Intelligent tracking and positioning method and system

By receiving real-time video of the law enforcement recorder and using computer vision to identify the characteristics of the target object, combining the position information of the preset monitoring device and the movement direction of the target object, optimizing the tracking route, the inaccurate tracking and low efficiency in the prior art is solved. The problem of this achieves more efficient target object tracking.

CN118982645APending Publication Date: 2024-11-19SHENZHEN DACHENWEI TECH GRP CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411101362.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing tracking and positioning methods rely on human resources and traditional communication technologies, resulting in inaccurate and inefficient positioning of target objects, especially in crowded environments that are difficult to track in real time.

Method used

By receiving real-time videos sent by law enforcement recorders, identifying the characteristics of the target object (wear, height, gender) and determining the location information of the preset monitoring device, using computer vision and object detection algorithms to quickly locate the target object, predict its movement direction and potential Location, optimize tracking routes.

Benefits of technology

It improves the accuracy and efficiency of tracking and positioning of target objects, reduces the time and errors of human searches, and enhances the tracking success rate and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982645A_ABST
    Figure CN118982645A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent tracking and positioning method and system, and the method comprises the steps: receiving a real-time video sent by a law enforcement recorder, and determining a target object in the real-time video; the target object is recognized, a target feature group is obtained, and the target feature group comprises the wearing, the height and the gender of the target object; determining all preset monitoring devices in a preset range of the law enforcement recorder, and receiving monitoring videos sent by all the preset monitoring devices; identifying all the monitoring videos, and determining a first monitoring video with a target feature group in all the monitoring videos; determining a video tag of the first monitoring video, and obtaining a first preset monitoring device corresponding to the first monitoring video; and the first position information of the first preset monitoring equipment is determined, and the first position information is sent to the mobile terminal corresponding to the law enforcement recorder, so that the accuracy and efficiency of tracking and positioning the target object are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of position positioning, and in particular to an intelligent tracking and positioning method and system. Background Art

[0002] In the tracking work, the positioning and tracking of the target object mainly rely on manpower and traditional communication technology. Generally speaking, the staff needs to track the target object by themselves, and report the appearance characteristics, location and displacement direction of the target object through the walkie-talkie, and then the control center will track the target object.

[0003] This tracking method relies on the staff's ability to track the target object and needs to be able to track the target object in real time. However, in actual situations, it is often difficult for the staff to track the target object. In this case, the control center needs to screen the target object from a large number of surveillance videos. This process is time-consuming and the target object may have disappeared without a trace, which brings great difficulty and challenges to tracking and positioning, and reduces the accuracy and efficiency of tracking the target object. Summary of the invention

[0004] The present application provides an intelligent tracking and positioning method and system for improving the accuracy and efficiency of tracking and positioning of a target object.

[0005] In the first aspect, the present application provides an intelligent tracking and positioning method, which receives real-time video sent by a law enforcement recorder and determines the target object in the real-time video; Identify the target object and obtain a target feature group, which includes the target object's clothing, height and gender; Determine all preset monitoring devices within the preset range of the law enforcement recorder and receive monitoring videos sent by all preset monitoring devices; Identify all surveillance videos and determine the first surveillance video that contains the target feature group among all surveillance videos; Determine a video tag of the first surveillance video, and obtain a first preset surveillance device corresponding to the first surveillance video; Determine the first location information of the first preset monitoring device, and send the first location information to the mobile terminal corresponding to the law enforcement recorder.

[0006] By adopting the above technical solution, the real-time video sent by the law enforcement recorder is received, the target object in the video is determined, and the characteristics of the target object, including clothing, height and gender, are identified, all preset monitoring devices within the preset range of the law enforcement recorder are determined, the monitoring videos sent by these monitoring devices are received, and the first monitoring video with the target feature group is identified in the monitoring video. Through the video tag of the first monitoring video, the corresponding first preset monitoring device and its location information can be determined, and the location information is sent to the mobile terminal corresponding to the law enforcement recorder. In this way, the staff can quickly and accurately track and locate the target object based on the location information received by the mobile terminal, greatly improving the accuracy and efficiency of tracking and locating the target object.

[0007] In conjunction with some embodiments of the first aspect, in some embodiments, receiving a real-time video sent by a law enforcement recorder and determining a target object in the real-time video specifically includes: Receive real-time video from law enforcement cameras; Identify target objects in real-time video whose moving speed is greater than a preset threshold; Use computer vision technology to determine the target object in the target object.

[0008] By adopting the above technical solution, target objects whose moving speed is greater than a preset value in real-time video are identified, and then the target object is determined from these target objects using computer vision technology. In this way, the target object to be tracked can be found from the real-time video quickly and accurately, avoiding unnecessary processing of non-target objects that are stationary or moving slowly, and improving the efficiency and accuracy of target object identification.

[0009] In conjunction with some embodiments of the first aspect, in some embodiments, obtaining the target feature group specifically includes: Use the target detection algorithm to identify the target object and obtain the bounding box of the target object; Locate the target area where the target object is located according to the bounding box; Perform feature extraction in the target area to obtain the target object's clothing; Use the posture estimation model to identify the target area and obtain the height of the target object; Use face recognition technology to identify the target area and obtain the gender of the target object; Combine clothing, height, and gender to get the target feature group.

[0010] By adopting the above technical solution, the target detection algorithm is used to identify the bounding box of the target object, and the area where the target object is located is located according to the bounding box. Then, feature extraction is performed in the target area to obtain the clothing features of the target object; the posture estimation model is used to identify the target area to obtain the height features of the target object; and face recognition technology is used to identify the target to obtain the gender features of the target object. Clothing, height and gender are combined to form a complete target feature group. In this way, the characteristics of the target object can be fully characterized from multiple angles, and a target feature group that is easy to identify and match is generated, which provides a reliable reference for the subsequent search for the target in the surveillance video and improves the accuracy and reliability of tracking and positioning.

[0011] In combination with some embodiments of the first aspect, in some embodiments, after determining the first location information of the first preset monitoring device and sending the first location information to the mobile terminal corresponding to the law enforcement recorder, the method further includes: Determining a moving direction of the target object according to the first surveillance video; Determine a collision boundary according to the moving direction, where the collision boundary is a boundary where the intersection of the moving direction and the boundary of the first monitoring video is located; A plurality of second preset monitoring devices are determined according to the collision boundary.

[0012] By adopting the above technical solution, the moving direction of the target object is determined according to the first monitoring video, and the collision boundary where the target object may intersect with the monitoring range boundary is determined according to the moving direction, and then several second preset monitoring devices that the target object may reach are determined according to the collision boundary. In this way, through the historical movement information of the target object, its possible future location is predicted, and the corresponding monitoring device is searched, so that preparations can be made before the target object moves out of the current monitoring range, and the subsequent location information of the target object can be obtained in advance. At the same time, by analyzing the relationship between the moving direction and the monitoring range, the number of potential second monitoring devices can be reduced, and the tracking efficiency can be improved.

[0013] In combination with some embodiments of the first aspect, in some embodiments, after determining a plurality of second preset monitoring devices according to the collision boundary, the method further includes: Acquire a plurality of monitoring videos of a plurality of second preset monitoring devices; Determine a second surveillance video in which a target object exists among the plurality of surveillance videos; Determine a video tag of a second surveillance video, and obtain a second preset surveillance device corresponding to the second surveillance video; Determine the second location information of the second preset monitoring device, and send the second location information to the mobile terminal corresponding to the law enforcement recorder.

[0014] By adopting the above technical solution, after determining some second preset monitoring devices that may have captured the target object, the monitoring videos of these monitoring devices are obtained, and the second monitoring video in which the target object actually exists is identified. Through the video tag of the second monitoring video, the corresponding second preset monitoring device and its location information can be determined, and the location information can be sent to the mobile terminal corresponding to the law enforcement recorder. In this way, the staff can continue to track the movement trajectory of the target object according to the continuously updated location information of the target object until the tracking is successful, thereby improving the reliability and success rate of tracking and positioning.

[0015] In combination with some embodiments of the first aspect, in some embodiments, after determining the second location information of the second preset monitoring device and sending the second location information to the mobile terminal corresponding to the law enforcement recorder, the method further includes: Determining a number of predicted tracking routes based on the first location information and the second location information; Send several predicted tracking routes to the mobile terminal.

[0016] By adopting the above technical solution, based on the first location information and the second location information, some possible predicted tracking routes are determined and sent to the mobile terminal. The staff can refer to the predicted routes, select the path that is most likely to track the target object in advance, and arrange the tracking action reasonably, instead of adjusting the direction at any time according to the location information. At the same time, the predicted routes can also help the staff judge the movement trend and intention of the target object, such as whether there is an intention to escape or hide, so as to take corresponding countermeasures.

[0017] In conjunction with some embodiments of the first aspect, in some embodiments, determining a plurality of predicted tracking routes according to the first location information and the second location information specifically includes: Obtaining a map corresponding to the first location information and the second location information; Marking the first location information and the second location information on the map to obtain a first punctuation point and a second punctuation point; Connect the first punctuation point and the second punctuation point to obtain the moved route; A plurality of movable routes in a map are determined, and routes among the plurality of movable routes that are connected to the moved route are determined as a plurality of predicted tracking routes.

[0018] By adopting the above technical solution, a map of the first and second positions of the target object is obtained, and the two positions are marked on the map. Then, the two positions are connected to obtain the route that the target object has moved. On this basis, all possible moving routes in the map are considered, and those routes connected to the moved routes are determined as predicted tracking routes. In this way, the known movement information of the target object can be fully utilized, the range of the predicted route can be reasonably narrowed, and the most likely tracking plan can be obtained. At the same time, by comparing the map to predict the route, the influence of actual influencing factors such as road influence can be considered, so that the predicted route can give a variety of possible predicted routes compared with simply extending the moved route.

[0019] In a second aspect, an embodiment of the present application provides a system, the system comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a system, causes the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product runs on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application provides an intelligent tracking and positioning method, which receives real-time video sent by a law enforcement recorder, determines the target object in the video, and identifies the characteristics of the target object, including clothing, height and gender, determines all preset monitoring devices within the preset range of the law enforcement recorder, receives monitoring videos sent by these monitoring devices, and identifies the first monitoring video with the target feature group in the monitoring video. Through the video tag of the first monitoring video, the corresponding first preset monitoring device and its location information can be determined, and the location information is sent to the mobile terminal corresponding to the law enforcement recorder. In this way, the staff can quickly and accurately track and locate the target object based on the location information received by the mobile terminal, greatly improving the accuracy and efficiency of tracking and locating the target object.

[0023] 2. The present application provides an intelligent tracking and positioning method, which uses a target detection algorithm to identify the bounding box of a target object, and locates the area where the target object is located based on the bounding box. Then, feature extraction is performed in the target area to obtain the clothing features of the target object; the target area is identified using a posture estimation model to obtain the height features of the target object; and the target is identified using face recognition technology to obtain the gender features of the target object. Clothing, height, and gender are combined to form a complete target feature group. In this way, the characteristics of the target object can be comprehensively characterized from multiple angles, and a target feature group that is easy to identify and match can be generated, which provides a reliable reference for the subsequent search for the target in the surveillance video and improves the accuracy and reliability of tracking and positioning.

[0024] 3. The present application provides an intelligent tracking and positioning method, which determines the moving direction of the target object based on the first monitoring video, and determines the collision boundary where the target object may intersect with the boundary of the monitoring range based on the moving direction, and then determines several second preset monitoring devices that the target object may reach based on the collision boundary. In this way, by using the historical movement information of the target object, its possible future location is predicted, and the corresponding monitoring device is searched. It is possible to prepare before the target object moves out of the current monitoring range and obtain the subsequent location information of the target object in advance. At the same time, by analyzing the relationship between the moving direction and the monitoring range, the number of potential second monitoring devices can be reduced and the tracking efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of an intelligent tracking and positioning method in an embodiment of the present application.

[0026] Figure 2 It is another flow chart of an intelligent tracking and positioning method in an embodiment of the present application.

[0027] Figure 3 It is a schematic diagram of the physical device structure of an intelligent tracking and positioning system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following describes an application scenario of this application: In a busy commercial district, the staff found a target who needed to be tracked and located. The target was very cautious on the crowded streets. After spotting the staff, he quickly fled the scene and disappeared in the bustling crowd. The staff immediately tracked him, but due to the large number of people at the scene, he soon lost the target. The staff then reported the relevant information of the target to the control center. Based on the information provided by the staff, the control center searched for the target among multiple cameras at the scene to track and locate the target.

[0031] As the tracking and positioning operation continued, the location of the target object became increasingly difficult to determine. Despite the investment of a large amount of manpower and material resources and attempts to expand the search range, it was difficult to grasp the movement of the target object in real time due to the lack of effective technical means. The target object seemed to be very familiar with the surrounding terrain and was always able to cleverly avoid tracking. As time went on, the whereabouts of the target object became more and more elusive, and the staff faced the risk of failure in the tracking operation.

[0032] In order to solve the above technical problems, the present application provides an intelligent tracking and positioning method and system for improving the accuracy and efficiency of tracking and positioning of target objects.

[0033] Combine the following Figure 1 , an intelligent tracking and positioning method in an embodiment of the present application is described: See also Figure 1 , which is a flow chart of an intelligent tracking and positioning method in an embodiment of the present application.

[0034] S101, receiving the real-time video sent by the law enforcement recorder, and determining the target object in the real-time video; The system receives the real-time video sent by the law enforcement recorder and determines the target object in the real-time video. Specifically: receiving the real-time video sent by the law enforcement recorder; Identify target objects in real-time video whose moving speed is greater than a preset threshold; Use computer vision technology to determine the target object in the target object.

[0035] The system uses computer vision technology to identify and track all target objects in the video. By setting the moving speed threshold, the system can quickly filter out target objects with faster moving speeds and exclude stationary or slow-moving passers-by. For example, if the speed threshold set by the system is 1.5 meters per second, all target objects moving faster than 1.5 meters per second will be marked. Among them, target objects include non-humans and humans.

[0036] Next, the system further analyzes these fast-moving target objects and uses the target detection algorithm to determine which object is most likely to be the target object that the staff wants to track. The target object is a human, and this step can exclude non-human target objects. Suppose the system finds through analysis that there is a male wearing a black jacket, about 1.75 meters tall, moving at a speed of 2 meters per second, which is consistent with the target object characteristics provided by the staff, and the system will mark him as a tracking target.

[0037] S102, identifying the target object and obtaining a target feature group; After determining the target object in the real-time video, the system identifies the target object and obtains a target feature group of the target object, which includes the target object's clothing, height and gender. Specifically: Use the target detection algorithm to identify the target object and obtain the bounding box of the target object; Locate the target area where the target object is located according to the bounding box; Perform feature extraction in the target area to obtain the target object's clothing; Use the posture estimation model to identify the target area and obtain the height of the target object; Use face recognition technology to identify the target area and obtain the gender of the target object; Combine clothing, height, and gender to get the target feature group.

[0038] After determining the target object in the real-time video, the system begins to perform more detailed recognition and feature extraction of the target object. First, the system uses an object detection algorithm, such as YOLO (You Only Look Once) or Faster R-CNN, to detect the target object and obtain its bounding box in the video. The bounding box accurately outlines the location and range of the target object.

[0039] Then, the system locates the specific area where the target object is located based on the bounding box information, namely the target area. Next, the system extracts features in the target area. By analyzing the pixel information in the target area, the system can obtain the target object's clothing features, such as the color, texture, and style of the clothes. Suppose the system detects that the target object is wearing a black jacket with obvious white marks on the jacket, this information will be extracted as one of the target features.

[0040] Next, the system uses a pose estimation model, such as OpenPose or AlphaPose, to analyze the target area and estimate the height of the target object. By detecting the key body nodes of the target object, such as the head, shoulders, waist, etc., and combining the camera parameters and distance information, the system can calculate the height of the target object more accurately. Assume that the system estimates that the height of the target object is about 1.75 meters.

[0041] Finally, the system will also use facial recognition technology, such as FaceNet or DeepFace, to analyze the faces in the target area to determine the gender of the target object. By detecting the detailed features of the face and comparing it with the pre-trained male and female face models, the system can determine whether the target object is male or female. Assume that the system recognizes that the target object is male.

[0042] Combining the above information, the system obtains a complete set of target features, including the target object's clothing (black jacket, white logo), height (1.75 meters) and gender (male). This feature information will be used to identify and track the same target object in other surveillance videos.

[0043] S103, determining all preset monitoring devices within the preset range of the law enforcement recorder, and receiving monitoring videos sent by all preset monitoring devices; After obtaining the characteristic information of the target object, the system begins to expand the search range and use nearby monitoring equipment to assist in tracking the target object. The system first determines the preset range of the law enforcement recorder, that is, the area within a certain radius of the location of the law enforcement recorder. This preset range can be set according to actual conditions, such as 200 meters or 500 meters, etc., which is not limited here.

[0044] The system maintains a database of preset monitoring devices, recording the location, coverage, shooting angle, etc. of each monitoring device. By querying the database, the system can quickly find all monitoring devices within the preset range of the law enforcement recorder. Suppose within the 200-meter range of the law enforcement recorder, the system finds 5 available monitoring devices, numbered C1, C2, C3, C4, and C5.

[0045] After determining the monitoring devices within the preset range, the system will actively establish connections with these devices and receive the monitoring videos they transmit in real time. Each monitoring device continuously captures the situation in its coverage area and sends the video data to the system in real time. The system assigns a unique identifier to each monitoring device to distinguish the video data of different devices.

[0046] For example, the video data transmitted by the C1 monitoring device may be identified as "C1_Video", the video data of the C2 monitoring device may be identified as "C2_Video", and so on. In this way, the system can manage and process the video data from different monitoring devices in an orderly manner, preparing for the subsequent target object recognition and tracking.

[0047] S104, identifying all surveillance videos, and determining the first surveillance video that has the target feature group among all surveillance videos; After receiving the real-time videos from all monitoring devices within the preset range, the system begins to analyze and identify these videos one by one to determine the location of the target object. The system uses a method similar to step S102 to detect and extract features of people in each monitoring video, obtain their clothing, height, gender and other information, and compare them with the target feature group.

[0048] Assume that when analyzing the video of the C1 surveillance device, the system finds that there are multiple people in the video, but their features do not completely match the target feature set. For example, there is a man who is about 1.8 meters tall and wears a black jacket, but there is no white logo on the jacket; there is also a man who is about 1.7 meters tall and wears a gray coat, and his features do not match the target object. Therefore, the system determines that the target object does not appear in the C1 surveillance video.

[0049] The system continued to analyze the videos from the C2, C3, and C4 surveillance devices, and still did not find a person who fully matched the target feature group. However, when analyzing the video from the C5 surveillance device, the system found a male about 1.75 meters tall in the video, wearing a black jacket with a clear white mark on it. These features were highly consistent with the target feature group.

[0050] Therefore, the system determines that the C5 monitoring device has captured the target object, and the C5 monitoring video is the first monitoring video with the target feature group. This means that the target object is likely to be within the coverage of the C5 monitoring device, providing important clues for subsequent tracking work.

[0051] S105: Determine a video tag of the first surveillance video, and obtain a first preset surveillance device corresponding to the first surveillance video; After determining that the C5 surveillance video contains the target object, the system needs to further determine the specific surveillance device that shot the video. Since the system assigns a unique identifier to each video when receiving surveillance videos, it can quickly find the corresponding surveillance device by querying the video tag.

[0052] For example, the identifier of the C5 surveillance video is "C5_Video". By querying the correspondence between the identifier and the surveillance device, the system obtains that the video was shot by the C5 surveillance device. In this way, the system determines the first preset surveillance device (C5 surveillance device) corresponding to the first surveillance video (C5 surveillance video).

[0053] Through the mapping relationship between video tags and surveillance devices, the system can easily manage and track videos shot by different surveillance devices and associate video content with specific geographic locations.

[0054] S106. Determine the first location information of the first preset monitoring device, and send the first location information to the mobile terminal corresponding to the law enforcement recorder.

[0055] After determining the first preset monitoring device (C5 monitoring device), the system immediately queries the location information of the monitoring device. In the monitoring device database, each device has a detailed location record, including longitude, latitude, street, etc.

[0056] Assume that the C5 monitoring device is located in the central square of the commercial district, its longitude and latitude coordinates are (31.2345, 121.5678), and the street it is located on is "Central Avenue". The system obtains this location information from the database and generates a standardized location description, such as "intersection of Central Avenue and Central Square, northeast corner".

[0057] Next, the system sends this location description as the first location information to the mobile terminal associated with the law enforcement recorder. The mobile terminal can be a mobile phone or tablet computer carried by the staff to receive and display the real-time location of the target object.

[0058] When the mobile terminal receives the first location information, it will immediately mark the location on the map and remind the staff in a conspicuous way. For example, the mobile terminal may display a flashing red mark on the map with a location description: "The target object may be located at the intersection of Central Avenue and Central Plaza, northeast corner."

[0059] With this location information, the staff can quickly adjust the tracking strategy and search and intercept the possible location of the target object. At the same time, the system will continue to analyze the video of other monitoring devices. Once the new location of the target object is found, the location information will be updated immediately and sent to the mobile terminal to ensure that the staff can keep up with the movement of the target object and improve the success rate of tracking.

[0060] The above embodiments have the following beneficial effects: Receive the real-time video sent by the law enforcement recorder, determine the target object in the video, and identify the characteristics of the target object, including clothing, height and gender, determine all preset monitoring devices within the preset range of the law enforcement recorder, receive the monitoring video sent by these monitoring devices, and identify the first monitoring video with the target feature group in the monitoring video. Through the video tag of the first monitoring video, the corresponding first preset monitoring device and its location information can be determined, and the location information is sent to the mobile terminal corresponding to the law enforcement recorder. In this way, the staff can quickly and accurately track and locate the target object based on the location information received by the mobile terminal, greatly improving the accuracy and efficiency of tracking and locating the target object.

[0061] Identify the target objects in the real-time video whose moving speed is greater than the preset value, and then use computer vision technology to determine the target object from these target objects. This can quickly and accurately find the target object to be tracked from the real-time video, avoid unnecessary processing of non-target objects that are stationary or moving slowly, and improve the efficiency and accuracy of target object recognition.

[0062] Use the target detection algorithm to identify the bounding box of the target object, and locate the area where the target object is located based on the bounding box. Then, perform feature extraction in the target area to obtain the clothing features of the target object; use the posture estimation model to identify the target area to obtain the height features of the target object; use face recognition technology to perform target recognition to obtain the gender features of the target object. Combine clothing, height and gender to form a complete target feature group. In this way, the characteristics of the target object can be fully characterized from multiple angles, and a target feature group that is easy to identify and match is generated, which provides a reliable reference for the subsequent search for the target in the surveillance video and improves the accuracy and reliability of tracking and positioning.

[0063] After determining the first location information, the target object is not stationary, but generally moves continuously, which will inevitably bring great challenges to tracking and positioning. Figure 2 , describes how to locate and track a moving target object: Please participate Figure 2 , is another flow chart of an intelligent tracking and positioning method in an embodiment of the present application.

[0064] S201, determining a moving direction of a target object according to a first monitoring video; After determining the initial position of the target object (i.e., the first position information), the system continues to analyze the first surveillance video (C5 surveillance video) to determine the moving direction of the target object. By tracking and analyzing the target object in the video, the system can calculate the displacement and motion trajectory of the target object between consecutive frames.

[0065] For example, the system can use optical flow or target tracking algorithms (such as Kalman filter, particle filter, etc.) to estimate the motion parameters of the target object. By comparing the position changes of the target object in different frames, the system can obtain an estimate of its moving direction and speed.

[0066] Assume that in the C5 surveillance video, the target object is initially located in the lower left corner of the screen and then gradually moves to the upper right corner of the screen. By analyzing the position change of the target object, the system determines that its moving direction is northeast (i.e., moving to the upper right). At the same time, the system can also estimate the moving speed of the target object, for example, 2 meters per second.

[0067] S202, determining a collision boundary according to the moving direction; After determining the moving direction of the target object, the system needs to predict the boundary position that the target object may reach, that is, the collision boundary. The collision boundary refers to the position where the target object may intersect with the edge of the monitoring area in the current moving direction.

[0068] In order to determine the collision boundary, the system first needs to obtain the coverage and shooting angle of the first monitoring device (C5 monitoring device). By querying the monitoring device database, the system can obtain the position, orientation, field of view and other parameters of the C5 monitoring device.

[0069] Assume that the C5 monitoring device has a field of view of 90 degrees, faces northeast, and covers a sector area. Based on the moving direction of the target object (northeast) and the coverage of the C5 monitoring device, the system can calculate the intersection of the target object and the edge of the coverage area, that is, the collision boundary.

[0070] For example, the system can use geometric calculations or raycasting to determine the intersection point. If the target object maintains its current moving direction and moves at a speed of 2 meters per second, the system can estimate that the target object will reach the collision boundary in approximately 10 seconds.

[0071] The determination of the collision boundary provides the system with a predicted time and location so that the next monitoring device can be selected in advance to ensure that the target object can be tracked in time after moving out of the current monitoring range.

[0072] S203, determining a number of second preset monitoring devices according to the collision boundary; Based on the collision boundary determined in the previous step, the system starts to search for other monitoring devices in the nearby area that may capture the target object, namely the second preset monitoring devices. These monitoring devices should be located in the moving direction of the target object, and their coverage should include or be close to the collision boundary.

[0073] The system queries the monitoring device database again to search for monitoring devices that are close to the collision boundary and facing the same direction as the target object.

[0074] Assume that there are three monitoring devices that meet the conditions near the collision boundary, namely C6, C7 and C8. They are located in the northeast, north and northwest directions of the collision boundary, respectively, and the distance from the collision boundary is between 50 meters and 100 meters. The orientation and field of view of these three monitoring devices can cover the collision boundary and its vicinity, so the system determines them as the second preset monitoring devices.

[0075] After selecting the second preset monitoring devices, the system will establish connections with these devices and prepare to receive their real-time video streams so as to promptly detect and track the target object when it moves into its coverage area.

[0076] S204, obtaining a plurality of monitoring videos of a plurality of second preset monitoring devices; After the second preset monitoring devices (C6, C7, and C8) are determined, the system begins to obtain real-time monitoring video from these devices. Similar to before, the system assigns a unique identifier to each monitoring device and establishes a data connection with the device.

[0077] Assume that the video ID of the C6 monitoring device is "C6_Video", the video ID of the C7 monitoring device is "C7_Video", and the video ID of the C8 monitoring device is "C8_Video". The system will receive and process these three video streams at the same time and store them in memory or buffer for subsequent target object recognition and tracking.

[0078] Since these monitoring devices are located in areas where the target object may appear, their video streams are likely to capture the target object. The system will analyze these video streams in real time to find the target object as soon as possible.

[0079] S205, determining that a second surveillance video of the target object exists in the plurality of surveillance videos; After receiving the video stream from the second preset monitoring device, the system begins to analyze each video frame by frame to determine whether the target object appears in it. The system uses similar object detection and feature matching algorithms as before to search for people in the video that match the target feature set.

[0080] Assume that when analyzing the C6 surveillance video, the system did not find a person who completely matched the target feature group. However, when analyzing the C7 surveillance video, the system detected a person with highly similar features to the target object. His clothing, height, and gender are consistent with the target feature group.

[0081] Further analysis found that the time when this person appeared in the C7 surveillance video coincided with the time when the system predicted that the target object would reach the collision boundary, and his movement direction and speed were also close to the previously estimated movement parameters of the target object. Therefore, the system can determine that this person is the target object being tracked.

[0082] Therefore, the system marks the C7 surveillance video as the second surveillance video, indicating that the target object has appeared in the video.

[0083] S206, determining a video tag of the second surveillance video, and obtaining a second preset surveillance device corresponding to the second surveillance video; S207: Determine the second location information of the second preset monitoring device, and send the second location information to the mobile terminal corresponding to the law enforcement recorder.

[0084] The method used in steps S206-S207 is similar to that used in steps S105-S106 and will not be described again here.

[0085] The above embodiments have the following beneficial effects: Determine the moving direction of the target object based on the first monitoring video, and determine the collision boundary where the target object may intersect with the monitoring range boundary based on the moving direction, and then determine several second preset monitoring devices that the target object may reach based on the collision boundary. In this way, by using the historical movement information of the target object, predicting its possible future location, and finding the corresponding monitoring device, you can prepare before the target object moves out of the current monitoring range and obtain the subsequent location information of the target object in advance. At the same time, by analyzing the relationship between the moving direction and the monitoring range, you can reduce the number of potential second monitoring devices and improve tracking efficiency.

[0086] After determining some second preset monitoring devices that may have captured the target object, the monitoring videos of these monitoring devices are obtained, and the second monitoring video where the target object actually exists is identified. Through the video tag of the second monitoring video, the corresponding second preset monitoring device and its location information can be determined, and the location information can be sent to the mobile terminal corresponding to the law enforcement recorder. In this way, the staff can continue to track the movement trajectory of the target object according to the continuously updated location information of the target object until the tracking is successful, which improves the reliability and success rate of tracking and positioning.

[0087] After determining the second movement information of the target object, it is necessary to predict the moving direction of the target object in order to track it more quickly. Then: Obtaining a map corresponding to the first location information and the second location information; Marking the first location information and the second location information on the map to obtain a first punctuation point and a second punctuation point; Connect the first punctuation point and the second punctuation point to obtain the moved route; Determine a plurality of movable routes in the map, and determine routes among the plurality of movable routes that are connected to the moved route as a plurality of predicted tracking routes; Send several predicted tracking routes to the mobile terminal.

[0088] In this way, staff can make judgments in advance based on several predicted tracking routes to improve the success rate of tracking.

[0089] The above embodiments have the following beneficial effects: Based on the first location information and the second location information, some possible predicted tracking routes are determined and sent to the mobile terminal. The staff can refer to the predicted routes and select the path that is most likely to track the target object in advance, and arrange the tracking action reasonably, instead of adjusting the direction at any time according to the location information. At the same time, the predicted routes can also help law enforcement officers determine the movement trend and intention of the target object, such as whether there is an intention to escape or hide, so as to take corresponding countermeasures.

[0090] Get the map where the first and second positions of the target object are located, and mark these two positions on the map. Then, connect the two positions to get the route that the target object has moved. On this basis, consider all possible moving routes in the map, and determine those routes that are connected to the moved routes as predicted tracking routes. In this way, we can make full use of the known movement information of the target object, reasonably narrow the scope of the predicted route, and obtain the most likely tracking plan. At the same time, by comparing the map to predict the route, we can consider the influence of actual influencing factors such as road influence, so that the predicted route can give multiple possible predicted routes compared with simply extending the moved route.

[0091] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of an intelligent tracking and positioning system provided in an embodiment of the present application.

[0092] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0093] like Figure 3As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0094] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0095] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0096] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0098] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiment; or may exist independently without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiment.

[0099] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0100] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0102] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An intelligent tracking and positioning method, characterized in that: include: Receive real-time video sent by the law enforcement recorder and determine the target object in the real-time video; Identify the target object and obtain a target feature group, wherein the target feature group includes clothing, height and gender of the target object; Determine all preset monitoring devices within the preset range of the law enforcement recorder, and receive monitoring videos sent by all preset monitoring devices; Identify all the surveillance videos, and determine the first surveillance video that contains the target feature group among all the surveillance videos; Determine a video tag of the first surveillance video, and obtain a first preset surveillance device corresponding to the first surveillance video; Determine the first location information of the first preset monitoring device, and send the first location information to the mobile terminal corresponding to the law enforcement recorder.

2. The method according to claim 1, characterized in that The receiving of the real-time video sent by the law enforcement recorder and determining the target object in the real-time video specifically includes: Receiving real-time video sent by the law enforcement recorder; Identify a target object in the real-time video whose moving speed is greater than a preset threshold; The target object in the target object is determined by using computer vision technology.

3. The method according to claim 1, characterized in that The identifying the target object and obtaining the target feature group specifically includes: Using a target detection algorithm to identify the target object and obtain a bounding box of the target object; Locating a target area where the target object is located according to the bounding box; Perform feature extraction in the target area to obtain the clothing of the target object; Using a posture estimation model to identify the target area, and obtain the height of the target object; Using face recognition technology to identify the target area and obtain the gender of the target object; The clothing, the height and the gender are combined to obtain the target feature group.

4. The method according to claim 1, characterized in that: After determining the first location information of the first preset monitoring device and sending the first location information to the mobile terminal corresponding to the law enforcement recorder, the method further includes: Determining a moving direction of the target object according to the first surveillance video; Determine a collision boundary according to the moving direction, where the collision boundary is a boundary where an intersection of the moving direction and a boundary of the first surveillance video is located; A plurality of second preset monitoring devices are determined according to the collision boundary.

5. The method according to claim 4, characterized in that After determining a plurality of second preset monitoring devices according to the collision boundary, the method further includes: Acquire a plurality of monitoring videos of the plurality of second preset monitoring devices; Determine that a second surveillance video of the target object exists in the plurality of surveillance videos; Determine a video tag of the second surveillance video, and obtain a second preset surveillance device corresponding to the second surveillance video; Determine the second location information of the second preset monitoring device, and send the second location information to the mobile terminal corresponding to the law enforcement recorder.

6. The method according to claim 5, characterized in that After determining the second location information of the second preset monitoring device and sending the second location information to the mobile terminal corresponding to the law enforcement recorder, the method further includes: determining a plurality of predicted tracking routes according to the first location information and the second location information; The plurality of predicted tracking routes are sent to the mobile terminal.

7. The method according to claim 6, characterized in that The determining of a plurality of predicted tracking routes according to the first location information and the second location information specifically includes: Obtaining maps corresponding to the first location information and the second location information; Marking the first location information and the second location information on the map to obtain a first punctuation point and a second punctuation point; Connecting the first punctuation point and the second punctuation point to obtain a moved route; A plurality of movable routes in the map are determined, and routes among the plurality of movable routes that are connected to the moved route are determined as the plurality of predicted tracking routes.

8. An intelligent tracking and positioning system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Route determination and display method and device

    CN110245268A

  • Method for tracking moving target through monitoring video

    CN110858400A

  • Pedestrian cross-lens tracking method and device

    CN111008993A

  • Target searching and tracking method, device and apparatus

    CN112507953A

  • Cross-video person location tracking method and system, and device

    WO2021196294A1