Target vehicle tracking method, system, target vehicle tracking device and storage medium

Abstract

The application provides a target vehicle tracking method, system, target vehicle tracking device and storage medium. The method comprises: when a target vehicle passes through a first intersection, acquiring travel data of the target vehicle when passing through the first intersection, the travel data comprising travel direction information; selecting at least one alternative subordinate intersection corresponding to the first intersection, and acquiring intersection direction information corresponding to the travel direction information; selecting a next intersection, as a second intersection, from the alternative subordinate intersections, according to the travel direction information of the target vehicle and the intersection direction information corresponding to the travel direction information of each alternative subordinate intersection, and predicting that the target vehicle will enter the next intersection; and sending a coordinated control instruction to a tracking resource device corresponding to the second intersection. The application predicts the travel direction of the target vehicle, and coordinates the tracking resource device available on the front travel route in advance, thereby improving the target vehicle tracking efficiency.

Description

Technical Field

[0001] This application relates to the field of vehicle tracking technology, and in particular to a target vehicle tracking method, system, target vehicle tracking device and storage medium. Background Technology

[0002] Real-time tracking of target vehicles is a crucial aspect of traffic police operations, applicable to scenarios such as apprehending and surrounding criminal vehicles. Currently, the conventional implementation involves using intersection monitoring equipment and video image recognition technology to identify target vehicles based on their license plate, model, and color, then issuing an alert. This is a reactive business model; further action can only be taken when the target vehicle is monitored at the intersection, by which time the vehicle may have already left, resulting in high latency and significantly reduced business value. Furthermore, in other applications requiring real-time target vehicle tracking, such as those needing real-time location information for more accurate navigation, the high latency of target vehicle tracking also significantly diminishes navigation effectiveness. Summary of the Invention

[0003] To address the problems in the prior art, the purpose of this application is to provide a target vehicle tracking method, system, target vehicle tracking device, and storage medium, which improves the tracking efficiency of target vehicles by predicting the direction of travel of the target vehicle and coordinating the available tracking resources and devices along the route in advance.

[0004] This application provides a target vehicle tracking method, including the following steps:

[0005] When a target vehicle is detected passing through the first intersection, the travel data of the target vehicle when passing through the first intersection is obtained, and the travel data includes travel direction information;

[0006] Select at least one alternative lower-level intersection corresponding to the first intersection, and obtain the intersection direction information corresponding to the travel direction information of the alternative lower-level intersection;

[0007] Based on the travel direction information of the target vehicle and the intersection direction information corresponding to the travel direction information of each of the candidate lower-level intersections, the next intersection to which the target vehicle is predicted to enter is selected from the candidate lower-level intersections as the second intersection.

[0008] The coordination control command is sent to the tracking resource device corresponding to the second intersection, and the coordination control command is used to instruct the tracking resource device to start executing the target vehicle tracking task.

[0009] In the target vehicle tracking method of this application, the travel direction information of the target vehicle when it passes through the first intersection is first obtained, and the intersection direction information of each candidate lower-level intersection is also obtained. The travel direction information of the target vehicle and the intersection direction information of each candidate lower-level intersection can be combined to predict the target vehicle's travel route, determine the next second intersection the predicted target vehicle will enter, and then send a coordinated control command in advance to the tracking resource device corresponding to the second intersection. The tracking resource device corresponding to the second intersection can then prepare for subsequent tracking in advance. By adopting this scheme, the continuity of target vehicle tracking can be improved, avoiding tracking delays caused by the corresponding tracking resource device not being ready when the target vehicle arrives at the second intersection, and greatly improving the effectiveness of continuous target vehicle tracking.

[0010] In some embodiments, the travel direction information includes a first direction angle of the travel direction of the target vehicle relative to a standard direction, and the intersection direction information includes a second direction angle of the first entrance lane of the candidate lower-level intersection relative to the standard direction, wherein the first entrance lane is the entrance lane of the candidate lower-level intersection corresponding to the travel direction information.

[0011] Selecting the next intersection from the candidate lower-level intersections to which the predicted target vehicle will enter includes comparing the first direction angle with the second direction angle of the first entrance lane of each candidate lower-level intersection, and selecting the intersection corresponding to the second direction angle closest to the first direction angle as the next intersection from which the predicted target vehicle will enter.

[0012] In some embodiments, the travel data further includes the target vehicle's position coordinates and the target vehicle's speed;

[0013] Sending the coordination control command to the tracking resource device corresponding to the second intersection includes the following steps:

[0014] Based on the target vehicle's location coordinates and the information of the first entrance lane of the second intersection, calculate the simulated driving trajectory of the target vehicle from the target vehicle's location coordinates to the first entrance lane of the second intersection;

[0015] Based on the driving distance of the simulated driving trajectory and the driving speed of the target vehicle, calculate the arrival time of the target vehicle to the first entrance lane of the second intersection;

[0016] The transmission time of the coordination control command is calculated based on the arrival time and the preset flexible time.

[0017] The coordinated control command is sent to the tracking resource device corresponding to the second intersection at the specified transmission time.

[0018] In some embodiments, when a target vehicle is detected passing through the first intersection, acquiring the travel data of the target vehicle when it passes through the first intersection includes the following steps:

[0019] The target vehicle was detected entering the area of ​​the first intersection.

[0020] The system acquires the location source data corresponding to the target vehicle in real time, calculates the real-time position coordinates of the target vehicle and the real-time direction angle relative to the standard direction, and projects the target vehicle onto the geographic information system map based on the calculation results.

[0021] The last frame within the location area of ​​the target vehicle at the first intersection;

[0022] Calculate the target vehicle's speed corresponding to the last frame, and use the target vehicle's real-time position coordinates, real-time direction angle, and target vehicle speed corresponding to the last frame as the travel data.

[0023] In some embodiments, obtaining the intersection direction information corresponding to the travel direction information of the candidate lower-level intersections includes:

[0024] Obtain the second direction angle of the first approach lane of the pre-stored candidate lower-level intersection; or,

[0025] Obtain the position coordinates of the centerline key points of the first entrance lane of the candidate lower-level intersection, and calculate the direction angle of the line connecting the centerline key points relative to the standard direction, which is used as the second direction angle.

[0026] In some embodiments, obtaining the intersection direction information corresponding to the travel direction information of the candidate lower-level intersections includes:

[0027] The instantaneous direction angle of all vehicles passing through the first entrance lane of the candidate lower-level intersection within a certain time period relative to the standard direction when passing the stop line of the first entrance lane is statistically analyzed, and the second direction angle of the first entrance lane of the candidate lower-level intersection is calculated based on all the obtained instantaneous direction angles.

[0028] In some embodiments, selecting the candidate lower-level intersections corresponding to the first intersection includes the following steps:

[0029] Based on road segment connectivity rules and the shortest path principle, a search for the first approach lane of a candidate lower-level intersection is performed on the geographic information system map. The candidate lower-level intersection corresponding to the first intersection is selected, and the first approach lane of the candidate lower-level intersection corresponding to the travel direction information is determined; or,

[0030] Based on the preset correspondence between each intersection and the candidate lower-level intersection, the candidate lower-level intersection corresponding to the first intersection is obtained, and the first entrance lane corresponding to the candidate lower-level intersection and the travel direction information is determined.

[0031] This application embodiment also provides a target vehicle tracking system applied to the aforementioned target vehicle tracking method, the system comprising:

[0032] The first information acquisition module is used to acquire the travel data of the target vehicle when it passes through the first intersection, and the travel data includes travel direction information.

[0033] The second information acquisition module is used to select at least one candidate lower-level intersection corresponding to the first intersection, and acquire the intersection direction information corresponding to the candidate lower-level intersection and the travel direction information.

[0034] The intersection prediction module is used to select the next intersection from the candidate lower-level intersections as the second intersection, based on the target vehicle's travel direction information and the intersection direction information corresponding to the travel direction information of each candidate lower-level intersection.

[0035] The instruction sending module is used to send coordination control instructions to the tracking resource device corresponding to the second intersection.

[0036] In the target vehicle tracking system of this application, a first information acquisition module acquires the target vehicle's direction of travel when it passes through a first intersection, a second information acquisition module acquires the intersection direction information of each candidate lower-level intersection, and an intersection prediction module combines the target vehicle's direction of travel information and the intersection direction information of each candidate lower-level intersection to predict the target vehicle's route and determine the next second intersection the target vehicle will enter. Then, a command sending module sends a coordinated control command in advance to the tracking resource device corresponding to the second intersection, allowing the tracking resource device at the second intersection to prepare for subsequent tracking. By adopting this scheme, the continuity of target vehicle tracking can be improved, avoiding tracking delays caused by the corresponding tracking resource device not being ready when the target vehicle arrives at the second intersection, and greatly improving the effectiveness of continuous target vehicle tracking.

[0037] This application embodiment also provides a target vehicle tracking device, including a computing hardware system, the computing hardware system comprising:

[0038] processor;

[0039] A memory in which executable instructions of the processor are stored;

[0040] The processor is configured to perform the steps of the target vehicle tracking method by executing the executable instructions.

[0041] By employing the target vehicle tracking device provided in this application, the processor executes the target vehicle tracking method when executing the executable instructions, thereby obtaining the beneficial effects of the aforementioned target vehicle tracking method. The target vehicle tracking device can, for example, be deployed as an edge computing device at the edge of an intersection, greatly reducing data transmission network latency, reducing the operational burden on the road traffic management center server, and its lightweight design allows for rapid deployment, reliably and efficiently ensuring the implementation of the target vehicle tracking method; however, this application is not limited to this.

[0042] This application also provides a computer-readable storage medium for storing a program that, when executed by a processor, implements the steps of the target vehicle tracking method.

[0043] By employing the computer-readable storage medium provided in this application, wherein the program stored therein implements the steps of the target vehicle tracking method when executed, the beneficial effects of the target vehicle tracking method described above can be obtained. Attached Figure Description

[0044] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings.

[0045] Figure 1 This is a flowchart of a target vehicle tracking method according to an embodiment of this application;

[0046] Figure 2 This is a schematic diagram illustrating the prediction of the movement of a target vehicle according to an embodiment of this application;

[0047] Figure 3 This is a schematic diagram of a first method for calculating the second direction angle of the first approach lane at an intersection according to an embodiment of this application;

[0048] Figure 4 This is a schematic diagram of a second method for calculating the second direction angle of the first approach lane at an intersection according to an embodiment of this application;

[0049] Figure 5 This is a schematic diagram of a target vehicle tracking system according to an embodiment of this application;

[0050] Figure 6 This is a structural block diagram of a target vehicle tracking device according to an embodiment of this application;

[0051] Figure 7 This is a schematic diagram of the structure of a computer storage medium according to an embodiment of this application. Detailed Implementation

[0052] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore repeated descriptions of them will be omitted. Although the terms "first" or "second," etc., are used in this specification to denote certain features, these are merely indicative of function and not as a limitation on the number or importance of specific features.

[0053] like Figure 1 As shown, in one embodiment, this application provides a target vehicle tracking method, including the following steps:

[0054] S100: When a target vehicle is detected passing through the first intersection, the travel data of the target vehicle when passing through the first intersection is obtained, and the travel data includes travel direction information;

[0055] Here, the target vehicle is the vehicle being tracked, and the first intersection is the intersection where the target vehicle is currently located. Specifically, the location area of ​​each intersection can be preset, and the location of the target vehicle can be obtained in real time. When it is determined that the target vehicle has traveled to the location area of ​​the first intersection based on its location, it is considered that the target vehicle has passed the first intersection. The real-time location of the target vehicle can be obtained directly from another target vehicle positioning device, or it can be obtained by using a vehicle fusion positioning algorithm based on the target vehicle's related positioning source data (video data and / or radar data).

[0056] The travel direction information is information that characterizes the travel direction trend of the target vehicle. For example, it can be expressed as the angle between the travel direction of the target vehicle and a certain direction, or the degree of deviation relative to a certain direction.

[0057] S200: Select at least one alternative lower-level intersection corresponding to the first intersection, and obtain the intersection direction information corresponding to the alternative lower-level intersection and the travel direction information;

[0058] The alternative lower-level intersections here are those connected to the first intersection, and the target vehicle can choose to enter the next intersection. The intersection direction information of the alternative lower-level intersections can be the angle between the extension direction of the intersection and a certain direction, or the degree of deviation relative to a certain direction, etc.

[0059] S300: Based on the travel direction information of the target vehicle and the intersection direction information corresponding to the travel direction information of each of the candidate lower-level intersections, select the next intersection from the candidate lower-level intersections to be the predicted target vehicle's next intersection as the second intersection;

[0060] This method combines information from two directions to predict the next intersection the target vehicle will enter, which means predicting the next intersection the target vehicle might pass through in its forward path based on the trend of the target vehicle's direction of travel.

[0061] S400: Send a coordination control command to the tracking resource device corresponding to the second intersection. The coordination control command is used to instruct the tracking resource device to start executing the target vehicle tracking task.

[0062] In this embodiment, the tracking resource device refers to the device corresponding to the second intersection that performs the target vehicle tracking task. For example, the tracking resource device is a monitoring device located at the second intersection, which can collect video data, radar data, etc. of the target vehicle at the second intersection. After predicting the next intersection the target vehicle will pass through, it sends a coordination control command to the monitoring device at the second intersection in advance, so that the monitoring device at the second intersection can start in advance and begin to execute the target vehicle tracking task pre-set in the monitoring device. This target vehicle tracking task may include shooting, identifying, and detecting the target vehicle, so that tracking can begin immediately when the target vehicle arrives at the second intersection, thereby greatly reducing the tracking delay. Alternatively, the tracking resource device may also be the internal communication device of the vehicle performing the tracking task. The tracking resource device corresponding to the second intersection may be the internal communication device of the vehicle performing the tracking task closest to the second intersection, which can send coordination control commands to the vehicle performing the tracking task. The target vehicle tracking task may include planning the driving route of the vehicle performing the tracking task according to the target vehicle's position and tracking the target vehicle's movement, or it may be the internal communication device of the vehicle performing the tracking task that is responsible for managing the second intersection. Alternatively, the tracking resource device can be a traffic light at the second intersection. The color of the traffic light can be adjusted by sending a coordinated control command. The target vehicle tracking task can include keeping the traffic light in the direction of the target vehicle's travel red, or it can restrict the passage of the target vehicle.

[0063] In the target vehicle tracking method of this application, step S100 obtains the travel direction information of the target vehicle when it passes through the first intersection. Step S200 obtains the intersection direction information corresponding to the travel direction information for each candidate lower-level intersection. Step S300 combines the travel direction information of the target vehicle and the corresponding intersection direction information for each candidate lower-level intersection to predict the target vehicle's travel route and determine the next second intersection the target vehicle will enter. Then, step S400 sends a coordination control command to the tracking resource device corresponding to the second intersection in advance, allowing the tracking resource device to prepare for subsequent tracking. By adopting this scheme, the continuity of target vehicle tracking can be improved, avoiding tracking delays caused by the corresponding tracking resource device not being ready when the target vehicle arrives at the second intersection, thus greatly improving the effectiveness of continuous target vehicle tracking. This application can be used for continuous tracking of a specific target vehicle, or for continuous tracking of multiple target vehicles. It predicts the next intersection that each target vehicle will pass through and coordinates the tracking resources and equipment at the corresponding intersection in advance.

[0064] In this embodiment, the travel direction information includes a first azimuth angle of the target vehicle's travel direction relative to a standard direction, and the intersection direction information includes a second azimuth angle of the first entrance lane of the candidate lower-level intersection relative to the standard direction. The first entrance lane is the entrance lane of the candidate lower-level intersection corresponding to the travel direction information. Specifically, for a crossroads, an intersection may have four entrance lanes, and the first entrance lane is the possible entrance lane determined based on the target vehicle's current travel direction. The standard direction can be selected as needed, for example, a specific coordinate axis direction of a coordinate system. When the standard direction is north, each azimuth angle refers to an azimuth angle. The first azimuth angle is the horizontal angle between the north direction line at the target vehicle's location and the target vehicle's travel direction line in a clockwise direction. The second azimuth angle is the horizontal angle between the north direction line at a point in the first entrance lane of the candidate lower-level intersection and the extended direction line of the first entrance lane in a clockwise direction. The following explanation uses azimuth angles as an example, but this application is not limited to this.

[0065] Figure 2 A schematic diagram illustrating an example of target vehicle travel prediction is provided, where the target vehicle being tracked is represented by a square at intersection A. In this embodiment, the travel data may further include the target vehicle's position coordinates and its speed. Step S100: When the target vehicle is detected passing through the first intersection, the travel data of the target vehicle at the first intersection is acquired, including the following steps:

[0066] Once the target vehicle is detected entering the area of ​​the first intersection, it is determined that the target vehicle has passed through the first intersection. Figure 2 For example, if the target vehicle is currently located within the area of ​​intersection A, then the first intersection is intersection A.

[0067] The system acquires the location source data corresponding to the target vehicle in real time, calculates the real-time position coordinates and real-time azimuth angle of the target vehicle relative to the standard direction, and projects the target vehicle onto a Geographic Information System (GIS) map based on the calculation results. Here, the location source data of the target vehicle may include, for example, video data and / or radar data related to the target vehicle. The calculation of the real-time position coordinates and real-time azimuth angle of the target vehicle relative to the standard direction can be achieved by using existing video / radar data fusion positioning algorithms or by relying solely on video or solely on radar data for positioning.

[0068] The last frame within the location area of ​​the target vehicle at the first intersection;

[0069] The target vehicle's speed corresponding to the last frame is calculated (e.g., based on changes in the target vehicle's position coordinates and time over adjacent frames), and the real-time position coordinates, real-time azimuth, and speed of the target vehicle corresponding to the last frame are used as the travel data; that is, the real-time azimuth of the target vehicle corresponding to the last frame is the first azimuth. In this embodiment, selecting the target vehicle's travel data from the last frame accurately represents the target vehicle's real-time position coordinates, real-time azimuth, and speed when it leaves the area of ​​the first intersection.

[0070] In this embodiment, the target vehicle tracking method can be implemented based on a holographic road network. A holographic road network is a road environment that uses a high-precision digital map as a unified coordinate system, integrating structured data from existing road sensors such as video, microwave radar, and lidar into a unified coordinate system. This results in the acquisition of the full range of positions, speeds, and trajectories of all vehicles, non-motorized vehicles, and pedestrians within the entire road network. At intersections within the holographic road network, for example, the following can be deployed: traffic signals and traffic lights; video capture devices to capture vehicle videos and collect vehicle attributes such as license plate, model, and color; radar devices to collect vehicle latitude and longitude coordinates, speed, and azimuth angle; and edge computing devices to acquire video data from the video capture devices and radar data from the radar devices. These devices then execute the steps of the target vehicle tracking method described in this application. This allows for the processing of various sensor data directly on the roadside without a central server, reducing data communication latency and the workload of the central server. However, this application is not limited to this; in another embodiment, the target vehicle tracking method can also be executed on a central server.

[0071] In this embodiment, step S200, selecting the candidate lower-level intersection corresponding to the first intersection, includes the following steps:

[0072] Based on road segment connectivity rules and the shortest path principle, a search for the first approach lane of a candidate lower-level intersection is performed on the geographic information system map. The candidate lower-level intersection corresponding to the first intersection is selected, and the first approach lane of the candidate lower-level intersection corresponding to the travel direction information is determined.

[0073] This method searches for the first approach lane of candidate lower-level intersections based on road segment connectivity rules and the shortest path principle. For example, it could include: first, obtaining all connected intersections to the first intersection based on road segment connectivity; then, calculating the path distance from the first intersection to each approach lane of each connected intersection; sorting by path distance; and selecting a preset number of intersections and their corresponding approach lanes with the smallest path distance as candidate lower-level intersections and their corresponding first approach lanes for the first intersection. Alternatively, it could include: first, obtaining the approach lanes of connected intersections of the first intersection in each direction of travel (e.g., a crossroads corresponds to four directions of travel (east, west, south, and north), while a T-junction corresponds to only three directions of travel); then selecting the intersection with the smallest path distance from the first intersection in each direction of travel and its corresponding approach lane as candidate lower-level intersections and their corresponding first approach lanes for that direction of travel, thus obtaining the candidate lower-level intersections and their corresponding first approach lanes for each direction of travel.

[0074] In another implementation, the first approach lanes of each intersection can be pre-searched on a geographic information system map based on road segment connectivity rules and the shortest path principle to obtain the corresponding candidate lower-level intersections. The correspondence between each intersection and the first approach lanes of its candidate lower-level intersections can be pre-stored. The method for searching the first approach lanes of candidate lower-level intersections can adopt the method described above for processing the first intersection. Step S200, selecting the candidate lower-level intersection corresponding to the first intersection, includes: obtaining the candidate lower-level intersection corresponding to the first intersection based on the preset correspondence between each intersection and the candidate lower-level intersections, and determining the first approach lane of the candidate lower-level intersection corresponding to the travel direction information. However, this application is not limited to this. In other implementations, for example, the correspondence between each intersection and the first approach lanes of its candidate lower-level intersections can be pre-set manually, or the correspondence between each intersection and the first approach lanes of its candidate lower-level intersections can be pre-learned using a deep learning model, all of which fall within the scope of protection of this application.

[0075] In step S300, selecting the next intersection from the candidate lower-level intersections to which the predicted target vehicle will enter includes: comparing the first azimuth angle with the second azimuth angle of the first entrance lane of each candidate lower-level intersection, and selecting the intersection corresponding to the second azimuth angle closest to the first azimuth angle as the next intersection to which the predicted target vehicle will enter, which is the second intersection, that is, the intersection where the target vehicle is most likely to enter.

[0076] Figure 2 A schematic diagram illustrating an example of selecting a second intersection is provided. The target vehicle is currently at intersection A (first intersection). The target vehicle's current first azimuth angle α is obtained. Each subsequent intersection of holographic intersection A is traversed as a candidate lower-level intersection, including intersections B1, B2, and B3. The first approach lane of each candidate lower-level intersection is determined, generating a set of candidate first approach lanes. Figure 2 The data includes the south entrance lane of intersection B1, the north entrance lane of intersection B2, and the west entrance lane of intersection B3. Then, the second azimuth angles β1, β2, and β3 corresponding to the three marked first entrance lanes are obtained, where β1 = 351°, β2 = 169.4°, and β3 = 77.7°.

[0077] The first azimuth angle α and the three second azimuth angles β i Perform the subtraction and calculate the absolute value Δ for each:

[0078] Δ1 = |α - β1| = 6.3°

[0079] Δ2 = |α - β2| = 175.3°

[0080] Δ3=|α-β3|=267°

[0081] Choose the minimum absolute value of the difference:

[0082] min(Δ1,Δ2,Δ3)=Δ1=6.3°

[0083] The minimum value is Δ1, which corresponds to intersection B1. Therefore, the second intersection into which the target vehicle is predicted to enter is intersection B1.

[0084] In this embodiment, step S400, sending the coordination control command to the tracking resource device corresponding to the second intersection, can be done immediately after determining the second intersection according to step S300. This allows for advance control of the tracking resource device's activation, preparing in advance before the target vehicle arrives at the second intersection. Furthermore, considering that the target vehicle needs a certain travel time from the first intersection to the second intersection—for example, this time may be long during periods of severe traffic congestion—activating the tracking resource device at the second intersection far in advance could result in prolonged waiting times and wasted resources. Therefore, in this embodiment, the arrival time of the target vehicle at the first entrance lane of the second intersection can be predicted based on its travel time. A lead time can be set before this arrival time, and the tracking resource device at the second intersection can be activated only when this lead time is met.

[0085] Specifically, step S400, which involves sending a coordination control command to the tracking resource device corresponding to the second intersection, includes the following steps:

[0086] Based on the target vehicle's location coordinates and the information of the first entrance lane of the second intersection, calculate the simulated driving trajectory of the target vehicle from the target vehicle's location coordinates to the first entrance lane of the second intersection. This simulated driving trajectory can be achieved by shortest path planning between the two intersections. Here, the information of the first entrance lane is, for example, the location coordinates of the stop line of the first entrance lane.

[0087] Based on the driving distance S of the simulated driving trajectory AB1 and the target vehicle's speed v A Calculate the arrival time t′ of the target vehicle to the first entrance lane of the second intersection;

[0088] In this embodiment, the calculation of the arrival time t′ includes: using the travel distance S AB1 Divide by the target vehicle's speed v A ,Right now

[0089] Based on the arrival time and a preset flexible time, the transmission time t of the coordination control command is calculated; specifically, the arrival time t′ is subtracted by a flexible time t. 弹 After setting a preset empirical value, the time t = t′ - t is used as the sending time for the coordination control command. 弹 ;

[0090] For example, assuming the travel distance is 120m and the speed is v AGiven a speed of 10 m / s and a preset elastic time of 5 seconds, the transmission time of the coordination control command is...

[0091] The coordinated control command is sent to the tracking resource device corresponding to the second intersection at the specified sending time. Specifically, if the calculated sending time t is less than or equal to 0, the coordinated control command is sent to the corresponding tracking resource device immediately. By setting a flexible time, the communication delay time for the coordinated control command to reach the tracking resource device and the response delay time of the tracking resource device after receiving the coordinated control command can be eliminated in advance, allowing for more accurate coordination of the tracking status of the tracking resource device and enabling the tracking resource device to start executing the target vehicle tracking task earlier.

[0092] Therefore, in this embodiment, the advance amount of the tracking resource device at the second intersection can be controlled by adjusting the specific length of the elastic time. By setting the elastic time, the tracking resource device can be prepared for tracking in advance without waiting for too long, thereby effectively improving tracking efficiency and saving resources.

[0093] In this embodiment, in step S200, obtaining the intersection direction information corresponding to the travel direction information of the candidate lower-level intersections can be done in one of the following three ways:

[0094] (1) Obtain the position coordinates of the centerline key point of the first entrance lane of the candidate lower level intersection, and calculate the azimuth angle of the line connecting the centerline key points relative to the standard direction, as the second azimuth angle.

[0095] by Figure 3 Taking intersection B1 as an example, calculate the azimuth angle (corresponding to the north direction n) of the line m connecting the key points of the centerline of the first approach lane B11 of intersection B1 relative to the north direction n. Figure 3 The clockwise angle indicated by the arc-shaped arrow is used as the second azimuth angle.

[0096] (2) Calculate the instantaneous azimuth angle of all vehicles passing through the first entrance lane of the candidate lower-level intersection within a certain time period when they pass the stop line of the first entrance lane relative to the standard direction, and calculate the second azimuth angle of the first entrance lane of the candidate lower-level intersection based on all the obtained instantaneous azimuth angles.

[0097] by Figure 4 Taking intersection B1 as an example, statistics are compiled on all vehicles passing through the first entrance lane of the candidate lower-level intersection within a certain time period. Figure 4Taking three vehicles as an example, the instantaneous azimuth angles (the azimuth angles between x1 and n, x2 and n, and x3 and n) relative to the standard direction are obtained when they pass the stop line of the first entrance lane. Figure 4 The mean of all instantaneous azimuth angles (indicated by the clockwise angle of the arc-shaped arrow) is calculated and used as the second azimuth angle of the first approach lane of the candidate lower-level intersection.

[0098] (3) Obtain the second azimuth angle of the first approach lane of the candidate lower-level intersection that is stored in advance. The second azimuth angle of the first approach lane of the candidate lower-level intersection that is stored in advance may be obtained in advance by the above-mentioned method (1) or (2), but this application is not limited to this.

[0099] In this embodiment, the target vehicle tracking method is a cyclically executed process. Once the target vehicle reaches the location area of ​​the second intersection, the second intersection becomes the first intersection of the next cycle, and steps S100 to S400 of the target vehicle tracking method are executed again to achieve continuous tracking of the target vehicle.

[0100] like Figure 5 As shown, this application embodiment also provides a target vehicle tracking system applied to the aforementioned target vehicle tracking method, the system comprising:

[0101] The first information acquisition module M100 is used to acquire the travel data of the target vehicle when it passes through the first intersection, and the travel data includes travel direction information.

[0102] The second information acquisition module M200 is used to select at least one candidate lower-level intersection corresponding to the first intersection and acquire the intersection direction information of the candidate lower-level intersection.

[0103] The intersection prediction module M300 is used to select the next intersection that the target vehicle will enter from the candidate lower-level intersections, based on the travel direction information of the target vehicle and the intersection direction information of each candidate lower-level intersection, as the second intersection.

[0104] The instruction sending module M400 is used to send coordination control instructions to the tracking resource device corresponding to the second intersection.

[0105] In the target vehicle tracking system of this application, the first information acquisition module M100 acquires the travel direction information of the target vehicle when it passes through the first intersection, the second information acquisition module M200 acquires the intersection direction information of each candidate lower-level intersection, and the intersection prediction module M300 combines the travel direction information of the target vehicle and the intersection direction information of each candidate lower-level intersection to predict the travel route of the target vehicle and determine the next second intersection into which the target vehicle will enter. Then, the command sending module M400 sends a coordinated control command to the tracking resource device corresponding to the second intersection in advance, allowing the tracking resource device at the second intersection to prepare for subsequent tracking. By adopting this scheme, the continuity of target vehicle tracking can be improved, avoiding tracking delays caused by the corresponding tracking resource device not being ready when the target vehicle arrives at the second intersection, and greatly improving the effectiveness of continuous target vehicle tracking.

[0106] The functions of each module in the target vehicle tracking system can be implemented using the specific implementation methods of each step in the target vehicle tracking method described above, which will not be elaborated here.

[0107] like Figure 6 As shown in the illustration, this application embodiment also provides a target vehicle tracking device, including a computing hardware system N100, wherein the computing hardware system N100 includes:

[0108] Processor N110;

[0109] Memory N120, wherein executable instructions of the processor are stored;

[0110] The processor N110 is configured to perform the steps of the target vehicle tracking method by executing the executable instructions.

[0111] By employing the target vehicle tracking device provided in this application, the processor executes the target vehicle tracking method when executing the executable instructions, thereby obtaining the beneficial effects of the target vehicle tracking method described above.

[0112] In this embodiment, such as Figure 6As shown, the target vehicle tracking device further includes a data access, conversion, and storage hardware system N200, a microcontroller unit N300, and a network switching module N400. The data access, conversion, and storage hardware system N200 receives and stores location source data from relevant devices in the holographic road network via the network switching module N400. This location source data includes, for example, video data and / or radar data. The data access, conversion, and storage hardware system N200 can also decode the video data to provide it to the computing hardware system N100 for subsequent data processing operations. The computing hardware system N100, whose processor N110 can be implemented using an algorithm acceleration chip, acquires the location source data for real-time analysis, obtains the target vehicle's position coordinates and azimuth angle in real-time, and executes the various steps of the target vehicle tracking method described above. The microcontroller unit N300 can be used to control the power-on timing of various parts of the target vehicle tracking device. The network switching module N400 is used to communicate with relevant devices (video acquisition devices, radar devices, etc.) in the holographic road network, acquire positioning source data and transmit it to the data access conversion and storage hardware system N200, and communicate with the tracking resource device to send the coordination control command to it.

[0113] The target vehicle tracking device can be deployed as an edge computing device at the edge of the intersection, significantly reducing data transmission network latency and the operational burden on the road traffic management center server. Its lightweight design allows for rapid deployment, reliably and efficiently ensuring the implementation of the target vehicle tracking method. This device not only completes data access, fusion, and identification from holographic sensing devices to obtain the target vehicle's location information, but also supports the algorithm implementation of the aforementioned target vehicle tracking method, forming a stable, fast, and lightweight intersection "thinking center." The target vehicle tracking device can fully utilize data from various sensors in the holographic road network environment, improving the accuracy of target vehicle perception. The target vehicle tracking device can be a standalone hardware device or integrated into existing intersection equipment, such as traffic lights or electronic police systems.

[0114] This application also provides a computer-readable storage medium for storing a program that, when executed by a processor, implements the steps of the target vehicle tracking method. In some possible implementations, various aspects of this application can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the target vehicle tracking method section of this specification according to various exemplary embodiments of this application.

[0115] refer to Figure 7As shown, a program product 800 for implementing the above-described method according to an embodiment of this application is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of this application is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0116] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0117] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0118] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or cluster. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0119] By employing the computer-readable storage medium provided in this application, wherein the program stored therein implements the steps of the target vehicle tracking method when executed, the beneficial effects of the target vehicle tracking method described above can be obtained.

[0120] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of this application and should not be construed as limiting the specific implementation of this application to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of this application, and all such modifications or substitutions should be considered within the scope of protection of this application.

Claims

1. A target vehicle tracking method, characterized in that, Includes the following steps: When a target vehicle is detected passing through the first intersection, the travel data of the target vehicle when passing through the first intersection is obtained, and the travel data includes travel direction information; Select at least one alternative lower-level intersection corresponding to the first intersection, and obtain the intersection direction information corresponding to the travel direction information of the alternative lower-level intersection; Based on the travel direction information of the target vehicle and the intersection direction information corresponding to the travel direction information of each of the candidate lower-level intersections, the next intersection to which the target vehicle is predicted to enter is selected from the candidate lower-level intersections as the second intersection. The coordination control command is sent to the tracking resource device corresponding to the second intersection, and the coordination control command is used to instruct the tracking resource device to start executing the target vehicle tracking task.

2. The target vehicle tracking method according to claim 1, characterized in that, The travel direction information includes a first direction angle of the target vehicle's travel direction relative to a standard direction, and the intersection direction information includes a second direction angle of the first entrance lane of the candidate lower-level intersection relative to the standard direction, wherein the first entrance lane is the entrance lane of the candidate lower-level intersection corresponding to the travel direction information. Selecting the next intersection from the candidate lower-level intersections to which the predicted target vehicle will enter includes comparing the first direction angle with the second direction angle of the first entrance lane of each candidate lower-level intersection, and selecting the intersection corresponding to the second direction angle closest to the first direction angle as the next intersection from which the predicted target vehicle will enter.

3. The target vehicle tracking method according to claim 2, characterized in that, The travel data also includes the target vehicle's position coordinates and the target vehicle's speed; Sending the coordination control command to the tracking resource device corresponding to the second intersection includes the following steps: Based on the target vehicle's location coordinates and the information of the first entrance lane of the second intersection, calculate the simulated driving trajectory of the target vehicle from the target vehicle's location coordinates to the first entrance lane of the second intersection; Based on the driving distance of the simulated driving trajectory and the driving speed of the target vehicle, calculate the arrival time of the target vehicle to the first entrance lane of the second intersection; The transmission time of the coordination control command is calculated based on the arrival time and the preset flexible time. The coordinated control command is sent to the tracking resource device corresponding to the second intersection at the specified transmission time.

4. The target vehicle tracking method according to claim 3, characterized in that, When the target vehicle is detected to be passing through the first intersection, the process of acquiring the target vehicle's travel data at the first intersection includes the following steps: The target vehicle was detected entering the area of ​​the first intersection. The system acquires the location source data corresponding to the target vehicle in real time, calculates the real-time position coordinates of the target vehicle and the real-time direction angle relative to the standard direction, and projects the target vehicle onto the geographic information system map based on the calculation results. The last frame within the location area of ​​the target vehicle at the first intersection; Calculate the target vehicle's speed corresponding to the last frame, and use the target vehicle's real-time position coordinates, real-time direction angle, and target vehicle speed corresponding to the last frame as the travel data.

5. The target vehicle tracking method according to claim 2, characterized in that, Obtaining the intersection direction information corresponding to the candidate lower-level intersections and the travel direction information includes: Obtain the second direction angle of the first approach lane of the pre-stored candidate lower-level intersection; or, Obtain the position coordinates of the centerline key points of the first entrance lane of the candidate lower-level intersection, and calculate the direction angle of the line connecting the centerline key points relative to the standard direction, which is used as the second direction angle.

6. The target vehicle tracking method according to claim 2, characterized in that, Obtaining the intersection direction information corresponding to the candidate lower-level intersections and the travel direction information includes: The instantaneous direction angle of all vehicles passing through the first entrance lane of the candidate lower-level intersection within a certain time period relative to the standard direction when passing the stop line of the first entrance lane is statistically analyzed, and the second direction angle of the first entrance lane of the candidate lower-level intersection is calculated based on all the obtained instantaneous direction angles.

7. The target vehicle tracking method according to claim 1, characterized in that, Selecting the candidate lower-level intersections corresponding to the first intersection includes the following steps: Based on road segment connectivity rules and the shortest path principle, the first entrance lane of the candidate lower-level intersection is searched on the geographic information system map, the candidate lower-level intersection corresponding to the first intersection is selected, and the first entrance lane of the candidate lower-level intersection corresponding to the travel direction information is determined. or, Based on the preset correspondence between each intersection and the candidate lower-level intersection, the candidate lower-level intersection corresponding to the first intersection is obtained, and the first entrance lane corresponding to the candidate lower-level intersection and the travel direction information is determined.

8. A target vehicle tracking system, characterized in that, The system, applied to the target vehicle tracking method according to any one of claims 1 to 7, comprises: The first information acquisition module is used to acquire the travel data of the target vehicle when it passes through the first intersection, and the travel data includes travel direction information. The second information acquisition module is used to select at least one candidate lower-level intersection corresponding to the first intersection, and acquire the intersection direction information corresponding to the candidate lower-level intersection and the travel direction information. The intersection prediction module is used to select the next intersection from the candidate lower-level intersections as the second intersection, based on the target vehicle's travel direction information and the intersection direction information corresponding to the travel direction information of each candidate lower-level intersection. The instruction sending module is used to send coordination control instructions to the tracking resource device corresponding to the second intersection. The coordination control instructions are used to instruct the tracking resource device to start executing the target vehicle tracking task.

9. A target vehicle tracking device, characterized in that, Includes a computing hardware system, the computing hardware system comprising: processor; A memory in which executable instructions of the processor are stored; The processor is configured to perform the steps of the target vehicle tracking method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the target vehicle tracking method according to any one of claims 1 to 7.

Images