A method and device for determining the distribution of cameras for collecting pedestrian gaits
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WATRIX TECH CORP LTD
- Filing Date
- 2024-03-19
- Publication Date
- 2026-07-21
AI Technical Summary
When traditional cameras are installed and deployed in public places, on-site surveys are required and additional markers are needed, which can lead to errors in installation location, resulting in inaccurate camera distribution and affecting the accuracy of pedestrian gait data collection.
By using a preset world coordinate system and target gait video, the pedestrian's movement trajectory and trajectory point coordinates are determined. Combined with the camera's pose and pixel coordinates, the actual distance and deviation angle of the trajectory are calculated. The target pose of the camera is determined using a preset distance-deviation angle threshold, thus achieving adaptive distribution.
It improves the accuracy of camera installation and the precision of pedestrian gait data collection, simplifies the installation process, increases installation efficiency, and does not rely on additional markers.
Smart Images
Figure CN118172836B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data acquisition technology, and in particular to a method and apparatus for determining the distribution of cameras for acquiring pedestrian gait. Background Technology
[0002] With social development and technological progress, in order to protect public security and people's property, more and more public places are beginning to deploy and install cameras to collect the gait or gait trajectory of pedestrians in public places, in order to analyze whether the behavior of different pedestrians in public places is abnormal.
[0003] However, the installation, deployment, and distribution of cameras in traditional public places often require on-site surveys of different public places and continuous attempts and adjustments to the camera installation positions based on additional reference markers. Furthermore, due to the different measuring tools used in the on-site surveys, errors may occur in the camera installation positions, resulting in inaccurate camera distribution. This leads to blind spots in the collection of pedestrian gait patterns in the public place, thus affecting the accuracy and precision of the data collection. Summary of the Invention
[0004] In view of this, the purpose of this application is to provide a method and apparatus for determining the camera distribution for collecting pedestrian gait, which realizes adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera installation and deployment, and thus improves the precision and accuracy of pedestrian gait acquisition.
[0005] This application provides a method for determining the camera distribution for collecting pedestrian gait, the method comprising:
[0006] Based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area, the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory are determined. The target area is used to represent a preset closed area with fixed length, width and height.
[0007] For any camera in the target area, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian and the vertical direction of the camera.
[0008] Based on the actual distance of the trajectory, the trajectory deflection angle, and the preset distance-deflection angle threshold of the camera within the target area, the actual distance of the target trajectory and the target trajectory deflection angle of the target motion trajectory in the target area are determined, so as to determine the target pose of the camera according to the actual distance of the target trajectory and the target trajectory deflection angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
[0009] Furthermore, determining the actual distance and trajectory deviation of the target motion trajectory relative to the camera's trajectory at the preset pose, based on the camera's preset pose, the camera's pixel coordinates, and the gait region corresponding to the pedestrian in the target gait video, includes:
[0010] Based on the camera's preset pose and the camera's pixel coordinates, determine the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system;
[0011] Based on the target mapping relationship and the coordinates of each target trajectory point under the target motion trajectory, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
[0012] Furthermore, the preset pose of the camera includes the camera's initial coordinate information and the camera's initial attitude angle. The step of determining the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system based on the camera's preset pose and the camera's pixel coordinates includes:
[0013] The parameter matrix of the camera is determined based on the initial coordinate information and the initial attitude angle;
[0014] Based on the parameter matrix, the pixel coordinates of the camera, and the camera's built-in parameters, the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system is determined.
[0015] Furthermore, the step of determining the actual distance and trajectory deviation of the target motion trajectory relative to the camera at the preset pose, based on the camera's preset pose, the camera's pixel coordinates, and the gait region corresponding to the pedestrian in the target gait video, also includes:
[0016] Based on the camera's preset pose and the camera's pixel coordinates, the view frustum region of the camera in the preset world coordinate system is determined;
[0017] Based on the visual cone region and the gait region corresponding to the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
[0018] Furthermore, determining the actual target trajectory distance and target trajectory angle of the target motion trajectory within the target area based on the actual trajectory distance, the trajectory deflection angle, and a preset distance-deflection angle threshold for the camera within the target area includes:
[0019] Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle, a candidate distance-deflection angle set for the target trajectory under the target area is determined. The candidate distance-deflection angle set includes at least one candidate trajectory actual distance and at least one candidate trajectory deflection angle.
[0020] Based on the preset distance-angle threshold of the camera within the target area and the candidate distance-angle set, the actual distance and target trajectory angle of the target motion trajectory within the target area are determined.
[0021] Furthermore, determining the candidate distance-angle set of the target trajectory in the target region based on multiple poses of each camera, the actual distance of the target motion trajectory under each of the multiple poses of the cameras, and the trajectory deflection angle includes:
[0022] Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle, the initial distance-angle set of the target motion trajectory under the target area is determined;
[0023] For trajectory deflection angles that are the same in the initial distance-angle set, merge them, and determine the candidate trajectory deflection angles from the merged trajectory deflection angles;
[0024] The longest actual distance of the trajectory corresponding to the same trajectory deflection angle is determined as the actual distance of the candidate trajectory corresponding to the candidate trajectory deflection angle;
[0025] Based on the candidate trajectory deflection angle and the actual distance of the candidate trajectory, the initial distance-angle set of the target motion trajectory under the target area is determined.
[0026] Furthermore, determining the actual distance and target trajectory deflection of the target motion trajectory within the target area based on a preset distance-angle threshold for cameras within the target area and the candidate distance-angle set includes:
[0027] Determine whether the candidate distance-angle set contains the actual distance and candidate trajectory angle of a candidate trajectory that are within a preset distance-angle threshold.
[0028] If they exist, the actual distance of the candidate trajectory and the deviation angle of the candidate trajectory are determined as the actual distance of the target trajectory and the deviation angle of the target trajectory under the target area.
[0029] This application embodiment also provides a device for determining the camera distribution for collecting pedestrian gait, the device for determining the camera distribution for collecting pedestrian gait includes:
[0030] The first determining module is used to determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area. The target area is used to represent a preset closed area with fixed length, width and height.
[0031] The second determining module is used to determine, for any camera in the target area, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian in the target gait video. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian and the vertical direction of the camera.
[0032] The third determining module is used to determine the actual distance and target trajectory angle of the target motion trajectory in the target area based on the actual distance of the trajectory, the trajectory deviation angle, and the preset distance-deviation angle threshold of the camera in the target area, so as to determine the target pose of the camera according to the actual distance and target trajectory deviation angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
[0033] This application embodiment also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the method for determining the distribution of camera images of pedestrian gait as described above are performed.
[0034] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the method for determining the camera distribution for collecting pedestrian gait as described above.
[0035] The method and apparatus for determining camera distribution for collecting pedestrian gait postures provided in this application, compared with the existing methods for determining camera distribution, determine the target motion trajectory of the pedestrian and the coordinates of each target trajectory point in the target area by using a preset world coordinate system and the target gait video of the pedestrian in the target area. Based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area of the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. Based on the actual trajectory distance, trajectory deviation, and a preset distance-angle threshold of the camera in the target area, the actual distance and trajectory deviation of the target motion trajectory in the target area are determined, as well as the gait area of the pedestrian in the target gait video. This application achieves adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera installation and deployment, and thus improves the accuracy and precision of pedestrian gait posture acquisition.
[0036] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0037] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1 This document illustrates one of the flowcharts for a method of determining the camera distribution for collecting pedestrian gait, as provided in an embodiment of this application.
[0039] Figure 2 The second flowchart illustrates a method for determining the camera distribution for collecting pedestrian gait, as provided in an embodiment of this application.
[0040] Figure 3 This paper shows a structural block diagram of a device for determining the distribution of cameras for collecting pedestrian gait, provided in an embodiment of this application.
[0041] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.
[0042] 300 - Device for determining the distribution of cameras that capture pedestrian gait; 310 - First determining module; 320 - Second determining module; 330 - Third determining module; 400 - Electronic device; 410 - Processor; 420 - Memory; 430 - Bus. Detailed Implementation
[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.
[0044] First, the applicable scenarios for this application will be introduced. This application can be applied to the field of data acquisition technology.
[0045] Research has found that the installation, deployment, and distribution of cameras in traditional public places often require on-site surveys of different public places and continuous attempts and adjustments to the camera installation positions based on additional reference markers. Furthermore, the different measuring tools used in the on-site surveys can lead to errors in the camera installation positions and inaccurate camera distribution. This results in blind spots in the collection of pedestrian gait patterns in the public place, thus affecting the accuracy and precision of the data collection.
[0046] Based on this, embodiments of this application provide a method and apparatus for determining the camera distribution for collecting pedestrian gait, which realizes adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera installation and deployment, and thus improves the precision and accuracy of pedestrian gait collection.
[0047] Please see Figure 1 , Figure 1 This is one of the flowcharts illustrating a method for determining the camera distribution for collecting pedestrian gait, provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the method for determining the camera distribution for collecting pedestrian gait includes the following steps:
[0048] S101. Based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area, determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory, wherein the target area is used to represent a preset closed area with fixed length, width and height.
[0049] In this step, the preset world coordinate system and target area in the embodiments provided in this application can be modeled and selected according to different application scenarios, and the origin in the preset world coordinate system can be any point in the selected application scenario, and the preset world coordinate system in the embodiments provided in this application is a three-dimensional coordinate system.
[0050] Here, in the embodiments provided in this application, the target region is assumed to be: a cube with length L, width W, and height H, and the cube has 8 vertices. The minimum and maximum coordinates are respectively: .
[0051] In the embodiments provided in this application, the target motion trajectory is a straight line, and the coordinates of each target trajectory point on the target motion trajectory are... satisfy: , , .
[0052] S102. For any camera in the target area, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian to be detected in the target gait video, determine the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian to be detected and the vertical direction of the camera.
[0053] In this step, the number of cameras in the embodiments provided in this application can be customized according to different application scenarios, and the preset pose of the cameras in the embodiments provided in this application can be set to... ,in, Used to characterize the preset pose of the camera. Used to characterize the rotation angle of the camera relative to the coordinate axes.
[0054] Here, the camera's pixel coordinates are used to represent the camera's coordinates in the pixel coordinate system.
[0055] In the embodiments provided in this application, the gait region corresponding to the pedestrian to be detected in the target gait video can be specifically set as a quadrilateral region ABCD (assuming the pedestrian width is 0).
[0056] Here, the trajectory deflection angle is used to characterize the angle between the target motion trajectory of the pedestrian to be detected and the vertical direction of the camera, and the trajectory deflection angle in the embodiments provided in this application can be specifically the angle between the vertical direction of the camera and the direction of the target motion trajectory of the pedestrian to be detected by rotating counterclockwise.
[0057] Optionally, step S102 includes the following sub-steps:
[0058] Sub-step 1021: Based on the camera's preset pose and the camera's pixel coordinates, determine the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system.
[0059] In this step, the parameter matrix of the camera is determined based on the initial coordinate information and the initial attitude angle; the target mapping relationship between the preset world coordinate system and the pixel coordinate system of the camera is determined based on the parameter matrix, the pixel coordinates of the camera, and the built-in parameters of the camera.
[0060] Here, the formula for determining the target mapping relationship is as follows:
[0061]
[0062] in, Used to characterize the parameter matrix.
[0063] The parameter matrix is composed of Calculated.
[0064] in, This provides the initial coordinate information for the camera.
[0065] here , , .
[0066] in , These are built-in parameters of the camera, and their values can be the factory default values or values obtained through camera calibration.
[0067] Sub-step 1022: Based on the target mapping relationship and the coordinates of each target trajectory point under the target motion trajectory, determine the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose.
[0068] In this step, the actual distance and trajectory angle of the camera can be specifically defined as follows:
[0069]
[0070] Optionally, step S102 further includes the following sub-steps:
[0071] Sub-step 1023: Determine the view frustum region of the camera in the preset world coordinate system based on the preset pose of the camera and the pixel coordinates of the camera.
[0072] In this step, the viewing cone region is used to characterize the area image generated by the camera when it captures the pedestrian to be detected in a preset pose, in a preset world coordinate system.
[0073] Sub-step 1024: Based on the visual cone region and the gait region corresponding to the pedestrian to be detected in the target gait video, determine the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose.
[0074] In this step, the embodiments provided in this application determine whether the gait region corresponding to the pedestrian to be detected in the target gait video coincides with or intersects with the visual cone region, thereby determining the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose.
[0075] Here, if the gait region corresponding to the target gait video does not coincide with or intersect with the visual cone region, the target gait video will not be collected for the pedestrian to be tested.
[0076] In the above, the camera frustum equation in the preset world coordinate system can be calculated based on the camera's preset pose (i.e., the camera's initial coordinate information and the camera's initial attitude angle), and the actual distance and trajectory deviation of the target's motion trajectory relative to the camera in the preset pose can be determined based on the camera frustum equation.
[0077] S103. Based on the actual distance of the trajectory, the trajectory deviation angle, and the preset distance-deviation angle threshold of the camera in the target area, determine the actual distance of the target trajectory and the target trajectory deviation angle of the target motion trajectory in the target area, so as to determine the target pose of the camera according to the actual distance of the target trajectory and the target trajectory deviation angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
[0078] In this step, the actual distance and trajectory deviation angle of the trajectory under multiple poses of each camera are combined to determine... Where n represents the number of cameras, and the combination of the actual trajectory distance and trajectory deflection angle is:
[0079]
[0080] here, Used to characterize the trajectory deflection angle of each of the aforementioned cameras in multiple poses; Used to characterize the actual distance of the trajectory under multiple poses of each of the aforementioned cameras.
[0081] The method for determining camera distribution for collecting pedestrian gait postures provided in this application, compared with the existing methods for determining camera distribution, uses a preset world coordinate system and a target gait video of the pedestrian to be detected in the target area to determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory. Based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian to be detected in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. Based on the actual trajectory distance, trajectory deviation, and a preset distance-angle threshold of the camera in the target area, the actual distance and target trajectory deviation of the target motion trajectory in the target area are determined, as well as the gait area corresponding to the pedestrian to be detected in the target gait video. This application achieves adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera installation and deployment, and thus improves the accuracy and precision of pedestrian gait posture acquisition.
[0082] The method for determining the camera distribution for collecting pedestrian gait postures provided in this application embodiment, compared with the existing methods for determining camera distribution, can provide the actual distance and target trajectory deviation of the camera in the target area. That is, the target pose of the camera can be determined without providing additional markers, which simplifies the actual distribution and installation process and improves the installation efficiency of the camera.
[0083] Please see Figure 2 , Figure 2 This is a second flowchart illustrating a method for determining the camera distribution for collecting pedestrian gait, provided as an embodiment of this application. Figure 2 As shown in the embodiments of this application, the method for determining the camera distribution for collecting pedestrian gait includes the following steps:
[0084] S201. Based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area, determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory, wherein the target area is used to represent a preset closed area with fixed length, width and height.
[0085] S202. For any camera in the target area, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian to be detected in the target gait video, determine the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian to be detected and the vertical direction of the camera.
[0086] S203. Based on the multiple poses of each of the cameras, the actual distance of the target motion trajectory under the multiple poses of each of the cameras, and the trajectory deflection angle, determine a candidate distance-deflection angle set for the target trajectory under the target area, wherein the candidate distance-deflection angle set includes at least one candidate trajectory actual distance and at least one candidate trajectory deflection angle.
[0087] Optionally, step S203 includes the following sub-steps:
[0088] Sub-step 2031: Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deviation angle, determine the initial distance-angle set of the target motion trajectory under the target area.
[0089] In this step, the initial distance-angle set in the embodiments provided in this application can be specifically set as follows:
[0090] ;
[0091] Sub-step 2032: Merge the same trajectory deflection angles in the initial distance-angle set, and determine the candidate trajectory deflection angles from the merged trajectory deflection angles.
[0092] In this step, the candidate trajectory deflection angle determined by the merged trajectory deflection angle has the same angle value as the trajectory deflection angle before merging.
[0093] Sub-step 2033: Determine the longest actual trajectory distance among the same trajectory deflection angles as the actual distance of the candidate trajectory corresponding to the candidate trajectory deflection angle.
[0094] In this step, the embodiments provided in this application can be specifically described as follows: Equal trajectory deflection angles are merged, leaving only the actual trajectory distance. The longest one is determined as the actual distance of the candidate trajectory corresponding to the candidate trajectory deflection angle.
[0095] Here, the longest trajectory distance can be specifically defined as the pose closer to the center of the image captured by the camera. .
[0096] Sub-step 2034: Determine the initial distance-angle set of the target motion trajectory in the target area based on the candidate trajectory deviation angle and the actual distance of the candidate trajectory.
[0097] In this step, the candidate trajectory deflection angle and the actual distance of the candidate trajectory corresponding to each camera in the target area are merged again to determine the initial distance-angle set of the target motion trajectory in the target area.
[0098] S204. Based on the preset distance-angle threshold of the camera in the target area and the candidate distance-angle set, determine the actual distance and target trajectory angle of the target motion trajectory in the target area, so as to determine the target pose of the camera according to the actual distance and target trajectory angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
[0099] In this step, the preset distance-angle threshold in the embodiments provided in this application can be customized according to the size of different target areas or requirements.
[0100] Optionally, step S204 includes the following sub-steps:
[0101] Sub-step 2041: Determine whether there exists a candidate trajectory actual distance and candidate trajectory deviation angle within the preset distance-deviation angle threshold in the candidate distance-deviation angle set.
[0102] In this step, it is determined whether the actual distance and deviation angle of each candidate trajectory in the candidate distance-angle set are within the preset distance-angle threshold.
[0103] Sub-step 2042: If they exist, the actual distance of the candidate trajectory and the deviation angle of the candidate trajectory are determined as the actual distance of the target trajectory and the deviation angle of the target trajectory under the target area.
[0104] In this step, if the candidate trajectory's actual distance and candidate trajectory's deviation angle do not exist, they will not be determined as the target trajectory's actual distance and target trajectory's deviation angle within the target area.
[0105] The descriptions of S201 to S202 can be referred to the descriptions of S101 to S102, and can achieve the same technical effect, so they will not be elaborated further.
[0106] The method for determining camera distribution for collecting pedestrian gait postures provided in this application, compared with the existing methods for determining camera distribution, uses a preset world coordinate system and a target gait video of the pedestrian to be detected in the target area to determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory. Based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian to be detected in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. Based on the actual trajectory distance, trajectory deviation, and a preset distance-deviation angle threshold of the camera in the target area, the actual distance and target trajectory deviation of the target motion trajectory in the target area are determined, as well as the gait area corresponding to the pedestrian to be detected in the target gait video. This application achieves adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera distribution, and thus improves the precision and accuracy of pedestrian gait posture acquisition.
[0107] The method for determining the camera distribution for collecting pedestrian gait postures provided in this application embodiment, compared with the existing methods for determining camera distribution, can provide the actual distance and target trajectory deviation of the camera in the target area. That is, the target pose of the camera can be determined without providing additional markers, which simplifies the actual distribution and installation process and improves the installation efficiency of the camera.
[0108] Please see Figure 3 , Figure 3 This is a schematic diagram of a camera deployment determination device for collecting pedestrian sequences, provided as an embodiment of this application. Figure 3 As shown, the camera distribution determination device 300 for collecting pedestrian gait patterns includes:
[0109] The first determining module 310 is used to determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory according to the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area. The target area is used to represent a preset closed area with fixed length, width and height.
[0110] The second determining module 320 is used to determine, for any camera in the target area, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait region corresponding to the pedestrian to be detected in the target gait video. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian to be detected and the vertical direction of the camera.
[0111] Optionally, the second determining module 320 is specifically used for:
[0112] Based on the camera's preset pose and the camera's pixel coordinates, a target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system is determined.
[0113] Based on the target mapping relationship and the coordinates of each target trajectory point under the target motion trajectory, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
[0114] Optionally, the preset pose of the camera includes the camera's initial coordinate information and the camera's initial attitude angle. Determining the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system based on the camera's preset pose and the camera's pixel coordinates includes:
[0115] The parameter matrix of the camera is determined based on the initial coordinate information and the initial attitude angle.
[0116] Based on the parameter matrix, the pixel coordinates of the camera, and the camera's built-in parameters, the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system is determined.
[0117] Optionally, the second determining module 320 is further specifically used for:
[0118] Based on the camera's preset pose and pixel coordinates, the viewing frustum region of the camera in the preset world coordinate system is determined.
[0119] Based on the visual cone region and the gait region corresponding to the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
[0120] The third determining module 330 is used to determine the actual target trajectory distance and the target trajectory deviation angle of the target motion trajectory in the target area based on the actual trajectory distance, the trajectory deviation angle and the preset distance-deviation angle threshold of the camera in the target area, so as to determine the target pose of the camera according to the actual target trajectory distance and the target trajectory deviation angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
[0121] Optionally, the third determining module 330 is specifically used for:
[0122] Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle, a candidate distance-deflection angle set for the target trajectory under the target area is determined. The candidate distance-deflection angle set includes at least one candidate trajectory actual distance and at least one candidate trajectory deflection angle.
[0123] Based on the preset distance-angle threshold of the camera within the target area and the candidate distance-angle set, the actual distance and target trajectory angle of the target motion trajectory within the target area are determined.
[0124] Optionally, determining the candidate distance-angle set of the target trajectory in the target region based on multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle includes:
[0125] Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deviation angle, the initial distance-angle set of the target motion trajectory under the target area is determined.
[0126] For the same trajectory deflection angle in the initial distance-angle set, merge them, and determine the candidate trajectory deflection angle from the merged trajectory deflection angle.
[0127] The longest actual distance of the trajectory corresponding to the same trajectory deflection angle is determined as the actual distance of the candidate trajectory corresponding to the candidate trajectory deflection angle.
[0128] Based on the candidate trajectory deflection angle and the actual distance of the candidate trajectory, the initial distance-angle set of the target motion trajectory under the target area is determined.
[0129] Optionally, determining the actual distance and target trajectory deflection of the target motion trajectory within the target area based on a preset distance-angle threshold of the camera within the target area and the candidate distance-angle set includes:
[0130] Determine whether there exists a candidate trajectory actual distance and candidate trajectory deviation angle in the candidate distance-angle set that are within the preset distance-angle threshold.
[0131] If they exist, the actual distance of the candidate trajectory and the deviation angle of the candidate trajectory are determined as the actual distance of the target trajectory and the deviation angle of the target trajectory under the target area.
[0132] The camera distribution determination device 300 for collecting pedestrian gait postures provided in this application embodiment, compared with the camera distribution determination device in the prior art, determines the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory by using a preset world coordinate system and the target gait posture video of the pedestrian to be detected in the target area. Based on the preset pose of the camera, the pixel coordinates of the camera, and the gait posture area corresponding to the pedestrian to be detected in the target gait posture video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. Based on the actual trajectory distance, trajectory deviation, and the preset distance-angle threshold of the camera in the target area, the actual distance and target trajectory deviation of the target motion trajectory in the target area are determined, as well as the gait posture area corresponding to the pedestrian to be detected in the target gait posture video. This application realizes adaptive camera distribution for target areas in different scenarios, improves the accuracy of camera distribution, and thus improves the accuracy and precision of pedestrian gait posture acquisition.
[0133] The camera distribution determination device for collecting pedestrian gait postures provided in this application embodiment, compared with the camera distribution determination device in the prior art, can give the actual distance and target trajectory deviation angle of the camera in the target area. That is, the target pose of the camera can be determined without providing additional markers, which simplifies the actual distribution and installation process and improves the installation efficiency of the camera.
[0134] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
[0135] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, they can perform the operations described above. Figure 1 as well as Figure 2 The steps of the camera deployment determination method for collecting pedestrian sequences in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.
[0136] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 as well as Figure 2The steps of the camera deployment determination method for collecting pedestrian sequences in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.
[0137] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0138] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0140] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0141] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0142] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for determining the distribution of cameras for collecting pedestrian gait, characterized in that, The method for determining the camera distribution for collecting pedestrian gait includes: Based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area, the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory are determined. The target area is used to represent a preset closed area with fixed length, width and height. For any camera in the target area, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian and the vertical direction of the camera. Based on the actual distance of the trajectory, the trajectory deflection angle, and the preset distance-deflection angle threshold of the camera within the target area, the actual distance of the target trajectory and the target trajectory deflection angle of the target motion trajectory in the target area are determined, so as to determine the target pose of the camera according to the actual distance of the target trajectory and the target trajectory deflection angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
2. The method for determining the camera distribution for collecting pedestrian gait according to claim 1, characterized in that, The step of determining the actual distance and trajectory deviation of the target motion trajectory relative to the camera's trajectory in the preset pose, based on the camera's preset pose, the camera's pixel coordinates, and the gait region corresponding to the pedestrian in the target gait video, includes: Based on the camera's preset pose and the camera's pixel coordinates, determine the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system; Based on the target mapping relationship and the coordinates of each target trajectory point under the target motion trajectory, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
3. The method for determining the camera distribution for collecting pedestrian gait according to claim 2, characterized in that, The preset pose of the camera includes the camera's initial coordinate information and the camera's initial attitude angle. Determining the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system based on the camera's preset pose and the camera's pixel coordinates includes: The parameter matrix of the camera is determined based on the initial coordinate information and the initial attitude angle; Based on the parameter matrix, the pixel coordinates of the camera, and the camera's built-in parameters, the target mapping relationship between the preset world coordinate system and the camera's pixel coordinate system is determined.
4. The method for determining the camera distribution for collecting pedestrian gait according to claim 3, characterized in that, The step of determining the actual distance and trajectory deviation of the target motion trajectory relative to the camera's trajectory in the preset pose, based on the camera's preset pose, the camera's pixel coordinates, and the gait region corresponding to the pedestrian to be detected in the target gait video, further includes: Based on the camera's preset pose and the camera's pixel coordinates, the view frustum region of the camera in the preset world coordinate system is determined; Based on the visual cone region and the gait region corresponding to the pedestrian in the target gait video, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose are determined.
5. The method for determining the camera distribution for collecting pedestrian gait according to claim 1, characterized in that, The step of determining the actual target trajectory distance and target trajectory angle within the target area based on the actual trajectory distance, the trajectory deflection angle, and a preset distance-deflection angle threshold for cameras within the target area includes: Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle, a candidate distance-deflection angle set for the target trajectory under the target area is determined. The candidate distance-deflection angle set includes at least one candidate trajectory actual distance and at least one candidate trajectory deflection angle. Based on the preset distance-angle threshold of the camera within the target area and the candidate distance-angle set, the actual distance and target trajectory angle of the target motion trajectory within the target area are determined.
6. The method for determining the camera distribution for collecting pedestrian gait according to claim 5, characterized in that, The process of determining a candidate distance-angle set for the target trajectory within the target region based on multiple poses of each camera, the actual distance of the target motion trajectory under each camera's multiple poses, and the trajectory deflection angle includes: Based on the multiple poses of each camera, the actual distance of the target motion trajectory under the multiple poses of each camera, and the trajectory deflection angle, the initial distance-angle set of the target motion trajectory under the target area is determined; For trajectory deflection angles that are the same in the initial distance-angle set, merge them, and determine the candidate trajectory deflection angles from the merged trajectory deflection angles; The longest actual distance of the trajectory corresponding to the same trajectory deflection angle is determined as the actual distance of the candidate trajectory corresponding to the candidate trajectory deflection angle; Based on the candidate trajectory deflection angle and the actual distance of the candidate trajectory, the initial distance-angle set of the target motion trajectory under the target area is determined.
7. The method for determining the camera distribution for collecting pedestrian gait according to claim 5, characterized in that, The step of determining the actual distance and target trajectory deflection of the target motion trajectory within the target area based on a preset distance-angle threshold of the camera within the target area and the candidate distance-angle set includes: Determine whether the candidate distance-angle set contains the actual distance and candidate trajectory angle of a candidate trajectory that are within a preset distance-angle threshold. If they exist, the actual distance of the candidate trajectory and the deviation angle of the candidate trajectory are determined as the actual distance of the target trajectory and the deviation angle of the target trajectory under the target area.
8. A device for determining the distribution of cameras for collecting pedestrian gait, characterized in that, The device for determining the distribution of cameras for collecting pedestrian gait includes: The first determining module is used to determine the target motion trajectory of the pedestrian to be detected in the target area and the coordinates of each target trajectory point under the target motion trajectory based on the preset world coordinate system and the target gait video of the pedestrian to be detected in the target area. The target area is used to represent a preset closed area with fixed length, width and height. The second determining module is used to determine, for any camera in the target area, the actual distance and trajectory deviation of the target motion trajectory relative to the camera in the preset pose, based on the preset pose of the camera, the pixel coordinates of the camera, and the gait area corresponding to the pedestrian in the target gait video. The trajectory deviation is used to characterize the angle between the target motion trajectory of the pedestrian and the vertical direction of the camera. The third determining module is used to determine the actual distance and target trajectory angle of the target motion trajectory in the target area based on the actual distance of the trajectory, the trajectory deviation angle, and the preset distance-deviation angle threshold of the camera in the target area, so as to determine the target pose of the camera according to the actual distance and target trajectory deviation angle, and deploy the camera according to the target pose to realize the acquisition of pedestrian gait video in the target area.
9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the method for determining the camera distribution for acquiring pedestrian gait as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the steps of the method for determining the camera distribution for collecting pedestrian gait as described in any one of claims 1-6.