CN117896626A - Method, device, equipment and storage medium for detecting motion trajectory with multiple cameras - Google Patents

Abstract

The application relates to the technical field of motion trail detection and provides a method, a device, equipment and a storage medium for detecting motion trail by multiple cameras. The method comprises the steps of obtaining a plurality of videos to be identified, which are shot by a plurality of cameras, and selecting a target video from the videos to be identified based on target characteristic information of a target object; wherein the target object appears in the target video, the target video including a plurality of; determining a motion track point of the target object in the monitoring area according to the target videos and a pixel coordinate network corresponding to the target videos, and labeling time labels for the motion track points; and generating a target motion track of the target object in the monitoring area based on the motion track points and the time labels corresponding to the motion track points. The method can detect the motion trail of the target object in the monitoring area through a plurality of cameras.

Description

Method, device, equipment and storage medium for detecting motion trajectory with multiple cameras

Technical Field

The present application relates to the field of motion trajectory detection technology, and in particular to a method, device, equipment and storage medium for detecting motion trajectories with multiple cameras.

Background technique

With the continuous development of camera technology, camera monitoring technology has been widely used in public places, factories, shops, etc. However, traditional camera monitoring technology usually only provides monitoring images of a single camera, and the monitoring reliability is low.

At present, some multi-camera monitoring technologies have been proposed. However, the existing multi-camera monitoring technologies can only identify the target object across scenes and cannot accurately identify the whereabouts of the target object.

Summary of the invention

The present application provides a method, device, equipment and storage medium for detecting motion trajectories with multiple cameras to solve the problems raised by the above-mentioned background technology.

In a first aspect, the present application provides a method for detecting motion trajectories with multiple cameras, for detecting the motion trajectory of a target object in a monitoring area, wherein the monitoring area is provided with multiple cameras, each of the cameras being provided at a different position in the monitoring area, and the method comprises:

Constructing a spatial rectangular coordinate system with the designated point of the monitoring area as the coordinate origin;

For each of the cameras, generating a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system;

Acquire a plurality of videos to be identified taken by a plurality of the cameras, and select a target video from the plurality of videos to be identified based on target feature information of the target object; wherein the target object appears in the target video, and the target video includes a plurality of videos;

For each of the target videos, determine the motion trajectory points of the target object in the monitoring area based on the target video and the pixel coordinate grid corresponding to the target video, and mark each of the motion trajectory points with a time tag;

Generate a target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and the time tag corresponding to each of the motion trajectory points;

The target motion trajectory is stored in a preset database.

In a second aspect, the present application provides a device for detecting motion trajectories with multiple cameras, which is used to detect the motion trajectory of a target object in a monitoring area, wherein the monitoring area is provided with multiple cameras, each of which is provided at a different position in the monitoring area, and the device comprises:

A construction module, used to construct a spatial rectangular coordinate system with a designated point of the monitoring area as a coordinate origin;

A first generating module, configured to generate, for each of the cameras, a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system;

A selection module is used to obtain a plurality of videos to be identified taken by a plurality of cameras, and select a target video from the plurality of videos to be identified based on target feature information of the target object; wherein the target object appears in the target video, and the target video includes a plurality of videos;

A determination module, configured to determine, for each of the target videos, a motion trajectory point of the target object in the monitoring area based on the target video and a pixel coordinate grid corresponding to the target video, and mark each of the motion trajectory points with a time tag;

A second generating module, configured to generate a target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and a time tag corresponding to each of the motion trajectory points;

The storage module is used to store the target motion trajectory in a preset database.

In a third aspect, the present application provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method of multi-camera motion trajectory detection as described above is implemented.

In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for detecting motion trajectories using multiple cameras as described above is implemented.

The present application provides a method, device, equipment and storage medium for detecting motion trajectories with multiple cameras, wherein the method is used to detect the motion trajectory of a target object in a monitoring area, wherein the monitoring area is provided with multiple cameras, and each of the cameras is provided at a different position in the monitoring area, and the method comprises:

A spatial rectangular coordinate system is constructed with the designated point of the monitoring area as the coordinate origin; for each of the cameras, a pixel coordinate grid corresponding to the shooting area of the camera is generated based on the shooting area of the camera and the rectangular coordinate system; multiple videos to be identified shot by multiple cameras are obtained, and a target video is selected from the multiple videos to be identified based on the target feature information of the target object; wherein the target object appears in the target video, and the target video includes multiple; for each of the target videos, the motion trajectory points of the target object in the monitoring area are determined based on the target video and the pixel coordinate grid corresponding to the target video, and a time tag is marked on each of the motion trajectory points; a target motion trajectory of the target object in the monitoring area is generated based on each of the motion trajectory points and the time tag corresponding to each of the motion trajectory points; and the target motion trajectory is stored in a preset database. In this embodiment, on the one hand, the videos to be identified shot by multiple cameras can be analyzed and integrated to generate the motion trajectory of the target object in the monitoring area, which helps to provide more comprehensive and reliable security management measures. On the other hand, by storing the target motion trajectory in a preset database, the long-term preservation and tracing of monitoring information can be achieved, providing reliable data support for future safety inspections, accident investigations, and even research and analysis.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

FIG1 is a schematic diagram of a flow chart of a method for detecting motion trajectories using multiple cameras provided in an embodiment of the present application;

FIG2 is a schematic block diagram of the structure of a device for detecting motion trajectories using multiple cameras provided in an embodiment of the present application;

FIG3 is a schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

Detailed ways

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations/steps, nor must they be executed in the order described. For example, some operations/steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term “and/or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

With the continuous development of camera technology, camera monitoring technology has been widely used in public places, factories, shops, etc. However, traditional camera monitoring technology usually only provides monitoring images of a single camera, and the monitoring reliability is low.

At present, some multi-camera monitoring technologies have been proposed, but the existing multi-camera monitoring technologies can only identify the target object across scenes and cannot accurately identify the whereabouts of the target object. To this end, the present application provides a method, device, equipment and storage medium for detecting motion trajectories with multiple cameras to solve the above problems.

In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

Please refer to Figure 1, which is a flow chart of the method for detecting motion trajectories with multiple cameras provided in an embodiment of the present application. The method is used to detect the motion trajectory of a target object in a monitoring area. The monitoring area is provided with multiple cameras, and each of the cameras is located at a different position of the monitoring area. As shown in Figure 1, the method for detecting motion trajectories with multiple cameras provided in an embodiment of the present application includes steps S100 to S600.

Step S100: constructing a spatial rectangular coordinate system with the designated point of the monitoring area as the coordinate origin.

Step S200: for each of the cameras, generate a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system.

Step S300, obtaining multiple videos to be identified shot by multiple cameras, and selecting a target video from the multiple videos to be identified based on target feature information of the target object; wherein the target object appears in the target video, and the target video includes multiple videos.

Step S400: for each of the target videos, determine the motion trajectory points of the target object in the monitoring area based on the target video and the pixel coordinate grid corresponding to the target video, and mark each of the motion trajectory points with a time tag.

Step S500: generating a target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and a time tag corresponding to each of the motion trajectory points.

Step S600: storing the target motion trajectory in a preset database.

In this embodiment, as described in step S100 above, a spatial rectangular coordinate system is constructed with the designated point of the monitoring area as the coordinate origin. Specifically, first, a designated point is found in the monitoring area, and then three rectangular coordinate axes X, Y and Z are established with the designated point as the coordinate origin to obtain the rectangular coordinate system. The designated point may be the center of the monitoring area or other landmark locations within the monitoring area, and the designated point is selected or input by the user through the interface of the monitoring system. The monitoring area may be a public area of a factory or a public area of a workshop, shopping mall, hospital, school, etc.

As described in the above step S200, after constructing a spatial rectangular coordinate system with the designated point of the monitoring area as the coordinate origin, for each of the cameras, a pixel coordinate grid corresponding to the shooting area of the camera is generated based on the shooting area of the camera and the rectangular coordinate system. Specifically, for each of the cameras, first, an image of the shooting area corresponding to the camera is acquired, and then, for each pixel of the image, the target area corresponding to the pixel in the monitoring area is determined, and the coordinate point corresponding to the center point of the target area is determined in the spatial rectangular coordinate system, and the coordinate point is marked on the pixel to obtain the pixel coordinate grid. It can be understood that the image of the shooting area corresponding to the camera is obtained by shooting the camera, and when the pixel coordinate grid is generated for the shooting area, there is no moving person or object in the shooting area.

As described in the above step S300, when it is necessary to detect the motion trajectory of the target object, a plurality of videos to be identified shot by a plurality of the cameras are obtained, and a target video is selected from the plurality of videos to be identified based on the target feature information of the target object. Specifically, first, a plurality of videos to be identified shot by a plurality of the cameras are obtained in a preset database, then the target feature information of the target object is determined, and finally, a target video is selected from the plurality of videos to be identified based on the target feature information of the target object. When the target object is active in the monitoring area, a plurality of the cameras photograph the monitoring area to obtain a plurality of videos to be identified, and the target feature information of the target object includes but is not limited to the contour features and running posture features of the target object. The target objects include pedestrians, customers, mobile robots, etc.

As described in step S400 above, after obtaining a plurality of target videos, for each of the target videos, based on the target video and the pixel coordinate grid corresponding to the target video, the motion trajectory point of the target object in the monitoring area is determined, and a time tag is marked for each of the motion trajectory points. Specifically, for each of the target videos, first, the target video is framed to obtain a plurality of video frames corresponding to the target video, and a time tag is marked for each of the video frames based on the corresponding timing of each of the video frames in the target video, and then, a target video frame including the target object is selected from the plurality of video frames, and then, for each of the target video frames, the center point position of the image contour corresponding to the target object in the target video frame is obtained, and the center point position is marked on the target video frame, and finally, for each of the target video frames, the pixel coordinate grid is mapped to the target video frame with the center point position marked, so as to determine the target coordinate point corresponding to the pixel at the center point position corresponding to the target video frame, and the time tag corresponding to the target video frame is marked for the target coordinate point, and the target coordinate point marked with the time tag is used as the motion trajectory point corresponding to the target video frame. It can be understood that, since the target object is constantly moving, there is at least one motion trajectory point of the target object in the same target video.

As described in the above step S500, after obtaining each of the motion trajectory points, the target motion trajectory of the target object in the monitoring area is generated based on each of the motion trajectory points and the time tags corresponding to each of the motion trajectory points. Specifically, first, each of the motion trajectory points is marked in the spatial rectangular coordinate system, and then, based on the time tags corresponding to each of the motion trajectory points, each of the motion trajectory points is sequentially connected to obtain the initial motion trajectory of the target object, and then, the initial motion trajectory is smoothed to obtain an intermediate motion trajectory, and finally, based on the time tags corresponding to each of the motion trajectory points, the starting point and the end point of the movement of the target object in the monitoring area are marked on the intermediate motion trajectory to obtain the target motion trajectory.

As described in step S600, the target motion trajectory is stored in a preset database. Specifically, the target motion trajectory is stored in a preset database corresponding to the monitoring area. It can be understood that the purpose of storing the motion trajectory in the preset database is to facilitate querying the motion trajectory.

The method provided in this embodiment, on the one hand, can analyze and integrate the videos to be identified taken by multiple cameras to generate the movement trajectory of the target object in the monitoring area, which helps to provide more comprehensive and reliable security management measures; on the other hand, by storing the target movement trajectory in a preset database, it can achieve long-term preservation and traceability of monitoring information, providing reliable data support for future safety inspections, accident investigations, and even research and analysis.

In some embodiments, generating a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system comprises the following steps:

Acquire an image of a shooting area corresponding to the camera;

For each pixel of the image, determine the target area corresponding to the pixel in the monitoring area, determine the coordinate point corresponding to the center point of the target area in the spatial rectangular coordinate system, and mark the coordinate point on the pixel to obtain the pixel coordinate grid.

In this embodiment, first, an image of the shooting area corresponding to the camera is obtained. Specifically, when there is no moving person or object in the monitoring area, the camera shoots the shooting area corresponding to the camera to obtain the image of the shooting area corresponding to the camera.

Then, after obtaining the image, for each pixel of the image, determine the target area corresponding to the pixel in the monitoring area, determine the coordinate point corresponding to the center point of the target area in the spatial rectangular coordinate system, and mark the coordinate point on the pixel to obtain the pixel coordinate grid. Specifically, first, for each pixel of the image, according to the position, orientation and imaging parameters of the camera, geometrically correct the pixel, and map the pixel after geometric correction to the actual monitoring area to obtain the target area corresponding to the pixel in the monitoring area, then determine the coordinate point corresponding to the center point of the target area in the spatial rectangular coordinate system, and mark the coordinate point on the pixel to obtain the pixel coordinate grid.

The method provided in this embodiment can accurately locate the actual position of the pixel in the monitoring area by marking the coordinate point of the center point of the target area corresponding to the pixel in the monitoring area on each pixel, which helps to accurately establish the corresponding relationship between the pixel and the spatial rectangular coordinate system, and further helps to accurately detect the motion trajectory of the target object.

In some embodiments, the step of selecting a target video from a plurality of videos to be identified based on target feature information of the target object comprises the following steps:

For each of the videos to be identified, play the video to be identified to obtain multiple objects to be matched in the video to be identified;

For each of the videos to be identified, extract the to-be-matched feature information of each of the to-be-matched objects corresponding to the videos to be identified, obtain the first similarities between each of the to-be-matched feature information and the target feature information, and select the maximum similarity among the first similarities;

For each of the videos to be identified, the maximum similarity corresponding to the video to be identified is compared with a first preset similarity, and if the maximum similarity is greater than the first preset similarity, the video to be identified is determined to be a target video.

In this embodiment, first, for each video to be identified, the video to be identified is played to obtain multiple objects to be matched in the video to be identified. Specifically, for each video to be identified, the video to be identified is played frame by frame to obtain objects to be matched in each frame of the video to be identified.

Then, for each of the videos to be identified, extract the feature information to be matched of each of the objects to be matched corresponding to the videos to be identified, obtain the first similarity between each of the feature information to be matched and the target feature information, and select the maximum similarity among the first similarities. Specifically, for each of the videos to be identified, first, input each of the objects to be matched corresponding to the videos to be identified into a preset object feature information extraction model to obtain the feature information to be matched of each of the objects to be matched, then input the target feature information and each of the feature information to be matched into a preset feature vector extraction model to obtain a target feature vector and multiple feature vectors to be matched, calculate the first similarity between the target feature vector and each of the feature vectors to be matched, and finally select the maximum similarity among the first similarities. Wherein, the object feature extraction model includes an input layer, a feature extraction layer, and an output layer, and the feature vector extraction model includes an input layer, a feature vector generation layer, and an output layer.

Finally, for each of the videos to be identified, the maximum similarity corresponding to the video to be identified is compared with a first preset similarity, and if the maximum similarity is greater than the first preset similarity, the video to be identified is determined to be a target video.

The method provided in this embodiment can accurately select the target video from a plurality of videos to be identified, which helps to improve the accuracy of motion trajectory detection.

In some embodiments, determining the motion trajectory points of the target object in the monitoring area based on the target video and the pixel coordinate grid corresponding to the target video, and marking a time tag for each of the motion trajectory points, includes the following steps:

Performing frame processing on the target video to obtain a plurality of video frames corresponding to the target video, and marking a time tag on each of the video frames based on a time sequence corresponding to each of the video frames in the target video;

Selecting a target video frame from the plurality of video frames; wherein the target video frame includes at least one, and the target video frame includes the target object in its picture;

For each of the target video frames, obtaining the center point position of the image contour corresponding to the target object in the target video frame, and marking the center point position on the target video frame;

For each of the target video frames, the pixel coordinate grid is mapped to the target video frame with the center point position marked to determine the target coordinate point corresponding to the pixel at the center point position corresponding to the target video frame, and the target coordinate point is marked with the time tag corresponding to the target video frame, and the target coordinate point marked with the time tag is used as the motion trajectory point corresponding to the target video frame.

In this embodiment, first, the target video is subjected to frame processing to obtain a plurality of video frames corresponding to the target video, and a time tag is marked on each of the video frames based on the timing corresponding to each of the video frames in the target video. Specifically, first, the target video is subjected to frame processing using video processing software to decompose the target video into a plurality of video frames, and then, for each of the video frames, the timing information of the video frame is obtained, and a time tag is marked on the video frame based on the timing information. The video processing software may be OpenCV, ffmpeg or other video processing software.

Then, a video frame including the target object is selected from the plurality of video frames as a target video frame.

Secondly, for each of the target video frames, the center point position of the image contour corresponding to the target object in the target video frame is obtained, and the center point position is marked on the target video frame. Specifically, for each of the target video frames, first, edge detection is performed on the target object in the target video frame using an edge detection algorithm to obtain the image contour of the target object, then a circumscribed circle of the image contour is constructed, and the center of the circumscribed circle of the image contour is used as the center point position of the image contour, and finally, the center point position is marked on the target video frame.

Finally, for each target video frame, the pixel coordinate grid is mapped to the target video frame with the center point position marked, so as to determine the target coordinate point corresponding to the pixel at the center point position corresponding to the target video frame, and the target coordinate point is marked with the time tag corresponding to the target video frame, and the target coordinate point marked with the time tag is used as the motion trajectory point corresponding to the target video frame. It can be understood that one target video frame corresponds to one motion trajectory point.

The method provided in this embodiment obtains multiple video frames corresponding to the target video by performing frame processing on the target video, and obtains the motion point trajectory of the target object on each of the video frames, which helps to accurately determine the motion trajectory of the target object in the monitoring area.

In some embodiments, generating the target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and the time tags corresponding to each of the motion trajectory points includes the following steps:

Marking each of the motion trajectory points in the spatial rectangular coordinate system;

Connecting the motion trajectory points in sequence based on the time tags corresponding to the motion trajectory points to obtain an initial motion trajectory of the target object;

Smoothing the initial motion trajectory to obtain an intermediate motion trajectory;

The movement start point and the movement end point of the target object in the monitoring area are marked on the intermediate movement trajectory based on the time tags corresponding to the respective movement trajectory points, so as to obtain the target movement trajectory.

In this embodiment, first, each of the motion trajectory points is marked in the spatial rectangular coordinate system. Specifically, the target coordinate point corresponding to each of the motion trajectory points is marked in the spatial rectangular coordinate system.

Then, the motion trajectory points are connected in sequence based on the time tags corresponding to the motion trajectory points to obtain the initial motion trajectory of the target object.

Secondly, the initial motion trajectory is smoothed to obtain an intermediate motion trajectory. Specifically, the initial motion trajectory can be smoothed by using a moving translation method, a Bayesian filtering method, a Kalman filtering method, or the like.

Finally, based on the time tags corresponding to the various motion trajectory points, the motion start point and the motion end point of the target object in the monitoring area are marked on the intermediate motion trajectory to obtain the target motion trajectory.

The method provided in this embodiment, on the one hand, obtains the initial motion trajectory of the target object by marking each of the motion trajectory points in the spatial rectangular coordinate system, and sequentially connects each of the motion trajectory points based on the time tags corresponding to each of the motion trajectory points, and then smoothes the initial motion trajectory to obtain a continuous intermediate motion trajectory with a certain degree of accuracy. This helps to analyze the motion trajectory of the target object more accurately. On the other hand, the starting point and the end point of the target object in the monitoring area are marked on the intermediate motion trajectory, so that the analyst can clearly understand the motion trajectory of the target object in the monitoring area.

In some embodiments, storing the target motion trajectory in a preset database comprises the following steps:

Obtaining an area identifier of the monitoring area and a camera identifier of each of the cameras;

Arrange the camera identifiers in sequence based on the positions of the cameras corresponding to the camera identifiers in the monitoring area to obtain a camera identifier sequence;

For each region identification character of the region identification, construct a blank set;

For each of the blank sets, respectively obtain a second similarity between the region identification character corresponding to the blank set and each camera identification character of the camera identification sequence, and compare each of the second similarities with a second preset similarity, and when the second similarity is greater than the second preset similarity, use the camera identification character corresponding to the second similarity as the target camera identification character corresponding to the blank set;

For each of the blank sets, based on the order of each of the target camera identification characters corresponding to the blank set in the camera identification sequence, each of the target camera identification characters corresponding to the blank set is sequentially filled into the blank set to obtain a to-be-selected set;

Determine a target set from all the candidate sets; the target set corresponds to the most target camera identification characters;

The target motion trajectory is encrypted based on the target set, and the encrypted target motion trajectory is stored in a preset database.

The method provided in this embodiment generates the target set through the area identifier and the camera identifier, encrypts the target motion trajectory based on the target set, and stores the encrypted target motion trajectory in a preset database. This can improve the security of the target motion trajectory, prevent the target motion trajectory from being stolen, and achieve effective management of the target motion trajectory.

Please refer to FIG. 2 , which is a schematic block diagram of the structure of a multi-camera motion trajectory detection device 100 provided in an embodiment of the present application. The multi-camera motion trajectory detection device 100 is used to detect the motion trajectory of a target object in a monitoring area. The monitoring area is provided with multiple cameras, and each of the cameras is provided at a different position of the monitoring area. As shown in FIG. 2 , the multi-camera motion trajectory detection device 100 includes:

The construction module 110 is used to construct a spatial rectangular coordinate system with the designated point of the monitoring area as the coordinate origin.

The first generating module 120 is configured to generate, for each of the cameras, a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system.

The selection module 130 is used to obtain multiple videos to be identified taken by multiple cameras, and select a target video from the multiple videos to be identified based on target feature information of the target object; wherein the target object appears in the target video, and the target video includes multiple videos.

The determination module 140 is used to determine, for each of the target videos, the motion trajectory points of the target object in the monitoring area based on the target video and the pixel coordinate grid corresponding to the target video, and mark each of the motion trajectory points with a time tag.

The second generating module 150 is configured to generate a target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and a time tag corresponding to each of the motion trajectory points.

The storage module 160 is used to store the target motion trajectory in a preset database.

It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned multi-camera motion trajectory detection method embodiment, and will not be repeated here.

The apparatus 100 for detecting motion trajectories using multiple cameras provided in the above embodiment may be implemented in the form of a computer program, and the computer program may be run on a terminal device 200 as shown in FIG. 3 .

Please refer to Figure 3, which is a schematic block diagram of the structure of a terminal device 200 provided in an embodiment of the present application. The terminal device 200 includes a processor 201 and a memory 202. The processor 201 and the memory 202 are connected via a system bus 203, wherein the memory 202 may include a non-volatile storage medium and an internal memory.

The non-volatile storage medium can store a computer program. The computer program includes program instructions, and when the program instructions are executed by the processor 201, the processor 201 can execute any of the above-mentioned methods for detecting motion trajectories using multiple cameras.

The processor 201 is used to provide computing and control capabilities to support the operation of the entire terminal device 200.

The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 201, the processor 201 can execute any of the above-mentioned methods for detecting motion trajectories using multiple cameras.

Those skilled in the art will understand that the structure shown in FIG. 3 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal device 200 involved in the scheme of the present application. The specific terminal device 200 may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

It should be understood that the processor 201 may be a central processing unit (CPU), and the processor 201 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

In some embodiments, the processor 201 is used to run a computer program stored in the memory to implement the following steps:

Constructing a spatial rectangular coordinate system with the designated point of the monitoring area as the coordinate origin;

For each of the cameras, generating a pixel coordinate grid corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system;

Acquire a plurality of videos to be identified taken by a plurality of the cameras, and select a target video from the plurality of videos to be identified based on target feature information of the target object; wherein the target object appears in the target video, and the target video includes a plurality of videos;

For each of the target videos, determine the motion trajectory points of the target object in the monitoring area based on the target video and the pixel coordinate grid corresponding to the target video, and mark each of the motion trajectory points with a time tag;

Generate a target motion trajectory of the target object in the monitoring area based on each of the motion trajectory points and the time tag corresponding to each of the motion trajectory points;

The target motion trajectory is stored in a preset database.

It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device 200 described above can refer to the corresponding process of the aforementioned multi-camera motion trajectory detection method, and will not be repeated here.

An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the one or more processors implement the method for detecting motion trajectories with multiple cameras as provided in an embodiment of the present application.

The computer-readable storage medium may be an internal storage unit of the terminal device 200 in the aforementioned embodiment, such as a hard disk or memory of the terminal device 200. The computer-readable storage medium may also be an external storage device of the terminal device 200, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped with the terminal device 200.

The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims (9)

1. The method for detecting the motion trail by using multiple cameras is characterized by being used for detecting the motion trail of a target object in a monitoring area, wherein the monitoring area is provided with multiple cameras, and each camera is arranged at different positions of the monitoring area, and the method comprises the following steps:

constructing a space rectangular coordinate system by taking a designated point of the monitoring area as a coordinate origin;

generating a pixel coordinate network corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system for each camera;

acquiring a plurality of videos to be identified, which are shot by a plurality of cameras, and selecting a target video from the videos to be identified based on target characteristic information of a target object; wherein the target object appears in the target video, the target video including a plurality of;

determining a motion track point of the target object in the monitoring area according to the target videos and a pixel coordinate network corresponding to the target videos, and labeling time labels for the motion track points;

generating a target motion track of the target object in the monitoring area based on the motion track points and the time labels corresponding to the motion track points;

And storing the target motion trail to a preset database.

2. The method for detecting a motion trajectory by using multiple cameras according to claim 1, wherein the generating a pixel coordinate network corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system includes:

acquiring an image of a shooting area corresponding to the camera;

and determining a target area corresponding to the pixel in the monitoring area according to each pixel of the image, determining a coordinate point corresponding to a central point of the target area in the space rectangular coordinate system, and labeling the coordinate point on the pixel to obtain the pixel coordinate system.

3. The method for detecting a motion trajectory by using multiple cameras according to claim 1, wherein the selecting a target video from a plurality of videos to be identified based on target feature information of a target object comprises:

for each video to be identified, playing the video to be identified to acquire a plurality of objects to be matched in the video to be identified;

extracting feature information to be matched of each object to be matched corresponding to each video to be identified, respectively obtaining first similarity between each feature information to be matched and the target feature information, and selecting the maximum similarity in each first similarity;

And comparing the maximum similarity corresponding to the videos to be identified with a first preset similarity aiming at each video to be identified, and determining the video to be identified as a target video when the maximum similarity is larger than the first preset similarity.

4. The method for detecting a motion trail by using multiple cameras according to claim 2, wherein the determining motion trail points of the target object in the monitoring area based on the target video and the pixel coordinate network corresponding to the target video, and labeling each motion trail point with a time tag comprises:

carrying out framing treatment on the target video to obtain a plurality of video frames corresponding to the target video, and marking time labels on the video frames based on the corresponding time sequences of the video frames in the target video;

selecting a target video frame from a plurality of video frames; wherein the target video frame comprises at least one, and the picture of the target video frame comprises the target object;

for each target video frame, acquiring the center point position of the corresponding image contour of the target object in the target video frame, and marking the center point position on the target video frame;

And mapping the pixel coordinate network to the target video frames with the central point positions marked so as to determine target coordinate points corresponding to the pixels where the central point positions corresponding to the target video frames are located, marking time labels corresponding to the target video frames for the target coordinate points, and taking the target coordinate points marked with the time labels as motion track points corresponding to the target video frames.

5. The method for detecting a motion trail by using multiple cameras according to claim 4, wherein the generating a target motion trail of the target object in the monitoring area based on each motion trail point and a time tag corresponding to each motion trail point comprises:

labeling each motion trail point in the space rectangular coordinate system;

sequentially connecting the motion track points based on the time labels corresponding to the motion track points to obtain an initial motion track of the target object;

smoothing the initial motion trail to obtain an intermediate motion trail;

and marking a motion starting point and a motion end point of the target object in the monitoring area on the middle motion track based on the time labels corresponding to the motion track points to obtain the target motion track.

6. The method for detecting a motion trajectory by using multiple cameras according to claim 1, wherein the storing the motion trajectory of the target in a preset database includes:

acquiring an area identifier of the monitoring area and camera identifiers of the cameras;

sequentially arranging the camera identifications based on the positions of the cameras corresponding to the camera identifications in the monitoring area to obtain a camera identification sequence;

constructing a blank set aiming at each region identification character of the region identification;

for each blank set, respectively obtaining second similarity between an area identification character corresponding to the blank set and each camera identification character of the camera identification sequence, comparing each second similarity with a second preset similarity, and taking a camera identification character corresponding to the second similarity as a target camera identification character corresponding to the blank set when the second similarity is larger than the second preset similarity;

for each blank set, based on the ordering of each target camera identification character corresponding to the blank set in the camera identification sequence, filling each target camera identification character corresponding to each blank set into the blank set in sequence to obtain a set to be selected;

Determining a target set in all the candidate sets; the target set corresponds to the most target camera identification characters;

and encrypting the target motion trail based on the target set, and storing the encrypted target motion trail into a preset database.

7. The utility model provides a device of many cameras detection motion trail, its characterized in that is used for detecting the motion trail of the target object in the monitored area, the monitored area is equipped with a plurality of cameras, and each the camera is located the different positions of monitored area, the device includes:

the construction module is used for constructing a space rectangular coordinate system by taking a specified point of the monitoring area as a coordinate origin;

the first generation module is used for generating a pixel coordinate network corresponding to the shooting area of the camera based on the shooting area of the camera and the rectangular coordinate system for each camera;

the selection module is used for acquiring a plurality of videos to be identified, which are shot by a plurality of cameras, and selecting a target video from the videos to be identified based on target characteristic information of a target object; wherein the target object appears in the target video, the target video including a plurality of;

The determining module is used for determining the motion track points of the target object in the monitoring area according to the target videos and the pixel coordinate networks corresponding to the target videos, and labeling time labels for the motion track points;

the second generation module is used for generating a target motion track of the target object in the monitoring area based on each motion track point and the time label corresponding to each motion track point;

and the storage module is used for storing the target motion trail to a preset database.

8. A terminal device comprising a processor, a memory and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the method of detecting a motion profile for a multi-camera as claimed in any one of claims 1 to 6.

9. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and wherein the computer program, when executed by a processor, implements the method for detecting a motion profile by using multiple cameras according to any one of claims 1 to 6.