Target vehicle tracking method and device, storage medium and product

Abstract

The embodiment of the invention provides a target vehicle tracking method and device, a storage medium and a product. The method comprises the steps of obtaining advancing data of a target vehicle and determining that the target vehicle drives into a current lane associated with an intersection to be passed; traversing at least one alternative lower-level exit lane corresponding to the intersection to be passed, and determining road direction information of each alternative lower-level exit lane; according to the advancing direction information of the target vehicle, the obtained lane turning information of the current lane and the road direction information of all the alternative lower-level exit lanes, selecting one alternative lower-level exit lane from all the alternative lower-level exit lanes to serve as a target exit lane where the predicted target vehicle enters after driving out of the current lane; and determining a predicted driving track of the target vehicle according to the position information of the target vehicle and the target exit lane, so as to track the target vehicle based on the predicted driving track. By using the method, the future driving path of the vehicle can be accurately pre-judged, and continuous and seamless tracking of the target vehicle is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle tracking, and in particular to a target vehicle tracking method, device, storage medium and product. Background Art

[0002] In the enforcement practices of public security traffic police, real-time tracking of specific target vehicles is crucial for maintaining public safety and ensuring traffic order. Traditional tracking methods based on video image recognition, limited by the layout and coverage of monitoring equipment, suffer from significant passivity and response delays, making it difficult to effectively address the rapid escape of target vehicles. Therefore, research on target vehicle trajectory tracking and prediction technology is essential to address complex and changing traffic environments and improve the effectiveness of public security traffic police enforcement. Summary of the Invention

[0003] The present invention provides a target vehicle tracking method, device, storage medium and product, which can accurately predict the future driving path of the vehicle and ensure continuous and seamless tracking of the target vehicle.

[0004] In a first aspect, an embodiment of the present invention provides a target vehicle tracking method, comprising:

[0005] Acquiring travel data of the target vehicle and determining that the target vehicle has entered a current lane associated with the intersection to be passed, the travel data including location information and travel direction information of the target vehicle;

[0006] Traversing at least one candidate lower-level exit road corresponding to the intersection to be passed, and determining road direction information of each candidate lower-level exit road;

[0007] selecting, based on the target vehicle's traveling direction information, the acquired lane turning information of the current lane, and the road direction information of each of the candidate lower-level exit roads, an alternative lower-level exit road as a target exit road predicted to be entered by the target vehicle after exiting the current lane;

[0008] The predicted driving trajectory of the target vehicle is determined according to the position information of the target vehicle and the target exit road, so as to track the target vehicle based on the predicted driving trajectory.

[0009] In a second aspect, an embodiment of the present invention provides an electronic device, including:

[0010] at least one processor; and

[0011] a memory communicatively connected to the at least one processor; wherein,

[0012] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the target vehicle tracking method according to any embodiment of the present invention.

[0013] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target vehicle tracking method as described in any embodiment of the present invention when executed.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the target vehicle tracking method as described in any embodiment of the present invention.

[0015] The embodiment of the present invention provides a target vehicle tracking method, device, storage medium and product, the method comprising: first, obtaining the target vehicle's travel data and determining the current lane associated with the intersection to be passed, the travel data including the target vehicle's position information and travel direction information; second, traversing at least one alternative lower-level exit road corresponding to the intersection to be passed and determining the road direction information of each alternative lower-level exit road; then, based on the target vehicle's travel direction information, the obtained lane turning information of the current lane and the road direction information of each alternative lower-level exit road, selecting an alternative lower-level exit road from each of the alternative lower-level exit roads as the target exit road predicted to be entered after the target vehicle exits the current lane; finally, determining the target vehicle's predicted driving trajectory based on the target vehicle's position information and the target exit road, so as to track the target vehicle based on the predicted driving trajectory. The above technical solution predicts the exit road that the target lane will enter based on the target vehicle's travel data and the attribute information of the current lane, combined with the attribute information of the alternative lower-level lane intersection, and thus predicts the target vehicle's future driving path. It improves the intelligent prediction capability of target vehicle tracking services, ensuring that the vehicle's location information and direction of travel can be quickly captured when the vehicle is operating on the road network, and based on the road topology, accurately predicts the vehicle's future driving path to ensure continuous and seamless tracking of the target vehicle.

[0016] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of a target vehicle tracking method provided in Example 1 of the present invention;

[0019] Figure 2 A schematic flow chart of another target vehicle tracking method provided in the second embodiment of the present invention;

[0020] Figure 3 A schematic diagram of an exit channel direction angle calibration provided in the second embodiment of the present invention;

[0021] Figure 4 A schematic diagram of selecting a target exit path in an application scenario provided in the second embodiment of the present invention;

[0022] Figure 5 This is a diagram showing the predicted trajectory of a target vehicle in an application scenario provided by the second embodiment of the present invention;

[0023] Figure 6 A schematic structural diagram of a target vehicle tracking device provided in Embodiment 3 of the present invention;

[0024] Figure 7 This is a structural diagram of an electronic device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "original", "target", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices.

[0027] Example 1

[0028] Figure 1 This is a flow chart of a target vehicle tracking method provided by the first embodiment of the present invention. This method is applicable to the case of tracking a target vehicle. This method can be executed by a target vehicle tracking device. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the target vehicle tracking method provided in this embodiment may specifically include the following steps:

[0029] S101. Acquire the travel data of a target vehicle and determine that the target vehicle enters a current lane associated with an intersection to be passed.

[0030] The travel data includes the location information and travel direction information of the target vehicle.

[0031] Considering that traditional tracking methods based on video image recognition are limited by the layout and coverage of monitoring equipment, have significant passivity and response delays, and are difficult to effectively deal with the rapid escape of the target vehicle, this embodiment predicts the target vehicle's driving trajectory based on the current driving conditions of the target vehicle and the attribute information of the road, so that the target vehicle can be tracked in a timely manner based on the predicted driving trajectory.

[0032] In this embodiment, the target vehicle can be specifically understood as the vehicle being tracked, the intersection to be passed can be specifically understood as the intersection that the target vehicle needs to pass after traveling in the current lane. The intersection to be passed can be a holographic intersection, and the current lane can be specifically understood as the lane in which the target vehicle is currently located. In order to predict the target vehicle's driving trajectory, it is necessary to first obtain relevant driving data of the target vehicle at the current moment, which is recorded as the target vehicle's travel data in the current lane. The target vehicle's travel data in the current lane can include the target vehicle's position information and travel direction information.

[0033] It should be noted that the target vehicle tracking method can be implemented based on a holographic road network. A holographic road network uses a high-precision digital map as a unified coordinate system. It integrates structured data captured by existing road sensors, such as video, microwave radar, and lidar, into a unified coordinate system, creating a road environment that fully captures the positions, speeds, and trajectories of all vehicles, non-motorized vehicles, and pedestrians in the network. For example, intersections in the holographic road network may be equipped with: traffic lights and signal lights; video capture equipment to capture vehicle attributes, such as license plates, models, and colors; radar equipment to collect vehicle latitude and longitude coordinates, speed, and heading angle; and edge computing equipment to capture video data from the video capture equipment and radar data from the radar equipment and execute the steps of the target vehicle tracking method of the present invention. This allows processing of sensor data directly on the roadside, without requiring a central server, reducing data communication latency and the workload of the central server. However, the present invention is not limited to this. In another embodiment, the target vehicle tracking method can also be executed on a central server.

[0034] Continuing with the above description, in this embodiment, a vehicle fusion positioning algorithm can be used to obtain the real-time positioning position of the target vehicle based on the video data and / or radar data related to the target vehicle, as the target vehicle's location information. For example, the target vehicle's location information can be represented by the target vehicle's latitude and longitude coordinates. Simultaneously, information representing the target vehicle's driving direction trend can also be obtained, recorded as travel direction information. In this embodiment, when the target vehicle enters the associated lane of the intersection to be passed, the target vehicle's location information and travel direction information are calculated in real time.

[0035] In this embodiment, the target vehicle's position and direction of travel are calculated in real time. The execution entity obtains the position and direction of travel of the target vehicle in the first frame of the target vehicle's entry into the lane associated with the intersection to be traversed. High-precision maps can provide lane-level data, such as the identification and location of lane edges and lane identification numbers. If the target vehicle's position matches a lane area provided by the high-precision map, that lane is determined to be the lane the target vehicle entered, and this is recorded as the target vehicle entering the current lane associated with the intersection to be traversed.

[0036] It should be noted that after the target vehicle enters the associated lane of the intersection to be passed, the target vehicle's travel data will be obtained in real time, and then the target vehicle's trajectory will be predicted in real time based on the travel data. This can effectively cover the situation where the target vehicle changes lanes. When the target vehicle changes lanes (such as the target vehicle changes from the straight lane to the left lane), the target vehicle tracking method provided by this embodiment can effectively capture this situation, thereby performing real-time trajectory prediction and tracking. After the target vehicle's travel data is obtained in real time, the target vehicle's travel data can also be mapped to a Geographic Information System (GIS) map to achieve real-time visualization of the target vehicle's location information and travel direction information.

[0037] S102: traverse at least one candidate lower-level exit road corresponding to the intersection to be passed, and determine road direction information of each candidate lower-level exit road.

[0038] In this embodiment, the candidate lower-level exit road can be understood as a road that is connected to the intersection to be entered and that the target vehicle can choose to enter after exiting the current lane. The road direction information of the candidate lower-level exit road can be the angle between the centerline of the road and a certain direction, or the degree of deviation from the certain direction.

[0039] In this embodiment, a pre-built road network topology structure is constructed. This structure includes information about roads and intersections, as well as the connections between roads and adjacent roads. Based on the road segment connectivity rules, this structure is traversed to obtain exits connected to the intersection to be traversed in directions other than the current lane, which are used as candidate lower-level exits corresponding to the intersection to be traversed. Alternatively, based on the preset correspondence between lanes and candidate lower-level exits, the candidate lower-level exits corresponding to the intersection to be traversed are traversed.

[0040] For example, if the intersection to be entered is an intersection, the candidate lower-level exits may be the other three downstream lanes associated with the intersection, excluding the current lane. If the intersection to be entered is a T-junction, the candidate lower-level exits may be the other two downstream lanes associated with the T-junction, excluding the current lane.

[0041] S103. Selecting an alternative lower-level exit road from the alternative lower-level exit roads as a target exit road predicted to be entered by the target vehicle after exiting the current lane based on the target vehicle's traveling direction information, the acquired lane turning information of the current lane, and the road direction information of the alternative lower-level exit roads.

[0042] The travel direction information includes the direction angle of the target vehicle's travel direction relative to the preset standard direction, the road direction information includes the road direction angle of the candidate lower-level exit road relative to the preset standard direction, and the lane turning information of the current lane includes the turning direction of the current lane. The target exit road can be specifically understood as the exit road that the target vehicle is predicted to enter in the future. It should be noted that in this embodiment, the preset standard direction used is a unified standard direction.

[0043] After determining which lane the target vehicle has entered, the current lane's turning direction can be obtained from the road network topology, as the road network topology includes various types of road information. This can be considered the subsequent target vehicle's turning direction. Based on the current lane's turning direction, the angle corresponding to the current lane's turning direction can be determined. By combining the target vehicle's travel direction information with the angle corresponding to the current lane's turning direction, the target vehicle's future turning angle can be predicted. The target vehicle's turning angle is then compared with the road angles of each candidate lower-level exit road. The candidate lower-level exit road corresponding to the road angle closest to the turning angle is selected as the predicted target exit road after the target vehicle exits the current lane.

[0044] S104: Determine a predicted driving trajectory of the target vehicle according to the location information of the target vehicle and the target exit lane, so as to track the target vehicle based on the predicted driving trajectory.

[0045] In this embodiment, once the target exit is determined, the target vehicle's most recent location can be plotted on a GIS map, thereby obtaining the target vehicle's latest location information. Based on the principle of road segment connectivity, the shortest path from the target vehicle's most recent location to the target exit is predicted and a simulated driving trajectory is generated, recorded as the target vehicle's predicted driving trajectory. After the target vehicle's driving trajectory is predicted, the target vehicle can be tracked based on the predicted driving trajectory.

[0046] It should be noted that when the target vehicle enters the current lane, steps S101 to S104 will be executed. During the target vehicle's travel, steps S101 to S104 will also be executed at preset time intervals. It can be considered that this process is continuously executed. When the vehicle enters the current lane, the judgment of the exit lane direction and the simulation of the vehicle trajectory will begin. When driving to the intersection to be passed, if the target vehicle changes lanes, the corresponding target vehicle's direction of travel and turning direction can also be determined in real time, thereby determining the corresponding exit lane direction. In addition, when the target vehicle enters the target exit lane, step S101 will be restarted to prejudge the target vehicle's travel trajectory again. In the present embodiment, the target vehicle tracking method is a step that is executed in a loop. When the target vehicle reaches the target exit lane, the target exit lane serves as the current lane of the next cycle, and steps S101 to S104 of the above-mentioned target vehicle tracking method are re-executed to achieve continuous tracking of the target vehicle.

[0047] This technical solution uses the target vehicle's travel data and the attributes of the current lane, combined with the attributes of potential lower-level lane entrances, to predict the target vehicle's exit lane and, in turn, the target vehicle's future path. This enhances the intelligent prediction capabilities of the target vehicle tracking service, ensuring that the vehicle's location and direction are quickly captured while operating on the road network. Based on the road topology, the vehicle's future path is accurately predicted, ensuring continuous and seamless tracking of the target vehicle.

[0048] Example 2

[0049] Figure 2 A flow chart of another target vehicle tracking method provided in Example 2 of the present invention. This embodiment is a further optimization of the above embodiment. In this embodiment, "obtaining the travel data of the target vehicle and determining that the target vehicle enters the current lane associated with the intersection to be passed" is further limited and optimized, and "traversing at least one alternative lower-level exit road corresponding to the intersection to be passed" is further limited and optimized, and "determining the road direction information of each of the alternative lower-level exit roads" is further limited and optimized, and "selecting an alternative lower-level exit road from each of the alternative lower-level exit roads as the target exit road predicted to be entered after the target vehicle exits the current lane based on the travel direction information of the target vehicle, the obtained lane turning information of the current lane, and the road direction information of each of the alternative lower-level exit roads" is further limited and optimized.

[0050] like Figure 2 As shown, this embodiment 2 provides a target vehicle tracking method, which specifically includes the following steps:

[0051] S201 : Acquire positioning source data corresponding to a target vehicle in real time, and calculate the real-time position information of the target vehicle and the moving direction angle of the target vehicle relative to the standard direction.

[0052] Among them, the traveling direction information is the information that characterizes the driving direction trend of the target vehicle. For example, the traveling direction information can be expressed as the angle between the traveling direction of the target vehicle and a certain direction, or the degree of deviation relative to a certain direction. In this embodiment, the traveling direction information is expressed as the traveling direction angle of the traveling direction of the target vehicle relative to the preset standard direction. The preset standard direction can be selected as needed, for example, a specific coordinate axis direction of a certain coordinate system, such as selecting the north direction as the preset standard direction. The traveling direction angle is the horizontal angle between the north direction line of the target vehicle's location and the traveling direction line of the target vehicle in a clockwise direction.

[0053] In this embodiment, the target vehicle's positioning source data can include multi-sensor data such as video data and / or radar data related to the target vehicle. Calculation of the target vehicle's real-time position information and its real-time azimuth relative to a preset standard direction can be achieved using existing video / radar data fusion positioning algorithms or algorithms that rely solely on video data or radar data for positioning. By fully integrating the diverse sensor data in the holographic road network environment and leveraging the unique advantages of each sensor, high-precision, all-round perception of the target vehicle is achieved.

[0054] Specifically, when a target vehicle enters the lane associated with the intersection it is about to pass through, a holographic algorithm is used to calculate the target vehicle's latitude and longitude coordinates and heading angle in real time. This data is then mapped onto a GIS map, enabling real-time visualization of the target vehicle's location and heading information.

[0055] S202: Use the target vehicle's position information and travel direction angle as travel data.

[0056] S203: Match the location information of the target vehicle with the geographic information system map to determine that the target vehicle has entered a current lane associated with the intersection to be passed.

[0057] In this embodiment, when a target vehicle enters a lane associated with the intersection to be traversed, its position and heading angle are calculated in real time. High-precision maps provide lane-level data, such as the location and positioning of lane edges and lane identification numbers. If the target vehicle's position matches a lane area provided by the high-precision map, that lane is identified as the lane the target vehicle entered, and this is recorded as the target vehicle entering the current lane associated with the intersection to be traversed.

[0058] S204: Based on the road segment connectivity rule, traverse the pre-built road network topology structure to obtain exit roads in directions other than the current lane connected to the intersection to be passed, as candidate lower-level exit roads corresponding to the intersection to be passed.

[0059] In this embodiment, after obtaining the road network topology structure, since the road network topology structure contains the connection relationship between roads and adjacent roads, such as the identification numbers of the preceding road / intersection and the subsequent road / intersection, the type of connection point, etc., according to the road segment connectivity rules, the exit roads in other directions of the intersection to be passed are traversed, and these exit roads are used as alternative lower-level exit roads corresponding to the intersection to be passed.

[0060] It should be noted that another implementation method for determining the candidate lower-level exit corresponding to the intersection to be traversed can be to obtain the candidate lower-level exit corresponding to the intersection to be traversed based on a preset correspondence between each intersection and the candidate lower-level exit. For example, a correspondence between any intersection in the lanes associated with each intersection and the candidate lower-level exit in other directions can be pre-set, or the correspondence between each intersection and the candidate lower-level exit can be pre-learned using a deep learning model.

[0061] S205 , obtaining position information of the centerline key points of the candidate lower-level exit road, calculating the direction angle of the line connecting the centerline key points relative to the preset standard direction, and recording it as the road direction angle of the candidate lower-level exit road.

[0062] In this embodiment, the road direction information includes the road direction angle of the candidate lower-level exit relative to a preset standard direction. Obtaining the position information of the centerline key points of the candidate lower-level exit can determine the direction of the centerline of the candidate lower-level exit. The road direction angle of the candidate lower-level exit can be calibrated using high-precision map data. The road direction angle is the angle between the north direction line at a certain point on each candidate lower-level exit and the centerline of the candidate lower-level exit in a clockwise direction. Figure 3 This is a schematic diagram of an exit direction angle calibration provided by the second embodiment of the present invention, as shown in FIG. Figure 3 As shown, taking the exit road of the east entrance as an example, the direction angle of the exit road is obtained based on the center line of the exit road provided by the high-precision map data.

[0063] In this embodiment, another implementation method for determining the road direction information for each candidate lower-level exit may be to obtain a pre-stored direction angle of the candidate lower-level exit and record it as the road direction angle of the candidate lower-level exit. For example, lane markings and lane direction angles for each lane are pre-collected and stored in the backend. Once each candidate lower-level exit is determined, the corresponding lane direction angle can be obtained based on the lane marking of each candidate lower-level exit as the road direction information for that candidate lower-level exit.

[0064] What you need to know is that the downstream roads in the road network topology have no concept of left and right turns, only angles. For example, road A is associated with four roads B, C, D, and E. These four roads have no concept of direction. They only know the longitude and latitude of B, C, D, and E, the angle when A looks at B, the angle when A looks at C, and so on. In theory, if they are all straight lines, they can be calculated directly based on the longitude and latitude. The calibration angle is to prevent some curved lanes.

[0065] S206 : Determine the turning direction angle of the target vehicle according to the traveling direction angle of the target vehicle and the turning direction of the current lane.

[0066] Among them, the lane turning information of the current lane includes the turning direction of the current lane. In this embodiment, a road network topology structure is pre-constructed, and the turning direction of the current lane is obtained from the pre-constructed road network topology structure as the lane turning information of the current lane. The road network topology structure contains information about roads and intersections, such as the length of the road, the identification number, and the identification number of the intersection to which it belongs; the connection relationship between the road and the adjacent roads, including the identification number of the preceding road / intersection and the subsequent road / intersection, the type of connection point, etc.; additional information such as the type of road, speed limit, and plan view; lane information, including lane offset, lane cross-section, etc., and the geometric shape of the road; and related features that affect the logic of the road network, such as lanes and signs; the information contained in the road network topology structure includes but is not limited to the information listed above. The road network topology structure can be obtained based on the analysis of drone aerial photos and map vector files through artificial intelligence algorithms. The map vector file can be an opendrive file, etc. The opendrive file format is a file format used to describe static road traffic networks and is used to provide standardized road network descriptions.

[0067] Specifically, after determining which lane the target vehicle has entered, the road network topology includes various road type information. This allows the target vehicle to obtain the current lane's turning direction from the road network topology and use this as the lane turning information for the current lane. For example, the current vehicle's turning direction could be left, going straight, right, a combination of left and straight, or a combination of right and straight, effectively knowing the target vehicle's future direction.

[0068] Continuing with the above description, one implementation method for determining the turning direction angle of the target vehicle can be described as: based on the turning direction of the current lane, the angle corresponding to the turning direction of the current lane can be determined, and the moving direction angle of the target vehicle is added to the angle corresponding to the turning direction of the current lane, and the result of the addition is used as the turning direction angle of the target vehicle.

[0069] As a specific implementation method, the step of determining the turning direction angle of the target vehicle according to the traveling direction angle of the target vehicle and the turning direction of the current lane can be optimized, including:

[0070] a1) Determine the angle corresponding to the turning direction of the current lane according to the turning direction of the current lane.

[0071] In this embodiment, the turning directions of different lanes are pre-set with corresponding angles. Once the turning direction of the current lane is known, the angle corresponding to the turning direction of the current lane can be determined. For example, the angle corresponding to straight driving can be set to 0 degrees; the angle corresponding to left turning can be set to -90 degrees; and the angle corresponding to right turning can be set to 90 degrees. For roads with at least two turning directions, the angle corresponding to the turning direction with the largest proportion in the traffic flow data within the historical time period is used as the turning angle of the lane. Once the turning direction of the current lane is known, the angle corresponding to the turning direction of the current lane can be obtained based on the above-mentioned preset correspondence between the turning direction and the angle. For example, assuming that the current lane is a mixed lane that includes left turns and straight driving, the turning direction with the larger turning ratio value can be used as the turning direction of the lane based on the historical traffic flow data of the day.

[0072] Furthermore, the step of determining the angle corresponding to the turning direction of the current lane according to the turning direction of the current lane may be optimized, including:

[0073] If the turning direction of the current lane is straight ahead, the angle corresponding to the turning direction of the current lane is 0 degrees; if the turning direction of the current lane is left turn, the angle corresponding to the turning direction of the current lane is -90 degrees; if the turning direction of the current lane is right turn, the angle corresponding to the turning direction of the current lane is 90 degrees; if the turning direction of the current lane includes at least two directions, the angle corresponding to the turning direction with the largest proportion in the traffic driving data during the historical time period is used as the angle corresponding to the turning direction of the current lane.

[0074] The above technical solution specifies the steps of how to determine the angle corresponding to the turning direction of the current lane, and provides basic data for the subsequent calculation of the turning direction angle of the target vehicle based on the target vehicle's traveling direction angle and the turning direction angle of the current lane.

[0075] b1) adding the target vehicle's heading angle to the angle corresponding to the current lane's turning direction, and using the sum as the target vehicle's turning direction angle.

[0076] In this embodiment, given the target vehicle's heading angle and the angle corresponding to the turning direction of the current lane, the theoretical angle at which the target vehicle would enter the new lane after passing through the intersection can be calculated and recorded as the turning direction angle. Specifically, the target vehicle's heading angle and the angle corresponding to the turning direction of the current lane are added together to form a turning direction angle. It should be noted that, assuming the turning direction angle is represented by γ, if γ<0°, γ+360° is assigned to γ; if γ>360°, γ is assigned to γ-360°.

[0077] The above technical solution concretizes the steps of determining the turning direction angle of the target vehicle. First, the angle corresponding to the turning direction of the current lane is determined, and then this angle is added to the moving direction angle of the target vehicle to obtain the target vehicle's predicted future turning direction angle, which provides a basis for subsequent screening of the exit lanes that the target vehicle may enter.

[0078] S207 , selecting an alternative lower-level exit road from the alternative lower-level exit roads according to the turning direction angle of the target vehicle and the road direction angles of the alternative lower-level exit roads as the target exit road that the target vehicle is predicted to enter after exiting the current lane.

[0079] In this embodiment, the turning direction angle of the target vehicle is compared with the road direction angles of each alternative lower-level exit road, and the exit road corresponding to the road direction angle closest to the turning direction angle of the target vehicle is selected from each alternative lower-level exit road as the target exit road predicted to be entered after the target vehicle exits the current lane, that is, the exit road that the target vehicle is most likely to enter after exiting the current lane.

[0080] As a specific implementation method, based on the steering direction angle of the target vehicle and the road direction angles of each candidate lower-level exit road, selecting the exit road predicted to be entered by the target vehicle from each candidate lower-level exit road includes:

[0081] a2) comparing the steering direction angle of the target vehicle with the road direction angles of each candidate lower-level exit road.

[0082] In this embodiment, the steering direction angle of the target vehicle and the road direction angles of each candidate lower-level exit road are subtracted and the absolute value of the subtraction result is taken.

[0083] b2) selecting an exit lane corresponding to a road direction angle closest to the steering direction angle as the target exit lane for the target vehicle to enter after exiting the current lane.

[0084] After calculating the difference between the target vehicle's steering direction angle and the road direction angles of each alternative lower-level exit road and taking the absolute value of the difference result, it can be considered that the road direction angle of the exit road corresponding to the minimum of these absolute values ​​is closest to the steering direction angle of the target vehicle, and thus the exit road corresponding to the road direction angle closest to the steering direction angle is used as the target exit road predicted to be entered after the target vehicle exits the current lane.

[0085] The above technical solution specifies the steps of how to select the target exit road that the target vehicle is predicted to enter after exiting the current lane from each alternative lower-level exit road. By comparing the steering direction angle of the target vehicle with the road direction angles of each alternative lower-level exit road, the exit road corresponding to the road direction angle closest to the steering direction angle is used as the target exit road that the target vehicle is predicted to enter after exiting the current lane. This enables the active prediction of the vehicle's direction of travel and achieves a forward-looking improvement in the time dimension.

[0086] For example, in order to more clearly describe how to determine the target exit lane in the target vehicle tracking method provided by the embodiment of the present invention, how to select the target exit lane in a certain application scenario is described as an example. Figure 4 This is a schematic diagram of selecting a target exit path in an application scenario provided by the second embodiment of the present invention. Figure 4 As shown, the target vehicle is currently in lane A. The platform obtains the latitude and longitude coordinates and the travel direction angle α of the first frame when the vehicle enters the lane associated with holographic intersection 1, where α = 303.6°. Because high-precision maps can provide lane-level data, including the identification and positioning of road lane edges, the latitude and longitude information of the target vehicle matches the area within lane A, which is determined to be the lane the vehicle entered. Based on the road network topology, the turning direction of this lane can be obtained as a left turn, corresponding to an angle of 90°.

[0087] Following the above description, obtain the pre-built road network topology structure, and according to the principle of road segment connectivity, traverse the exit roads in other directions in the holographic intersection 1, namely B1, B2, and B3, where B1 corresponds to the east exit road, B2 corresponds to the west exit road, and B3 corresponds to the north exit road, generate a set of alternative lower-level exit roads, and then call the direction angles β1, β2, and β3 corresponding to these alternative lower-level exit roads, where β1 = 44.7°, β2 = 226.6°, and β3 = 306.1°. Add the heading angle of the target vehicle and the angle corresponding to the turning direction of the entering lane to obtain the steering direction angle: γ = 303.6° - 90° = 213.6°. Combine the steering direction angle γ and the road direction angle β iPerform difference calculation and take the absolute value Δ: Δ1 = |γ-β1| = 168.9°, Δ2 = |γ-β2| = 13°, Δ3 = |γ-β1| = 92.5°, the minimum value is Δ2, and the corresponding exit lane is B2, so B2 is the target exit lane that the target vehicle is about to enter.

[0088] S208. Determine a predicted driving trajectory of the target vehicle according to the location information of the target vehicle and the target exit lane, so as to track the target vehicle based on the predicted driving trajectory.

[0089] In this embodiment, the edge computing equipment deployed at the holographic intersection can be used to analyze the video stream of the electronic police checkpoint in real time, accurately identify the license plate and model of the target vehicle, and calculate the position of the target vehicle in the current video. Subsequently, with the help of a set algorithm, the building calibration and vehicle position information in the video are combined to convert them into the real-time latitude and longitude coordinates of the target vehicle. In addition, dynamic layer fusion technology can be used to integrate these real-time data into a high-precision map to intuitively display the dynamics of the target vehicle. Furthermore, based on the latitude and longitude, azimuth and GIS intersection details of the target vehicle, the future driving path of the vehicle can be intelligently predicted, and the map trajectory of the target vehicle that is about to travel can be dynamically depicted to achieve full-area tracking of the target vehicle.

[0090] In order to more clearly illustrate the effect achieved by the target vehicle tracking method provided by the embodiment of the present invention, the tracking of a target vehicle in a certain application scenario is described as an example. Figure 5 This is a prediction effect diagram of the target vehicle tracking trajectory in an application scenario provided by the second embodiment of the present invention, such as Figure 5 As shown, it can be seen that the turning direction of the target vehicle's current lane and the target vehicle's heading angle can be used to predict that the target vehicle will enter the left lane in the future. Based on the target vehicle's position information and the future left lane, the target vehicle's driving trajectory can be predicted, represented by the "orange" route in the figure. Based on this predicted driving trajectory, the target vehicle can be tracked. The target vehicle's own information such as license plate number, color, vehicle model, speed, current intersection information, predicted intersection information, and the target vehicle's predicted driving trajectory can all be integrated into a high-precision map using dynamic layer fusion technology, and this real-time data can be intuitively displayed to the user. There are no specific restrictions on the specific content displayed to the user here, and it can be set according to actual needs. No specific display is given in the figure.

[0091] The above technical solution first determines the position information and travel direction angle of the target vehicle by obtaining the positioning source data corresponding to the target vehicle, and matches the position information of the target vehicle with the high-precision map to determine the current lane entered by the target vehicle; secondly, obtaining the turning direction of the current lane from the road network topology is equivalent to knowing the subsequent turning direction of the target vehicle; then, based on the road section connectivity rule, the alternative lower-level exit roads corresponding to the intersection to be passed and the road direction angles of each alternative lower-level exit road are obtained from the road network topology; then, based on the subsequent turning direction of the target vehicle and the travel direction angle of the target vehicle, the turning direction angle of the target vehicle is determined, and the exit road corresponding to the road direction angle closest to the turning direction angle is selected as the exit road predicted to be entered by the target vehicle; finally, based on the position information of the target vehicle and the exit road predicted to be entered by the target vehicle, the future driving trajectory of the target vehicle is predicted. It is possible to quickly capture the target vehicle's location information and travel direction angle, and then combine the road topology structure to know the current road's turning direction and the road direction angle of the alternative lower-level exit road, so as to accurately predict the exit road that the target vehicle will enter in the future, thereby ensuring accurate prediction of the vehicle's future driving path and ensuring continuous and seamless tracking of the target vehicle.

[0092] Example 3

[0093] Figure 6 This is a schematic diagram of the structure of a target vehicle tracking device provided by the third embodiment of the present invention. The device is applicable to the case of tracking a target vehicle. The target vehicle tracking device can be configured in an electronic device, such as Figure 6 As shown, the device includes: a data acquisition module 31, an alternative determination module 32, an exit path determination module 33 and a trajectory prediction module 34; wherein,

[0094] A data acquisition module 31 is used to acquire the target vehicle's travel data and determine that the target vehicle has entered a current lane associated with the intersection to be passed, wherein the travel data includes the target vehicle's location information and travel direction information;

[0095] An alternative determination module 32 is configured to traverse at least one alternative lower-level exit road corresponding to a road intersection to be passed through and determine road direction information of each alternative lower-level exit road;

[0096] an exit lane determining module 33 for selecting, based on the target vehicle's traveling direction information, the acquired lane turning information of the current lane, and the road direction information of each candidate lower-level exit lane, a candidate lower-level exit lane as a target exit lane predicted to be entered by the target vehicle after exiting the current lane;

[0097] The trajectory prediction module 34 is used to determine the predicted driving trajectory of the target vehicle according to the position information of the target vehicle and the target exit lane, so as to track the target vehicle based on the predicted driving trajectory.

[0098] This technical solution uses the target vehicle's travel data and the attributes of the current lane, combined with the attributes of potential lower-level lane entrances, to predict the target vehicle's exit lane and, in turn, the target vehicle's future path. This enhances the intelligent prediction capabilities of the target vehicle tracking service, ensuring that the vehicle's location and direction are quickly captured while operating on the road network. Based on the road topology, the vehicle's future path is accurately predicted, ensuring continuous and seamless tracking of the target vehicle.

[0099] Optionally, the traveling direction information includes a traveling direction angle of the target vehicle relative to a preset standard direction, the road direction information includes a road direction angle of the alternative lower-level exit road relative to the standard direction, and the lane turning information of the current lane includes a turning direction of the current lane;

[0100] Optionally, the data acquisition module 31 includes:

[0101] a steering direction angle determination unit, configured to determine a steering direction angle of the target vehicle based on the traveling direction angle of the target vehicle and the steering direction of the current lane;

[0102] The exit lane determining unit is used to select an alternative lower-level exit lane from each alternative lower-level exit lane as the target exit lane that the target vehicle is predicted to enter after exiting the current lane based on the steering direction angle of the target vehicle and the road direction angles of each alternative lower-level exit lane.

[0103] Optionally, the exit channel determination unit is specifically configured to:

[0104] Comparing the steering direction angle of the target vehicle with the road direction angles of each alternative lower-level exit road;

[0105] The alternative lower-level exit lane corresponding to the road direction angle closest to the steering direction angle is selected as the target exit lane that the target vehicle is predicted to enter after exiting the current lane.

[0106] Optionally, the steering direction angle determination unit is specifically configured to:

[0107] According to the turning direction of the current lane, determine the angle corresponding to the turning direction of the current lane;

[0108] The target vehicle's heading angle is added to the angle corresponding to the current lane's turning direction, and the result of the addition is used as the target vehicle's turning direction angle.

[0109] Optionally, the steering direction angle determination unit is configured to perform the step of determining an angle corresponding to the steering direction of the current lane according to the steering direction of the current lane, including:

[0110] If the turning direction of the current lane is straight ahead, the angle corresponding to the turning direction of the current lane is 0 degrees;

[0111] If the turning direction of the current lane is left, the angle corresponding to the turning direction of the current lane is -90 degrees;

[0112] If the turning direction of the current lane is right turn, the angle corresponding to the turning direction of the current lane is 90 degrees;

[0113] If the turning direction of the current lane includes at least two directions, the angle corresponding to the turning direction with the largest proportion in the traffic flow driving data within the historical time period is used as the angle corresponding to the turning direction of the current lane.

[0114] Optionally, the data acquisition module 31 is specifically configured to:

[0115] Obtain the positioning source data corresponding to the target vehicle in real time, calculate the real-time position information of the target vehicle and the moving direction angle of the target vehicle relative to the preset standard direction;

[0116] The position information and the traveling direction angle of the target vehicle are used as the traveling data;

[0117] The target vehicle's location information is matched with the geographic information system map to determine the current lane associated with the intersection to be passed by the target vehicle.

[0118] Optionally, the alternative determination module 32 includes an alternative acquisition unit, specifically configured to:

[0119] Based on the road segment connectivity rules, traverse the pre-built road network topology structure to obtain the exit roads connected to the intersection to be passed in directions other than the current lane, as the alternative lower-level exit roads corresponding to the intersection to be passed; or,

[0120] According to the preset correspondence between each lane and the alternative lower-level exit road, the alternative lower-level exit road corresponding to the intersection to be passed is obtained.

[0121] Optionally, the alternative determination module 32 includes a direction determination unit, specifically configured to:

[0122] Obtain the direction angle of the pre-stored candidate lower-level exit road, and record it as the road direction angle of the candidate lower-level exit road; or,

[0123] The position information of the centerline key points of the alternative lower-level exit road is obtained, and the direction angle of the line connecting the centerline key points relative to the preset standard direction is calculated, and recorded as the road direction angle of the alternative lower-level exit road.

[0124] The target vehicle tracking device provided by the embodiment of the present invention can execute the target vehicle tracking method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0125] Example 4

[0126] Figure 7 A schematic diagram of the structure of an electronic device provided for embodiment four of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0127] like Figure 7 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., which is communicatively connected to the at least one processor 41. The memory stores a computer program that can be executed by the at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. Various programs and data required for the operation of the electronic device 40 can also be stored in the RAM 43. The processor 41, ROM 42, and RAM 43 are connected to each other via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0128] Multiple components in the electronic device 40 are connected to the I / O interface 45, including an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0129] The processor 41 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors for running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the target vehicle tracking method.

[0130] In some embodiments, the target vehicle tracking method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the target vehicle tracking method described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to perform the target vehicle tracking method in any other appropriate manner (e.g., by means of firmware).

[0131] The electronic device 40 can be deployed as an edge computing device at the edge of the intersection, which greatly reduces the data transmission network delay and the operating burden of the road traffic management center server. In addition, the device is lightweight and can be quickly deployed, which reliably and efficiently guarantees the implementation of the target vehicle tracking method. This electronic device can not only complete the data access, fusion and identification of the holographic sensing device and obtain the positioning information of the target vehicle, but also support the algorithm implementation of the above-mentioned target vehicle tracking method, forming a stable, fast and lightweight intersection "thinking center". The electronic device can make full use of the various sensor data in the holographic road network environment, give full play to the unique advantages of each sensor, and achieve high-precision and all-round perception of the target vehicle. With its low-latency data transmission network and efficient lightweight deployment, it ensures the rapid response and reliable execution of the analysis algorithm. The electronic device 40 can be a separate hardware device, or it can be integrated into existing intersection equipment, such as into traffic lights or electric police systems.

[0132] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0134] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0136] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0137] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0138] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the target vehicle tracking method provided by any embodiment of the present invention.

[0139] The computer program product may be implemented by writing computer program code for performing the operations of the present disclosure in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0140] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0141] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A target vehicle tracking method, characterized in that: include: Acquire the travel data of the target vehicle and determine that the target vehicle enters a current lane associated with the intersection to be passed, wherein the travel data includes the location information and travel direction information of the target vehicle; Traversing at least one candidate lower-level exit road corresponding to the intersection to be passed, and determining road direction information of each candidate lower-level exit road; According to the traveling direction information of the target vehicle, the acquired lane turning information of the current lane, and the road direction information of each of the candidate lower-level exit roads, selecting an alternative lower-level exit road from each of the candidate lower-level exit roads as the target exit road predicted to be entered after the target vehicle exits the current lane; The predicted driving trajectory of the target vehicle is determined according to the position information of the target vehicle and the target exit road, so as to track the target vehicle based on the predicted driving trajectory.

2. The method according to claim 1, characterized in that The traveling direction information includes a traveling direction angle of the target vehicle relative to a preset standard direction, the road direction information includes a road direction angle of the candidate lower-level exit road relative to a preset standard direction, and the lane turning information of the current lane includes a turning direction of the current lane; The method of selecting, based on the traveling direction information of the target vehicle, the acquired lane information of the current lane, and the road direction information of each of the candidate lower-level exit roads, a candidate lower-level exit road from each of the candidate lower-level exit roads as a target exit road predicted to be entered by the target vehicle after exiting the current lane, comprises: Determining a turning direction angle of the target vehicle according to the traveling direction angle of the target vehicle and the turning direction of the current lane; According to the steering direction angle of the target vehicle and the road direction angle of each of the candidate lower-level exit roads, an alternative lower-level exit road is selected from each of the candidate lower-level exit roads as the target exit road predicted to be entered after the target vehicle exits the current lane.

3. The method according to claim 2, characterized in that The step of selecting, according to the turning direction angle of the target vehicle and the road direction angle of each of the candidate lower-level exit roads, an alternative lower-level exit road from each of the candidate lower-level exit roads as a target exit road predicted to be entered by the target vehicle after exiting the current lane comprises: Comparing the steering direction angle of the target vehicle with the road direction angle of each of the candidate lower-level exit roads; The alternative lower-level exit road corresponding to the road direction angle closest to the steering direction angle is selected as the target exit road predicted to be entered by the target vehicle after it exits the current lane.

4. The method according to claim 2, characterized in that: Determining the turning direction angle of the target vehicle according to the traveling direction angle of the target vehicle and the turning direction of the current lane includes: Determining an angle corresponding to the turning direction of the current lane according to the turning direction of the current lane; The traveling direction angle of the target vehicle is added to the angle corresponding to the turning direction of the current lane, and the result of the addition is used as the turning direction angle of the target vehicle.

5. The method according to claim 4, characterized in that The determining, according to the turning direction of the current lane, an angle corresponding to the turning direction of the current lane includes: If the turning direction of the current lane is straight ahead, the angle corresponding to the turning direction of the current lane is 0 degrees; If the turning direction of the current lane is to turn left, the angle corresponding to the turning direction of the current lane is -90 degrees; If the turning direction of the current lane is right turn, the angle corresponding to the turning direction of the current lane is 90 degrees; If the turning direction of the current lane includes at least two directions, the angle corresponding to the turning direction with the largest proportion in the traffic flow driving data within the historical time period is used as the angle corresponding to the turning direction of the current lane.

6. The method according to claim 1, characterized in that The step of obtaining the travel data of the target vehicle and determining that the target vehicle enters a current lane associated with the intersection to be passed includes: Acquire the positioning source data corresponding to the target vehicle in real time, calculate the real-time position information of the target vehicle and the traveling direction angle of the target vehicle relative to a preset standard direction; Using the position information and the traveling direction angle of the target vehicle as the traveling data of the target vehicle; The location information of the target vehicle is matched with a geographic information system map to determine that the target vehicle enters a current lane associated with the intersection to be passed.

7. The method according to claim 1, characterized in that The traversing at least one candidate lower-level exit road corresponding to the intersection to be passed includes: Based on the road segment connectivity rule, traverse the pre-constructed road network topology structure to obtain the exit road connected to the intersection to be passed in the direction other than the current lane as the candidate lower-level exit road corresponding to the intersection to be passed; or, According to the preset correspondence between each intersection and the candidate lower-level exit road, the candidate lower-level exit road corresponding to the intersection to be passed is obtained.

8. The method according to claim 1, characterized in that The determining of the road direction information of each of the candidate lower-level exit roads includes: Obtaining the pre-stored direction angle of the candidate lower-level exit road, and recording it as the road direction angle of the candidate lower-level exit road; or, The position information of the centerline key points of the candidate lower-level exit road is obtained, and the direction angle of the line connecting the centerline key points relative to the preset standard direction is calculated, which is recorded as the road direction angle of the candidate lower-level exit road.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the target vehicle tracking method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target vehicle tracking method according to any one of claims 1 to 8 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the target vehicle tracking method according to any one of claims 1 to 8 is implemented.

Images