Target tracking method and device, terminal equipment and storage medium
By setting up a zigzag base station on both sides of the target perception area, multi-angle feature fusion and identity binding technology, the tracking loss caused by base station occlusion on tunnels or highways is solved, and the accuracy of target tracking is improved.
Patent Information
- Application Number
- CN202311872871.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-29
- Publication Date
- 2025-07-08
AI Technical Summary
In tunnels or highways, due to installation height limitations, it is difficult to effectively detect and track all targets in their perception area, especially when large vehicles block the trolley, resulting in lost tracking of trolleys.
Multiple base stations are arranged on both sides of the target perception area in a zigzag layout. Through multi-angle feature fusion and identity binding technology, the occlusion problem is solved and tracking accuracy is improved.
Through the base station system with zigzag layout, the tracking loss problem caused by long-term occlusion between targets is solved, and the accuracy of target tracking is improved.
Smart Images
Figure CN120282098A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of computer technology, and particularly relates to a target tracking method, device, terminal device, and storage medium. Background Art
[0002] In the field of transportation, it is usually necessary to monitor some road data, such as monitoring and tracking whether vehicles are driving illegally, etc., to relieve the duty pressure of traffic enforcement personnel. With the continuous development of base station technology, such as cameras, lidar, or millimeter-wave radars in base stations, due to their advantages of high resolution, good concealment, and strong anti-active interference ability, they are widely used in the process of road monitoring.
[0003] In the related art, roadside base stations are generally set on one side of the lane. However, there are generally installation height restrictions for roadside base stations on tunnels or highways, and it is difficult to detect and track all targets in their sensing areas well. If there is a small car beside a large truck and the two vehicles are traveling at similar speeds, it will cause the large truck to block the small car for a long time, resulting in the loss of tracking of the small car. Summary of the Invention
[0004] Embodiments of this application provide a target tracking method, device, terminal device, and storage medium, which can solve the problem of tracking loss caused by occlusion between different targets.
[0005] The first aspect of the embodiments of this application provides a target tracking method, including:
[0006] Perceive the target to be tracked in the target sensing area through multiple base stations to obtain the sensing data of the target to be tracked collected by each base station, where the multiple base stations are arranged on both sides of the target sensing area in a zigzag layout;
[0007] Bind the identity of the target to be tracked according to the sensing data of the target to be tracked collected by each base station;
[0008] Track the target to be tracked after identity binding.
[0009] Optionally, in a possible implementation manner of the first aspect, the above-mentioned perceiving the target to be tracked in the target sensing area through multiple base stations to obtain the sensing data of the target to be tracked collected by each base station includes:
[0010] Obtain the first angle feature of the target to be tracked by using the first base station, and obtain the second angle feature of the target to be tracked by using the second base station, where the first base station and the second base station are two adjacent base stations;
[0011] Combine the first angle feature and the second angle feature to determine the sensing data of the target to be tracked in the sensing areas of the first base station and the second base station.
[0012] Optionally, in another possible implementation manner of the first aspect, when the third base station and the fourth base station detect that the target to be tracked is partially occluded, where the third base station and the fourth base station are two adjacent base stations, performing identity binding on the target to be tracked according to the perception data of the target to be tracked collected by each base station includes:
[0013] Extracting a first unoccluded feature of the target to be tracked based on the perception data of the target to be tracked collected by the third base station, and extracting a second unoccluded feature of the target to be tracked based on the perception data of the target to be tracked collected by the fourth base station;
[0014] Performing identity binding on the target to be tracked within the sensing areas of the third base station and the fourth base station according to the first unoccluded feature and the second unoccluded feature.
[0015] Optionally, in another possible implementation manner of the first aspect, when the fifth base station detects the target to be tracked and the sixth base station does not detect the target to be tracked, where the fifth base station is an upstream base station adjacent to the sixth base station, performing identity binding on the target to be tracked according to the perception data of the target to be tracked collected by each base station includes:
[0016] Determining that the target to be tracked is completely occluded within the sensing area of the sixth base station;
[0017] Performing trajectory prediction on the target to be tracked within the sensing area of the sixth base station according to the perception data of the target to be tracked collected by the fifth base station to obtain a trajectory prediction result;
[0018] Performing identity binding on the target to be tracked within the sensing areas of the fifth base station and the sixth base station according to the perception data of the target to be tracked collected by the fifth base station and the trajectory prediction result.
[0019] Optionally, in another possible implementation manner of the first aspect, tracking the target to be tracked after identity binding includes:
[0020] Obtaining a detection box and a prediction box of the target to be tracked in the target frame according to the perception data of the target to be tracked collected by each base station;
[0021] Matching the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result;
[0022] When the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
[0023] Optionally, in another possible implementation manner of the first aspect, matching the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result includes:
[0024] Use the Intersection over Union (IOU) matching method to match the detection boxes and prediction boxes of the target frame, and obtain the matching results.
[0025] Optionally, in another possible implementation manner of the first aspect, the above-mentioned matching of the detection boxes and prediction boxes of the target to be tracked in the target frame to obtain the matching results includes:
[0026] Obtain the horizontal distance and vertical distance between the detection box and the prediction box;
[0027] Based on the horizontal distance and vertical distance between the detection box and the prediction box, perform distance matching on the detection box and the prediction box to obtain the matching results.
[0028] Optionally, in another possible implementation manner of the first aspect, when the matching result is a successful match, update the tracking data of the target to be tracked in the target frame to track the target to be tracked, including:
[0029] When the matching result is a successful match, obtain the categories of the detection box and the prediction box respectively;
[0030] When the categories of the detection box and the prediction box are the same, determine to execute the update of the tracking data of the target to be tracked in the target frame to track the target to be tracked;
[0031] When the categories of the detection box and the prediction box are different, determine not to execute the update of the tracking data of the target to be tracked in the target frame to track the target to be tracked.
[0032] Optionally, in another possible implementation manner of the first aspect, when the matching result is a successful match, update the tracking data of the target to be tracked in the target frame to track the target to be tracked, including:
[0033] When the matching result is a successful match, obtain the speeds corresponding to the detection box and the prediction box respectively;
[0034] When the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset first threshold, determine to execute the update of the tracking data of the target to be tracked in the target frame to track the target to be tracked;
[0035] When the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset speed threshold, determine not to execute the update of the tracking data of the target to be tracked in the target frame to track the target to be tracked.
[0036] Optionally, in another possible implementation manner of the first aspect, when the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked includes:
[0037] When the matching result is a successful match, respectively obtain the speeds corresponding to the detection box and the prediction box;
[0038] When the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset second threshold, determine to execute updating the tracking data of the target to be tracked in the target frame to track the target to be tracked;
[0039] When the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset second threshold, determine not to execute updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
[0040] A second aspect of the embodiments of the present application provides a target tracking device, including:
[0041] A data acquisition module, configured to sense a target to be tracked in a target sensing area through multiple base stations, and obtain sensing data of the target to be tracked collected by each base station, where the multiple base stations are arranged on both sides of the target sensing area in a zigzag layout;
[0042] An identity binding module, configured to perform identity binding on the target to be tracked according to the sensing data of the target to be tracked collected by each base station;
[0043] A target tracking module, configured to track the target to be tracked after identity binding.
[0044] A third aspect of the embodiments of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the target tracking method of the first aspect when executing the computer program.
[0045] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program implements the target tracking method of the first aspect when executed by a processor.
[0046] A fifth aspect of the embodiments of the present application provides a computer program product, which causes a terminal device to execute the target tracking method of the first aspect when the computer program product runs on the terminal device.
[0047] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: The embodiments of the present application disclose a target tracking method, device, terminal device, and storage medium. Among them, the method first senses a target to be tracked within a target sensing area through multiple base stations to obtain sensing data of the target to be tracked collected by each base station. Among them, the multiple base stations are arranged in a zigzag layout on both sides of the target sensing area; then, according to the sensing data of the target to be tracked collected by each base station, identity binding is performed on the target to be tracked; finally, the target to be tracked after identity binding is tracked. Thus, by arranging the base stations in a zigzag layout, the occlusion problem that may be caused by the long-term side-by-side movement of targets is solved, and the accuracy of target tracking is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0049] Figure 1 is a flowchart of a target tracking method provided by an embodiment of the present application;
[0050] Figure 2 is a schematic structural diagram of a target tracking device provided by an embodiment of the present application;
[0051] Figure 3 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0052] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.
[0053] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.
[0054] It should also be understood that the term "and / or" as used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0055] As used in the specification and appended claims of the present application, the term "if" may be construed as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.
[0056] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0057] Reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.
[0058] It should be understood that the magnitude of the sequence numbers of the steps in this embodiment does not mean the sequence of execution. The execution sequence of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
[0059] In the related art, roadside base stations are generally installed on one side of a lane. However, there are generally installation height restrictions for roadside base stations in tunnels or on highways, and it is difficult to detect and track all targets in their sensing areas well. If there is a small vehicle beside a large vehicle and the two vehicles are traveling at similar speeds, it will cause the large vehicle to block the small vehicle for a long time, resulting in the loss of tracking of the small vehicle.
[0060] In view of this, the embodiments of the present application provide a target tracking method, device, terminal device, and storage medium. First, multiple base stations are used to sense a target to be tracked within a target sensing area, and sensing data of the target to be tracked collected by each base station is obtained. Among them, the multiple base stations are arranged in a zigzag layout on both sides of the target sensing area; then, based on the sensing data of the target to be tracked collected by each base station, identity binding is performed on the target to be tracked; finally, the target to be tracked after identity binding is tracked. Thus, by arranging the base stations in a zigzag layout, the occlusion problem that may be caused by the long-term side-by-side movement of targets is solved, and the accuracy of target tracking is improved.
[0061] To illustrate the technical solution of the present application, specific embodiments will be used for illustration below.
[0062] Refer to Figure 1 , which shows a schematic flowchart of a target tracking method provided by an embodiment of the present application.
[0063] As Figure 1 shown, the target tracking method may include the following steps:
[0064] Step 101, sense a target to be tracked within a target sensing area through multiple base stations, and obtain sensing data of the target to be tracked collected by each base station.
[0065] Among them, the multiple base stations are arranged in a zigzag layout on both sides of the target sensing area. The zigzag layout can provide a wider coverage range and capture more comprehensive information about the target.
[0066] In the embodiments of the present application, since the base stations are arranged in a zigzag layout, there must be a difference in the detection angles of two adjacent base stations for the same target. Therefore, multi-angle feature fusion can be performed on two adjacent base stations. Specifically, features of the target from different angles can be collected. For example, length, type, speed, etc., and these features are fused at the data level, and finally algorithms are used to integrate information from different angles to enhance the accuracy of target recognition.
[0067] That is, as a possible implementation manner of the embodiments of the present application, the above step 101 may include: obtaining a first angle feature of the target to be tracked by using a first base station, and obtaining a second angle feature of the target to be tracked by using a second base station, where the first base station and the second base station are two adjacent base stations; combining the first angle feature and the second angle feature to determine the sensing data of the target to be tracked within the sensing areas of the first base station and the second base station.
[0068] Step 102, perform identity binding on the target to be tracked according to the sensing data of the target to be tracked collected by each base station.
[0069] It should be noted that each base station includes a camera. Since there are usually more than one target in the target perception area, it is necessary to bind the identity of each target. That is to say, after capturing the features of a single target in the cameras of two adjacent base stations with a zigzag layout, template matching is performed, and combined with the target to be tracked determined by the zigzag layout, accurate identity binding of the target to be tracked can be carried out.
[0070] As an example, the time and space information of the target appearing under different base stations can be used for association. For example, if a target appears in two adjacent base stations successively within a short period of time (e.g., within several frames), it can be inferred that it is the same target.
[0071] In a possible implementation manner of the embodiment of the present application, if the target is unobstructed, more traditional feature matching techniques can be adopted, such as template matching, feature point matching, etc.
[0072] In another possible implementation manner of the embodiment of the present application, if the target is partially blocked, for example, there are two adjacent base stations, such as the third base station and the fourth base station, and it is detected that the target to be tracked (taking a vehicle as an example) is partially blocked. For example, the third base station detects the front part of the vehicle, and the fourth base station detects the rear part of the vehicle. Then, the unblocked part can be focused on for analysis, and features can be extracted for matching. That is, based on the perception data of the target to be tracked collected by the third base station, the first unblocked feature of the target to be tracked is extracted, and based on the perception data of the target to be tracked collected by the fourth base station, the second unblocked feature of the target to be tracked is extracted; according to the first unblocked feature and the second unblocked feature, identity binding of the target to be tracked within the perception areas of the third base station and the fourth base station is performed.
[0073] In yet another possible implementation manner of the embodiment of the present application, if the target is completely blocked, for example, there are two adjacent base stations, such as the fifth base station and the sixth base station. The fifth base station is the upstream base station adjacent to the sixth base station. The fifth base station detects the target to be tracked, and the sixth base station does not detect the target to be tracked. Then, it can be determined that the target to be tracked is completely blocked within the perception area of the sixth base station. Therefore, according to the perception data of the target to be tracked collected by the fifth base station, trajectory prediction of the target to be tracked within the perception area of the sixth base station is performed to obtain a trajectory prediction result; according to the perception data of the target to be tracked collected by the fifth base station and the trajectory prediction result, identity binding of the target to be tracked within the perception areas of the fifth base station and the sixth base station is performed. Among them, trajectory prediction can adopt a matching method based on motion prediction, such as using a Kalman filter or other motion models to predict its trajectory.
[0074] Step 103, track the target to be tracked after identity binding.
[0075] It should be noted that after identity binding, each target to be tracked within the target perception area can be tracked.
[0076] In a possible implementation manner of the embodiment of the present application, the above step 103 may include: obtaining the detection box and prediction box of the target to be tracked in the target frame according to the perception data of the target to be tracked collected by each base station; matching the detection box and prediction box of the target to be tracked in the target frame to obtain a matching result; when the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
[0077] Among them, first, the detection box and prediction box of each frame can be obtained, and the detection box and prediction box can be matched by using the method of Intersection over Union (IOU) matching or distance matching.
[0078] That is, as an example, the detection box and prediction box of the target frame can be matched by using the IOU matching method to obtain a matching result. Specifically, the IOU area overlap degree of the detection box and prediction box can be calculated. First, the widths of the detection box and prediction box are scaled by using width scaling; then the detection box and prediction box are transformed into two dimensions and the IOU value is calculated, and the IOU matrix, that is, the cost matrix, is returned; then the Hungarian algorithm can be used to perform matching calculation on the detection box and prediction box, and the matching index (including row index and column index) is returned. Finally, the corresponding indexes are grouped in pairs, and the width is restored, so as to complete the matching of the detection box and prediction box.
[0079] As another example, the horizontal distance and vertical distance between the detection box and prediction box can be obtained; then, based on the horizontal distance and vertical distance between the detection box and prediction box, distance matching is performed on the detection box and prediction box to obtain a matching result. For example, it can be determined whether the horizontal distance or vertical distance between the detection box and prediction box is particularly large, that is, it is determined whether the horizontal distance between the detection box and prediction box is greater than the horizontal distance threshold, or whether the vertical distance between the two is greater than the vertical distance threshold. If it is greater, it is determined that the two do not match.
[0080] Specifically, the weighted distance of the horizontal and vertical distances of the detection box and prediction box can be calculated. First, the horizontal distance threshold and vertical distance threshold are set; then the distance between the detection box and prediction box is calculated, and the maximum distance threshold is calculated; then the indexes of the two boxes with a relatively large distance can be found and assigned 10000 to ensure that the two boxes with a relatively large distance will not be matched; finally, the Hungarian algorithm can be used to perform matching calculation on the detection box and prediction box, and the matching index (including row index and column index) is returned, and the corresponding indexes are grouped in pairs, so as to complete the matching of the detection box and prediction box.
[0081] Further, after completing the matching of the detection box and the prediction box, the matching result can be further confirmed. As an example, for the aforementioned IOU matching method, a distance matching strategy can be added on the basis of IOU matching for further inspection. The specific steps are as follows: First, check whether the IOU value between the already matched pairs is less than the threshold (which may be the result calculated by the Hungarian algorithm, and there may be no overlapping area in the actual situation); then judge whether the vertical distance between the detection box and the prediction box is greater than the vertical distance. If the IOU value of the two boxes is less than the threshold or the distance between the two boxes is greater than the distance threshold, it is considered that they do not match. In addition, for the aforementioned distance matching method, an IOU matching strategy can also be added on the basis of distance matching for further inspection.
[0082] To ensure the accuracy of the matching between the detection box and the prediction box, after determining the matching result (matching pair), the matching result can be rechecked.
[0083] As an example, a category check can be performed on the matching result, that is, the major categories of the detection box and the tracking box (such as motor vehicles, non-motor vehicles, pedestrians, etc.) should be consistent. Specifically, when the matching result is a successful match, the categories of the detection box and the prediction box can be obtained respectively; when the categories of the detection box and the prediction box are consistent, determine to execute the aforementioned step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked"; when the categories of the detection box and the prediction box are inconsistent, determine not to execute the aforementioned step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked".
[0084] As another example, a speed check can be performed on the matching result, that is, the ratio of the speed of the detection box to the speed of the tracking box should be less than the threshold. Specifically, when the matching result is a successful match, the speeds corresponding to the detection box and the prediction box can be obtained respectively; when the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than the preset first threshold, determine to execute the aforementioned step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked"; when the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset speed threshold, determine not to execute the aforementioned step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked".
[0085] As another example, the absolute value of the speed difference can be checked, that is, the difference between the detection box speed and the tracking box speed should be less than a threshold. Specifically, when the matching result is a successful match, the speeds corresponding to the detection box and the prediction box can be obtained respectively; when the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset second threshold, it is determined to execute the foregoing step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked"; when the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset second threshold, it is determined not to execute the foregoing step of "updating the tracking data of the target to be tracked in the target frame to track the target to be tracked".
[0086] The target tracking method disclosed in the foregoing embodiments of the present application first senses the target to be tracked in the target sensing area through multiple base stations to obtain the sensing data of the target to be tracked collected by each base station, where the multiple base stations are arranged in a zigzag layout on both sides of the target sensing area; then, according to the sensing data of the target to be tracked collected by each base station, identity binding is performed on the target to be tracked; finally, the target to be tracked after identity binding is tracked. Thus, by arranging the base stations in a zigzag layout, the occlusion problem that may be caused by the long-term side-by-side movement of targets is solved, and the accuracy of target tracking is improved.
[0087] See Figure 2 , which shows a schematic structural diagram of a target tracking device provided by an embodiment of the present application. For the convenience of description, only the parts related to the embodiments of the present application are shown.
[0088] The target tracking device may specifically include the following modules:
[0089] The data acquisition module 201 is configured to sense the target to be tracked in the target sensing area through multiple base stations to obtain the sensing data of the target to be tracked collected by each base station, where the multiple base stations are arranged in a zigzag layout on both sides of the target sensing area.
[0090] The identity binding module 202 is configured to perform identity binding on the target to be tracked according to the sensing data of the target to be tracked collected by each base station.
[0091] The target tracking module 203 is configured to track the target to be tracked after identity binding.
[0092] The target tracking device disclosed in the above embodiments of the present application first senses a target to be tracked in a target sensing area through multiple base stations, and obtains sensing data of the target to be tracked collected by each base station. Among them, the multiple base stations are arranged on both sides of the target sensing area in a zigzag layout. Then, based on the sensing data of the target to be tracked collected by each base station, identity binding is performed on the target to be tracked. Finally, the target to be tracked after identity binding is tracked. Thus, by arranging the base stations in a zigzag layout, the occlusion problem that may be caused by the long-term side-by-side movement of targets is solved, and the accuracy of target tracking is improved.
[0093] Further, in a possible implementation manner of the embodiments of the present application, the above data acquisition module 201 may specifically include the following sub-modules:
[0094] The first acquisition sub-module is used to obtain the first angle feature of the target to be tracked by using the first base station, and obtain the second angle feature of the target to be tracked by using the second base station, where the first base station and the second base station are two adjacent base stations.
[0095] The first processing sub-module is used to determine the sensing data of the target to be tracked in the sensing areas of the first base station and the second base station by combining the first angle feature and the second angle feature.
[0096] Further, in another possible implementation manner of the embodiments of the present application, when the third base station and the fourth base station detect that the target to be tracked is partially occluded, and the third base station and the fourth base station are two adjacent base stations, the above identity binding module 202 may specifically include the following sub-modules:
[0097] The second processing sub-module is used to extract the first unoccluded feature of the target to be tracked based on the sensing data of the target to be tracked collected by the third base station, and extract the second unoccluded feature of the target to be tracked based on the sensing data of the target to be tracked collected by the fourth base station.
[0098] The third processing sub-module is used to perform identity binding on the target to be tracked in the sensing areas of the third base station and the fourth base station according to the first unoccluded feature and the second unoccluded feature.
[0099] Further, in yet another possible implementation manner of the embodiments of the present application, when the fifth base station detects the target to be tracked and the sixth base station does not detect the target to be tracked, and the fifth base station is the upstream base station adjacent to the sixth base station, the above identity binding module 202 may specifically include the following sub-modules:
[0100] The fourth processing sub-module is used to determine that the target to be tracked is completely occluded in the sensing area of the sixth base station.
[0101] The fifth processing sub-module is used to perform trajectory prediction on the target to be tracked within the sensing area of the sixth base station according to the sensing data of the target to be tracked collected by the fifth base station, and obtain a trajectory prediction result.
[0102] The sixth processing sub-module is used to perform identity binding on the target to be tracked within the sensing areas of the fifth base station and the sixth base station according to the sensing data and the trajectory prediction result of the target to be tracked collected by the fifth base station.
[0103] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned target tracking module 203 may specifically include the following sub-modules:
[0104] The seventh processing sub-module is used to obtain the detection box and the prediction box of the target to be tracked in the target frame according to the sensing data of the target to be tracked collected by each base station.
[0105] The eighth processing sub-module is used to match the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result.
[0106] The ninth processing sub-module is used to update the tracking data of the target to be tracked in the target frame when the matching result is a successful match, so as to track the target to be tracked.
[0107] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned eighth processing sub-module may specifically include the following units:
[0108] The first processing unit is used to match the detection box and the prediction box of the target frame by using the intersection over union (IOU) matching method to obtain a matching result.
[0109] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned eighth processing sub-module may specifically include the following units:
[0110] The first acquisition unit is used to acquire the horizontal distance and the vertical distance between the detection box and the prediction box.
[0111] The second processing unit is used to perform distance matching on the detection box and the prediction box based on the horizontal distance and the vertical distance between the detection box and the prediction box to obtain a matching result.
[0112] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned ninth processing sub-module may specifically include the following units:
[0113] The second acquisition unit is used to acquire the categories of the detection box and the prediction box respectively when the matching result is a successful match.
[0114] A third processing unit, configured to determine to perform an update on the tracking data of the target to be tracked in the target frame when the categories of the detection box and the prediction box are the same, so as to track the target to be tracked.
[0115] A fourth processing unit, configured to determine not to perform an update on the tracking data of the target to be tracked in the target frame when the categories of the detection box and the prediction box are different, so as to track the target to be tracked.
[0116] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned ninth processing sub-module may specifically include the following units:
[0117] A third acquisition unit, configured to respectively acquire the speeds corresponding to the detection box and the prediction box when the matching result is a successful match.
[0118] A fifth processing unit, configured to determine to perform an update on the tracking data of the target to be tracked in the target frame when the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset first threshold, so as to track the target to be tracked.
[0119] A sixth processing unit, configured to determine not to perform an update on the tracking data of the target to be tracked in the target frame when the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to a preset speed threshold, so as to track the target to be tracked.
[0120] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned ninth processing sub-module may specifically include the following units:
[0121] A fourth acquisition unit, configured to respectively acquire the speeds corresponding to the detection box and the prediction box when the matching result is a successful match.
[0122] A seventh processing unit, configured to determine to perform an update on the tracking data of the target to be tracked in the target frame when the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset second threshold, so as to track the target to be tracked.
[0123] An eighth processing unit, configured to determine not to perform an update on the tracking data of the target to be tracked in the target frame when the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to a preset second threshold, so as to track the target to be tracked.
[0124] The target tracking device provided by the embodiment of the present application can be applied to the foregoing method embodiment. For details, refer to the description of the foregoing method embodiment, which will not be elaborated here.
[0125] Figure 3 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 3As shown, the terminal device 300 of this embodiment includes: at least one processor 310 ( Figure 3 only one is shown in the figure), a processor, a memory 320, and a computer program 321 stored in the memory 320 and executable on the at least one processor 310. When the processor 310 executes the computer program 321, the steps in the embodiment of the above-mentioned target tracking method are implemented.
[0126] The terminal device 300 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 310 and a memory 320. Those skilled in the art can understand that Figure 3 merely examples of the terminal device 300 do not constitute a limitation on the terminal device 300, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input and output devices, network access devices, etc.
[0127] The so-called processor 310 may be a central processing unit (CPU), and the processor 310 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0128] The memory 320 may be an internal storage unit of the terminal device 300 in some embodiments, such as the hard disk or memory of the terminal device 300. The memory 320 may also be an external storage device of the terminal device 300 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 300. Further, the memory 320 may also include both the internal storage unit and the external storage device of the terminal device 300. The memory 320 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 320 may also be used to temporarily store data that has been output or will be output.
[0129] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.
[0130] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0131] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.
[0132] In the embodiments provided in this application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.
[0133] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0134] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing unit, may exist physically alone for each unit, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.
[0135] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, all or part of the processes in the above-mentioned embodiment methods of the present application can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0136] All or part of the processes in the above-mentioned embodiment methods of the present application can also be completed by a computer program product. When the computer program product runs on a terminal device, the terminal device can execute the steps in the above-mentioned various method embodiments when executed.
[0137] The above-mentioned 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A target tracking method, characterized in that, Including: Perceiving a target to be tracked within a target perception area through multiple base stations, and obtaining perception data of the target to be tracked collected by each of the base stations, where the multiple base stations are arranged in a zigzag layout on both sides of the target perception area; Performing identity binding on the target to be tracked according to the perception data of the target to be tracked collected by each of the base stations; Tracking the target to be tracked after identity binding.
2. The target tracking method according to claim 1, characterized in that The step of perceiving a target to be tracked within a target perception area through multiple base stations and obtaining perception data of the target to be tracked collected by each of the base stations includes: Obtaining a first angle feature of the target to be tracked by using a first base station, and obtaining a second angle feature of the target to be tracked by using a second base station, where the first base station and the second base station are two adjacent base stations; Combining the first angle feature and the second angle feature to determine perception data of the target to be tracked within the perception area of the first base station and the perception area of the second base station.
3. The target tracking method according to claim 1, wherein, When a third base station and a fourth base station detect that the target to be tracked is partially occluded, and the third base station and the fourth base station are two adjacent base stations, the step of performing identity binding on the target to be tracked according to the perception data of the target to be tracked collected by each of the base stations includes: Extracting a first unoccluded feature of the target to be tracked based on the perception data of the target to be tracked collected by the third base station, and extracting a second unoccluded feature of the target to be tracked based on the perception data of the target to be tracked collected by the fourth base station; Performing identity binding on the target to be tracked within the perception areas of the third base station and the fourth base station according to the first unoccluded feature and the second unoccluded feature.
4. The target tracking method according to claim 1, characterized in that When a fifth base station detects the target to be tracked and a sixth base station does not detect the target to be tracked, and the fifth base station is an upstream base station adjacent to the sixth base station, the step of performing identity binding on the target to be tracked according to the perception data of the target to be tracked collected by each of the base stations includes: Determining that the target to be tracked is completely occluded within the perception area of the sixth base station; Performing trajectory prediction on the target to be tracked within the perception area of the sixth base station according to the perception data of the target to be tracked collected by the fifth base station, and obtaining a trajectory prediction result; Performing identity binding on the target to be tracked within the perception areas of the fifth base station and the sixth base station according to the perception data of the target to be tracked collected by the fifth base station and the trajectory prediction result.
5. The target tracking method according to claim 1, characterized in that, The step of tracking the target to be tracked after identity binding includes: Obtaining a detection box and a prediction box of the target to be tracked in a target frame according to the perception data of the target to be tracked collected by each of the base stations; Matching the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result; When the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
6. The target tracking method according to claim 5, wherein Performing matching on the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result, including: Using the Intersection over Union (IOU) matching method to perform matching on the detection box and the prediction box of the target frame to obtain the matching result.
7. The target tracking method according to claim 5, characterized in that, Performing matching on the detection box and the prediction box of the target to be tracked in the target frame to obtain a matching result, including: Obtaining the horizontal distance and the vertical distance between the detection box and the prediction box; Based on the horizontal distance and the vertical distance between the detection box and the prediction box, performing distance matching on the detection box and the prediction box to obtain the matching result.
8. The target tracking method according to claim 5, wherein When the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked, including: When the matching result is a successful match, respectively obtaining the categories of the detection box and the prediction box; When the categories of the detection box and the prediction box are the same, determining to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked; When the categories of the detection box and the prediction box are different, determining not to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
9. The target tracking method according to claim 5, characterized in that, When the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked, including: When the matching result is a successful match, respectively obtaining the speeds corresponding to the detection box and the prediction box; When the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset first threshold, determining to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked; When the ratio between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset speed threshold, determining not to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
10. The target tracking method according to claim 5, wherein, When the matching result is a successful match, updating the tracking data of the target to be tracked in the target frame to track the target to be tracked, including: When the matching result is a successful match, respectively obtaining the speeds corresponding to the detection box and the prediction box; When the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is less than a preset second threshold, determining to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked; When the difference between the speed corresponding to the detection box and the speed corresponding to the prediction box is greater than or equal to the preset second threshold, determining not to perform updating the tracking data of the target to be tracked in the target frame to track the target to be tracked.
11. A target tracking device, characterized in that, Including: A data acquisition module, configured to sense a target to be tracked within a target sensing area through multiple base stations, and obtain sensing data of the target to be tracked collected by each of the base stations, wherein the multiple base stations are arranged on both sides of the target sensing area in a zigzag layout; An identity binding module, configured to perform identity binding on the target to be tracked according to the sensing data of the target to be tracked collected by each of the base stations; A target tracking module, configured to track the target to be tracked after identity binding.
12. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 10 is implemented.
13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.