement algorithm of the server.
    [0017] Preferably, the multi-scale detection algorithm includes a basic convolutional network for obtaining predictive boxes and a multi-scale convolutional network for obtaining a ground truth box. Finally, the ground truth box where the antenna is located is obtained, including abscissa and ordinate as well as length and width of the ground truth box.
    [0018] Referring to FIG. 2, in one embodiment, the basic convolutional network is improved based on a VGG model, the image of the antenna is processed in sequence by a plurality of series-connected convolutional layers, and the image of the antenna is max-pooled each time the image of the antenna is processed by one of the series-connected convolutional layers. The plurality of series-connected convolutional layers include series-connected convolutional layers of two 64 convolution kernels, two 128 convolution kernels, three 256 convolution kernels, three 512 convolution kernels, and three 512 convolution kernels. The basic convolutional network outputs a feature map by processing the max-pooled image of the antenna by two fully-connected layers (i.e., a 3∗3 convolutional layer FC6, and a 1∗1 convolutional layer FC7) and four layers of convolution kernels of different scales. The feature map convolved in each layer is used as input of a next layer.
    [0019] Referring to FIG. 3, in one embodiment, the basic convolutional network generates, on the feature map, the predictive boxes taking a center of the feature map as an origin and being concentric, wherein the predictive boxes include two rectangular predictive boxes and two square predictive boxes. A side length of the smaller square predictive box is min size; a side length of the larger square predictive box is min _ size × max _ size ;
    [0020] A formula for calculating the side length of the predictive box is:s k = s min +s max − s minm − 1k − 1 ,
    [0021] Referring to FIG. 4, in one embodiment, the multi-scale convolutional network outputs a class probability and an offset between a location of the antenna and the predictive box after processing the image of the antenna with the predictive box by two convolutional layers convoluted in parallel by two 3∗3 convolution kernels. The feature map of a higher convolutional layer covers a wider perceptual field, and a larger object may be detected; whereas the feature map of the lower convolutional layer covers a narrower perceptual field, and a smaller object may be detected.
    [0022] Further, the multi-scale convolutional network connects 8732 parameters of each class probability after respectively performing a channel concat, to obtain a candidate box with a class predictive value and a regression predictive value. The ground truth box is obtained by performing local maximum searching on the candidate box based on a non-maximum suppression algorithm. Specifically, confidence scores of the candidate boxes are sorted from low to high, and the candidate box having the highest confidence score is selected as a pre-output box. An overlap rate between each candidate box and the pre-output box is calculated, the candidate box whose overlap rate is less than the threshold of 0.5 is selected as the ground truth box, and the area covered by the ground truth box is the optimal image of the antenna.
    [0023] In one embodiment, the loss function used by the multi-scale convolutional network is L x c l g = 1 NL conf x c + αL loc x l g ;
    [0024] In one embodiment, according to the antenna target segmentation algorithm, a minimum spanning tree is constructed by classifying pixels within the ground truth box of the image of the antenna whose color distances L0 are close into one class; and a regional fusion is performed based on a determination result obtained by comparing an intra-class variation and an inter-class difference. The color distance L0 is determined by an RGB distance, whereinL 0 = r 1 − r 2 2 +g 1 − g 2 2 +b 1 − b 2 2.
    [0025] The intra-class variation within one ground truth box is Int c = max e ∈ MST Ee ,
    [0026] If the intra-class variation within one ground truth box is far less than the inter-class difference between two ground truth boxes, i.e., Diff(c 1,c 2 ) ≤ min(Int(c 1),Int(c 2)), it is considered that the two ground truth boxes belong to the same antenna, and a regional fusion is performed.
    [0027] Referring to FIG. 5, in one embodiment, a downtilt of an antenna is an included angle between the antenna and a vertical plane, and a formula for measuring an antenna downtilt angle based on the antenna downtilt measurement algorithm is θ = arctan a b ,
    [0028] The above descriptions are merely preferred embodiments of the present disclosure, but the present disclosure is not limited to the above embodiments. Any embodiment should fall within the protection scope of the present disclosure as long as it achieves the technical effects of the present disclosure by the same means.
    权利要求:
    Claims (9)
    [0001] A method for measuring an antenna downtilt based on a multi-scale detection algorithm, comprising:
    capturing an image of an antenna using an unmanned aerial vehicle;
    obtaining a ground truth box where the antenna is located by performing the multi-scale detection algorithm on the image of the antenna;
    segmenting the ground truth box based on an antenna target segmentation algorithm of a server; and
    obtaining an antenna downtilt angle based on an antenna downtilt measurement algorithm of the server.
    [0002] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 1, wherein the obtaining a ground truth box where the antenna is located based on the multi-scale detection algorithm of the server comprises:
    obtaining predictive boxes through a basic convolutional network; and
    obtaining the ground truth box through a multi-scale convolutional network.
    [0003] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 2, wherein the obtaining predictive boxes through a basic convolutional network comprises:
    processing the image of the antenna by a plurality of series-connected convolutional layers,
    wherein the image of the antenna is max-pooled each time the image of the antenna is processed by one of the plurality of the series-connected convolutional layers;
    outputting a feature map by processing the max-pooled image of the antenna by two fully-connected layers and multiple layers of convolution kernels of different scales; and
    generating, on the feature map, the predictive boxes taking a center of the feature map as an origin and being concentric.
    [0004] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 3, wherein the predictive boxes comprise two square predictive boxes and two rectangular predictive boxes.
    [0005] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 2, wherein the obtaining the ground truth box through a multi-scale convolutional network comprises:
    outputting a class probability and an offset between a location of the antenna and the predictive box after processing the image of the antenna with the predictive boxes by two convolutional layers convoluted in parallel by two 3∗3 convolution kernels;
    connecting parameters of the class probability after performing a channel concat, and
    obtaining, by using a loss function, a candidate box with a class predictive value and a regression predictive value; and
    obtaining the ground truth box by performing local maximum searching on the candidate box based on a non-maximum suppression algorithm.
    [0006] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 5, wherein the loss function used by the multi-scale convolutional network is ; wherein N represents the number of the predictive boxes, α represents a preset weight, Lconf represents a classification loss, and Lloc represents a location loss.
    [0007] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 1, wherein the segmenting the ground truth box based on an antenna target segmentation algorithm of a server comprises:
    constructing a minimum spanning tree by classifying pixels within the ground truth box of the image of the antenna whose color distances L0 are close into one class; and
    performing a regional fusion based on a determination result obtained by comparing an intra-class variation and an inter-class difference.
    [0008] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 7, wherein the color distance L0 is L0=, wherein r, g, and b represent color channels.
    [0009] The method for measuring an antenna downtilt based on a multi-scale detection algorithm of claim 7, wherein the intra-class variation within one ground truth box is , wherein c represents a class, e represents a side having a minimum similarity in a minimum spanning tree of this class; the inter-class difference between two ground truth boxes is , wherein ω(vi, vj) represents sides connecting Class c1 and Class c2, vi represents a point on the Class cl, and vj represents a point on the Class c2.
    类似技术:
    公开号 | 公开日 | 专利标题
    CN106780612B|2019-09-17|Object detecting method and device in a kind of image
    US10540577B2|2020-01-21|System and method for detecting features in aerial images using disparity mapping and segmentation techniques
    CN104700099B|2017-08-11|The method and apparatus for recognizing traffic sign
    US20190156507A1|2019-05-23|Method and apparatus for processing point cloud data and storage medium
    CN106127204B|2019-08-09|A kind of multi-direction meter reading Region detection algorithms of full convolutional neural networks
    Li et al.2018|Automatic pavement crack detection by multi-scale image fusion
    US9536313B2|2017-01-03|Method and apparatus for direct detection, location, analysis, identification, and reporting of vegetation clearance violations
    CN108961235B|2021-05-14|Defective insulator identification method based on YOLOv3 network and particle filter algorithm
    CN103164858B|2015-09-09|Adhesion crowd based on super-pixel and graph model is split and tracking
    CN105955258B|2018-10-30|Robot global grating map construction method based on the fusion of Kinect sensor information
    CN103679674B|2017-01-11|Method and system for splicing images of unmanned aircrafts in real time
    CN105760886B|2019-04-12|A kind of more object segmentation methods of image scene based on target identification and conspicuousness detection
    Varadharajan et al.2014|Vision for road inspection
    CN104778721B|2017-08-11|The distance measurement method of conspicuousness target in a kind of binocular image
    US9563808B2|2017-02-07|Target grouping techniques for object fusion
    Awrangjeb et al.2010|Automatic detection of residential buildings using LIDAR data and multispectral imagery
    CN106803071B|2020-02-14|Method and device for detecting object in image
    CN106022232A|2016-10-12|License plate detection method based on deep learning
    US8340420B2|2012-12-25|Method for recognizing objects in images
    CA2840436C|2021-02-09|System for mapping and identification of plants using digital image processing and route generation
    Secord et al.2007|Tree detection in urban regions using aerial lidar and image data
    CN101975940B|2012-11-28|Segmentation combination-based adaptive constant false alarm rate target detection method for SAR image
    CN107316064B|2020-07-14|Asphalt pavement crack classification and identification method based on convolutional neural network
    Puissant et al.2005|The utility of texture analysis to improve per‐pixel classification for high to very high spatial resolution imagery
    CN104050481B|2017-05-03|Multi-template infrared image real-time pedestrian detection method combining contour feature and gray level
    同族专利:
    公开号 | 公开日
    CN109458978B|2020-12-01|
    WO2020093624A1|2020-05-14|
    CN109458978A|2019-03-12|
    US20210142519A1|2021-05-13|
    EP3680608A4|2021-06-02|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    法律状态:
    2020-03-11| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: UNKNOWN |
    2020-05-16| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
    2020-06-12| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
    2020-06-12| PUAI| Public reference made under article 153(3) epc to a published international application that has entered the european phase|Free format text: ORIGINAL CODE: 0009012 |
    2020-07-15| AX| Request for extension of the european patent|Extension state: BA ME |
    2020-07-15| AK| Designated contracting states|Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
    2020-07-15| 17P| Request for examination filed|Effective date: 20200311 |
    2020-11-25| RAP1| Party data changed (applicant data changed or rights of an application transferred)|Owner name: WUYI UNIVERSITY |
    2020-11-25| RIN1| Information on inventor provided before grant (corrected)|Inventor name: KE, QIRUI Inventor name: DENG, WENBO Inventor name: WANG, TIANLEI Inventor name: GAN, JUNYING Inventor name: GUAN, HUIXIN Inventor name: ZHI, YIHANG Inventor name: XU, YING Inventor name: ZHAI, YIKUI |
    2021-06-02| RIC1| Information provided on ipc code assigned before grant|Ipc: G01C1/00 20060101AFI20210426BHEP Ipc: G01R 29/10 20060101ALI20210426BHEP Ipc: G01C 11/04 20060101ALI20210426BHEP Ipc: H04W 24/08 20090101ALI20210426BHEP |
    2021-06-02| A4| Supplementary search report drawn up and despatched|Effective date: 20210503 |
    2022-02-16| DAX| Request for extension of the european patent (deleted)|
    2022-02-16| DAV| Request for validation of the european patent (deleted)|
    优先权:
    申请号 | 申请日 | 专利标题
    [返回顶部]