Intersection lane scene recognition methods and related equipment

Abstract

This application discloses an intersection lane scene recognition method and related equipment, relating to the field of autonomous driving technology. The method includes: acquiring scene data; traversing frames in the scene data that contain separated lane elements or merged lane elements; taking the traversed frame as the current frame; determining a corresponding perception map based on the current frame; determining the start frame and end frame corresponding to the set of lane centerlines in the perception map; and determining the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the set of lane centerlines based on the start frame, the end frame, and the perception map. This application determines the perception map based on the scene data corresponding to frames containing separated lane elements or merged lane elements, and then determines the specific type of the intersection lane scene corresponding to two lane lines with overlapping areas in the perception map, accurately determining the intersection lane scene from a large amount of scene data.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to methods and equipment for lane scene recognition at intersections. Background Technology

[0002] With the evolution of intelligent transportation systems, the refined data collection and analysis of intersection lane scenarios has become a core requirement for improving traffic management efficiency. Therefore, accurately identifying intersection lane scenarios is of paramount importance.

[0003] However, with the explosive growth of data volume, the amount of data to be processed has increased, making it extremely difficult to accurately identify intersection lane scenarios from historical driving data.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is related technology. Summary of the Invention

[0005] The main purpose of this application is to provide a method for recognizing lane scenes at intersections, aiming to solve the technical problem of how to accurately recognize lane scenes at intersections.

[0006] To achieve the above objectives, this application proposes a method for recognizing lane scenes at intersections, the method comprising:

[0007] Acquire scene data;

[0008] The frame containing separated lane elements or merged lane elements in the scene data is traversed, and the traversed frame is taken as the current frame. The corresponding perception map is determined based on the current frame.

[0009] The starting frame and ending frame corresponding to the set of lane centerlines in the perception map are determined. Based on the starting frame, the ending frame and the perception map, the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the set of lane centerlines is determined. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane centerlines contains two or more sets of lane centerlines with overlapping areas. The number of overlaps between the first lane centerline and the second lane centerline is greater than or equal to a preset overlap number threshold.

[0010] In one embodiment, the step of determining the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the lane centerline set based on the start frame, the end frame, and the perception map includes:

[0011] Based on the start frame, the end frame, and the perception map, calculate the first projected distance from the vehicle to the center line of the first lane to obtain the first projected distance corresponding to each frame from the start frame to the end frame, and calculate the second projected distance from the vehicle to the center line of the second lane to obtain the second projected distance corresponding to each frame from the start frame to the end frame.

[0012] Calculate the sum of the first projection distance and the second projection distance corresponding to the same frame to obtain multiple sets of third projection distances;

[0013] Calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value;

[0014] If the third projection distance corresponding to the starting frame is greater than the average value, and the third projection distance corresponding to the ending frame is less than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is determined to be a merged lane scene; if the third projection distance corresponding to the starting frame is less than the average value, and the third projection distance corresponding to the ending frame is greater than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is a separated lane scene.

[0015] In one embodiment, the step of determining the corresponding perceptual map based on the current frame includes:

[0016] Based on the scenario data, determine multiple sets of coordinate sequences for lane centerlines;

[0017] A global grid is constructed, and each coordinate in the coordinate sequence is mapped to the global grid to determine the corresponding perception map for the current frame.

[0018] In one embodiment, the step of constructing a global grid, mapping each coordinate in the coordinate sequence to the global grid, and determining the corresponding perception map for the current frame includes:

[0019] Based on the coordinate sequence, the boundary values ​​of the lane centerline are determined, and a global grid is constructed based on the boundary values.

[0020] Each coordinate in the coordinate sequence is mapped to the global grid to obtain the target grid;

[0021] Based on the target grid, find the center lines of the third lane and the fourth lane that have overlapping areas, determine the number of times the center lines of the third lane and the fourth lane overlap, and determine whether the number of overlaps is greater than or equal to a preset overlap threshold.

[0022] If the number of overlaps is greater than or equal to a preset overlap threshold, the center line of the third lane and the center line of the fourth lane are added to the same set of lane center lines; or, if the number of overlaps is less than the preset overlap threshold, the center line of the third lane and the center line of the fourth lane are added to different sets of lane center lines respectively.

[0023] Based on the set of all lane centerlines, determine the corresponding perception map for the current frame.

[0024] In one embodiment, the step of mapping each coordinate in the coordinate sequence to the global grid to obtain the target grid further includes any one of the following:

[0025] Each coordinate in the coordinate sequence is mapped to its corresponding position in the grid to obtain the initial grid. The first thinning operation is then performed on the initial grid to obtain the target grid.

[0026] Each coordinate in the coordinate sequence is mapped to the corresponding position in the grid to obtain the initial grid. The initial grid is then subjected to a first thinning operation, and the grid after the first thinning operation is subjected to a second thinning operation to obtain the target grid. The corresponding thinning operation includes a floor operation.

[0027] In one embodiment, the step of determining the coordinate sequence of multiple lane centerlines based on the scene data further includes:

[0028] Based on the scene data, the vehicle location information is determined, wherein the vehicle location information includes the vehicle coordinates and the vehicle heading angle;

[0029] Based on the vehicle location information, a vehicle coordinate system is constructed;

[0030] Obtain multiple coordinates corresponding to the center line of each lane, and determine the first distance from each coordinate to the vehicle based on the vehicle coordinate system;

[0031] Each coordinate is saved sequentially into a coordinate sequence based on the first distance in ascending order, resulting in multiple sets of coordinate sequences for the lane centerlines.

[0032] In one embodiment, the step of constructing a vehicle coordinate system based on the vehicle location information further includes:

[0033] Extract the vehicle coordinates and vehicle heading angle from the vehicle location information;

[0034] The vehicle coordinates are set as the origin, and the direction corresponding to the vehicle heading angle is set as the positive y-axis. Based on the origin and the positive y-axis, a vehicle coordinate system is constructed for each set of local perception type map data.

[0035] Furthermore, to achieve the above objectives, this application also proposes an intersection lane scene recognition device, which includes:

[0036] The acquisition module is used to acquire scene data;

[0037] The first determining module is used to traverse the frames in the scene data that contain separated lane elements or merged lane elements, take the traversed frame as the current frame, and determine the corresponding perception map based on the current frame.

[0038] The second determining module is used to determine the start frame and end frame corresponding to the set of lane center lines in the perception map. Based on the start frame, the end frame and the perception map, the module determines the intersection lane scene corresponding to the first lane center line and the second lane center line in the set of lane center lines. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane center lines contains two or more sets of lane center lines with overlapping areas. The number of overlaps between the first lane center line and the second lane center line is greater than or equal to a preset overlap number threshold.

[0039] In one embodiment, the second determining module includes:

[0040] The first calculation unit is used to calculate the first projection distance from the vehicle to the center line of the first lane based on the start frame, the end frame and the perception map, to obtain the first projection distance corresponding to each frame from the start frame to the end frame, and to calculate the second projection distance from the vehicle to the center line of the second lane, to obtain the second projection distance corresponding to each frame from the start frame to the end frame.

[0041] The second calculation unit is used to calculate the sum of the first projection distance and the second projection distance corresponding to the same frame, and obtain multiple sets of third projection distances;

[0042] The third calculation unit is used to calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value.

[0043] The first determining unit is configured to determine the intersection lane scene corresponding to the first lane centerline and the second lane centerline as a merged lane scene if the third projection distance corresponding to the starting frame is greater than the average value and the third projection distance corresponding to the ending frame is less than the average value; and to determine the intersection lane scene corresponding to the first lane centerline and the second lane centerline as a separated lane scene if the third projection distance corresponding to the starting frame is less than the average value and the third projection distance corresponding to the ending frame is greater than the average value.

[0044] In one embodiment, the first determining module includes:

[0045] The second determining unit is used to determine multiple sets of coordinate sequences of lane center lines based on the scene data.

[0046] The first construction unit is used to construct a global grid, map each coordinate in the coordinate sequence to the global grid, and determine the corresponding perception map for the current frame.

[0047] In one embodiment, the first determining module further includes:

[0048] The third determining unit is used to determine the boundary value of the lane centerline based on the coordinate sequence, and to construct a global grid based on the boundary value;

[0049] The first mapping unit is used to map each coordinate in the coordinate sequence to the global grid to obtain the target grid;

[0050] The search unit is used to search for the center lines of the third lane and the fourth lane that have overlapping areas based on the target grid, and to determine the number of times the center lines of the third lane and the fourth lane overlap, and to determine whether the number of overlaps is greater than or equal to a preset overlap threshold.

[0051] The addition unit is used to add the center line of the third lane and the center line of the fourth lane to the same set of lane center lines if the number of overlaps is greater than or equal to a preset overlap threshold; or, if the number of overlaps is less than the preset overlap threshold, add the center line of the third lane and the center line of the fourth lane to different sets of lane center lines respectively.

[0052] The fourth determining unit is used to determine the corresponding perception map for the current frame based on the set of all lane centerlines.

[0053] In one embodiment, the first determining module further includes:

[0054] The second mapping unit is used to map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain the initial grid, and to perform the first thinning operation on the initial grid to obtain the target grid.

[0055] The third mapping unit is used to map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain an initial grid. The initial grid is subjected to a first thinning operation, and the grid after the first thinning operation is subjected to a second thinning operation to obtain a target grid. The corresponding thinning operation includes a floor operation.

[0056] In one embodiment, the first determining module further includes:

[0057] The fifth determining unit is used to determine vehicle position information based on the scene data, wherein the vehicle position information includes vehicle coordinates and vehicle heading angle;

[0058] The second construction unit is used to construct a vehicle coordinate system based on the vehicle location information;

[0059] The sixth determining unit is used to obtain multiple coordinates corresponding to the center line of each lane, and determine the first distance from each coordinate to the vehicle based on the vehicle coordinate system;

[0060] The storage unit is used to save each coordinate in ascending order based on the first distance to the coordinate sequence, thereby obtaining multiple sets of lane centerline coordinate sequences.

[0061] In one embodiment, the first determining module further includes:

[0062] The extraction unit is used to extract the vehicle coordinates and vehicle heading angle from the vehicle location information;

[0063] The setting unit is used to set the vehicle coordinates as the origin, set the direction corresponding to the vehicle heading angle as the positive y-axis direction, and construct the vehicle coordinate system corresponding to each set of local perception type map data based on the origin and the positive y-axis direction.

[0064] In addition, to achieve the above objectives, this application also proposes an intersection lane scene recognition device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the intersection lane scene recognition method described above.

[0065] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the intersection lane scene recognition method described above.

[0066] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the intersection lane scene recognition method described above.

[0067] One or more technical solutions proposed in this application have at least the following technical effects:

[0068] This application proposes a method and related equipment for intersection lane scene recognition, relating to the field of autonomous driving technology and related technologies. In the context of explosive growth in data volume, the amount of data to be processed has increased, making it extremely difficult to accurately identify intersection lane scenes from historical driving data. In this application, firstly, scene data is acquired; then, frames containing separated or merged lane elements are traversed within the scene data, and the traversed frame is taken as the current frame. Based on the current frame, a corresponding perception map is determined. Further, the starting and ending frames corresponding to the lane centerline set in the perception map are determined. Based on the starting frame, the ending frame, and the perception map, the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the lane centerline set is determined. The intersection lane scene includes separated lane scenes and merged lane scenes. The lane centerline set contains two or more sets of lane centerlines with overlapping areas, and the number of overlaps between the first lane centerline and the second lane centerline is greater than or equal to a preset overlap threshold.

[0069] It is understood that this application determines the perception map based on the scene data corresponding to frames with separate lane elements or merged lane elements, and then determines the specific type of intersection lane scene corresponding to two lane lines with overlapping areas in the perception map, so as to accurately identify the intersection lane scene from a large amount of scene data. Attached Figure Description

[0070] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0071] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a flowchart illustrating an embodiment of the intersection lane scene recognition method of this application.

[0073] Figure 2This is a flowchart illustrating Embodiment 2 of the intersection lane scene recognition method of this application;

[0074] Figure 3 This is a flowchart illustrating Embodiment 3 of the intersection lane scene recognition method of this application;

[0075] Figure 4 This is a schematic diagram of the module structure of the intersection lane scene recognition device according to an embodiment of this application;

[0076] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the intersection lane scene recognition method in this application embodiment.

[0077] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0078] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0079] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0080] The main solution in this application's embodiments is:

[0081] In this embodiment, for ease of description, the following description will focus on the intersection lane scene recognition device as the execution subject.

[0082] Due to the explosive growth in data volume, the amount of data to be processed has increased, making it extremely difficult to accurately identify intersection lane scenarios from historical driving data.

[0083] This application provides a solution that: acquires scene data, traverses frames in the scene data containing separated or merged lane elements, takes the traversed frames as the current frame, determines the corresponding perception map based on the current frame, determines the start and end frames corresponding to the set of lane centerlines in the perception map, and, based on the start frame, the end frame, and the perception map, determines the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the set of lane centerlines. This application determines the perception map based on the scene data corresponding to frames containing separated or merged lane elements, and then determines the specific type of intersection lane scene corresponding to two lane lines with overlapping areas in the perception map, accurately determining the intersection lane scene from a large amount of scene data.

[0084] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an intersection lane scene recognition device. The following description uses an intersection lane scene recognition device as an example to illustrate this embodiment and the subsequent embodiments.

[0085] Based on this, embodiments of this application provide a method for intersection lane scene recognition, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intersection lane scene recognition method of this application.

[0086] In this embodiment, the intersection lane scene recognition method includes steps S100~S300:

[0087] Step S100: Obtain scene data;

[0088] It should be noted that the scene data is collected by the vehicle's sensors during the vehicle's operation. The scene data includes lane data, pedestrian data on the roadside, etc., and the vehicle's sensors include vision sensors, radar, etc.

[0089] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, grid communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an intersection lane scene recognition device. The following description uses an intersection lane scene recognition device as an example to illustrate this embodiment and the subsequent embodiments.

[0090] In this application, specific application scenarios may include:

[0091] Vehicles traveling on the road use sensors such as lidar, radar, and cameras to collect road data, vehicle driving data, and traffic environment data in real time. Furthermore, the intersection lane scene recognition equipment receives the road data, vehicle driving data, and traffic environment data collected by the sensors. The scene data is the road data, vehicle driving data, and traffic environment data collected by the sensors in real time.

[0092] Step S200: Traverse the frames in the scene data that contain separated lane elements or merged lane elements, take the traversed frame as the current frame, and determine the corresponding perception map based on the current frame.

[0093] It should be noted that if there are at least two lane center lines (the first lane center line and the second lane center line) in the scene data corresponding to a certain frame, and the first lane center line and the second lane center line have an overlapping area, and neither the first lane center line nor the second lane center line is an intersection lane guide line, then it is considered that there are separated lane elements or merged lane elements in the scene data corresponding to that frame, and that frame is set as the current frame.

[0094] Step S300: Determine the start frame and end frame corresponding to the set of lane center lines in the perception map. Based on the start frame, the end frame, and the perception map, determine the intersection lane scene corresponding to the first lane center line and the second lane center line in the set of lane center lines. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane center lines contains two or more sets of lane center lines with overlapping areas. The number of overlaps between the first lane center line and the second lane center line is greater than or equal to a preset overlap number threshold.

[0095] It should be noted that the lane centerline is a characteristic line formed by connecting the center points of each lane in sequence. The lane centerline can reflect the horizontal position and curvature of the road.

[0096] Specifically, the step of determining the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the lane centerline set based on the start frame, the end frame, and the perceived map includes steps S310~S340:

[0097] Step S310: Based on the start frame, the end frame and the perception map, calculate the first projection distance from the vehicle to the center line of the first lane to obtain the first projection distance corresponding to each frame from the start frame to the end frame, and calculate the second projection distance from the vehicle to the center line of the second lane to obtain the second projection distance corresponding to each frame from the start frame to the end frame.

[0098] It should be noted that in actual scenarios, the first projection distance and the second projection distance only need to be determined once every n frames, which reduces the amount of computation and improves computational efficiency.

[0099] Step S320: Calculate the sum of the first projection distance and the second projection distance corresponding to the same frame to obtain multiple sets of third projection distances;

[0100] Step S330: Calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value.

[0101] Step S340: If the third projection distance corresponding to the starting frame is greater than the average value, and the third projection distance corresponding to the ending frame is less than the average value, then the intersection lane scene corresponding to the first lane centerline and the second lane centerline is determined to be a merged lane scene; if the third projection distance corresponding to the starting frame is less than the average value, and the third projection distance corresponding to the ending frame is greater than the average value, then the intersection lane scene corresponding to the first lane centerline and the second lane centerline is a separated lane scene.

[0102] It is understood that if the third projection distance corresponding to the starting frame is greater than the average value, and the third projection distance corresponding to the ending frame is less than the average value, it indicates that the distance between the two lanes is gradually decreasing, and therefore, the intersection lane scene corresponding to the two lanes is considered a merging lane scene. Similarly, if the third projection distance corresponding to the starting frame is less than the average value, and the third projection distance corresponding to the ending frame is greater than the average value, it indicates that the distance between the two lanes is gradually increasing, and therefore, the intersection lane scene corresponding to the two lanes is considered a separating lane scene.

[0103] One or more technical solutions proposed in this application have at least the following technical effects:

[0104] This application proposes a method and related equipment for intersection lane scene recognition, relating to the field of autonomous driving technology and related technologies. In the context of explosive growth in data volume, the amount of data to be processed has increased, making it extremely difficult to accurately identify intersection lane scenes from historical driving data. In this application, firstly, scene data is acquired; then, frames containing separated or merged lane elements are traversed within the scene data, and the traversed frame is taken as the current frame. Based on the current frame, a corresponding perception map is determined. Further, the start and end frames corresponding to the lane centerline set in the perception map are determined. Based on the start frame, the end frame, and the perception map, the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the lane centerline set is determined. The intersection lane scene includes separated lane scenes and merged lane scenes. The lane centerline set contains two or more sets of lane centerlines with overlapping areas. The number of overlaps between the first lane centerline and the second lane centerline is greater than or equal to a preset overlap threshold. Finally, based on the intersection scene, the map scene corresponding to the perception map of the current frame is determined.

[0105] It is understood that this application determines the perception map based on the scene data corresponding to frames with separated lane elements or merged lane elements, and then determines the specific type of the intersection lane scene corresponding to two lane lines with overlapping areas in the perception map. Based on the intersection lane scene in the perception map, the intersection lane scene is accurately determined from a large amount of scene data.

[0106] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The step of determining the corresponding perceptual map based on the current frame also includes steps A100~A200:

[0107] Step A100: Based on the scene data, determine multiple sets of coordinate sequences for lane centerlines;

[0108] It should be noted that, specifically, the step of determining the coordinate sequence of multiple lane centerlines based on the scene data further includes steps A110 to A140:

[0109] Step A110: Based on the scene data, determine the vehicle position information, wherein the vehicle position information includes the vehicle coordinates and the vehicle heading angle;

[0110] It should be noted that vehicle position information typically includes the vehicle's coordinates (x, y) and heading angle. Specifically, the steps for determining vehicle position information based on the aforementioned scene data include:

[0111] First, the intersection lane scene recognition device collects all information about the vehicle's position from the scene data. This information includes the vehicle's GPS coordinates, the vehicle's IMU (Inertial Measurement Unit) data, the vehicle's wheel speed information, the vehicle's steering angle, etc.

[0112] Understandably, intersection lane scene recognition devices use data fusion technology to improve the accuracy of location information because a single data source may not be accurate enough. Common data fusion technologies include Kalman filtering and particle filtering.

[0113] Furthermore, the intersection lane scene recognition equipment uses GPS data to obtain the vehicle's global coordinates (longitude, latitude, and altitude).

[0114] The heading angle of a vehicle can be determined using magnetometer data from an IMU (Important Measure) or estimated using the vehicle's steering angle and trajectory. If the scene data includes IMU data, the intersection lane scene recognition device can directly use the magnetometer data to determine the heading angle. If there is no IMU data, the intersection lane scene recognition device may need to use other methods (such as visual odometry, wheel speed measurement, etc.) to estimate the heading angle.

[0115] Finally, the intersection lane scene recognition device obtains vehicle position information with the vehicle's coordinates and heading angle.

[0116] Step A120: Based on the vehicle location information, construct a vehicle coordinate system;

[0117] It's important to note that constructing the Vehicle Coordinate System (VCS) is a crucial step in autonomous driving and vehicle navigation, aiding in understanding and controlling the vehicle's position and movement in space. The VCS is typically a two-dimensional coordinate system with its origin at the center of the vehicle's rear axle, the x-axis pointing forward, and the y-axis pointing to the left. The steps for constructing the VCS are as follows:

[0118] Understandably, since the vehicle is in motion, the vehicle coordinate system needs to be updated in real time to reflect the vehicle's latest position and orientation, which is usually achieved through vehicle sensor data (such as GPS, IMU, wheel speedometer, etc.).

[0119] Specifically, the step of constructing a vehicle coordinate system based on the vehicle location information further includes steps A121 to A122:

[0120] Step A121: Extract the vehicle coordinates and vehicle heading angle from the vehicle location information;

[0121] Step A122: Set the vehicle coordinates as the origin, set the direction corresponding to the vehicle heading angle as the positive y-axis direction, and construct the vehicle coordinate system corresponding to each set of local perception type map data based on the origin and the positive y-axis direction.

[0122] It is understandable that the lane centerline may be a curved curve. In this case, to save the coordinates of the lane centerline sequentially into the coordinate sequence, a reference coordinate is needed. As vehicles move in the same direction in the lane over time, using the vehicle as the origin to construct a coordinate system can provide a basis for subsequent steps to save the coordinates of the lane centerline sequentially into the coordinate sequence.

[0123] Step A130: Obtain multiple coordinates corresponding to the center line of each lane, and determine the first distance from each coordinate to the vehicle based on the vehicle coordinate system;

[0124] It should be noted that the multiple coordinates corresponding to the center line of each lane are not obtained based on the vehicle coordinate system.

[0125] Step A140: Save each coordinate in ascending order of the first distance to the coordinate sequence to obtain multiple sets of lane centerline coordinate sequences.

[0126] Step A200: Construct a global grid, map each coordinate in the coordinate sequence to the global grid to obtain a global perception map with a preset precision, and determine the vehicle coordinates of the vehicle in the future frame based on the global perception map.

[0127] Specifically, the step of constructing a global grid and mapping each coordinate in the coordinate sequence to the global grid to obtain a globally perceived map with a preset accuracy includes steps A210 to A250:

[0128] Step A210: Based on the coordinate sequence, determine the boundary values ​​of the lane centerline, and construct a global mesh based on the boundary values;

[0129] It should be noted that the size of the global grid is related to the boundary values ​​of the lane centerline. For example, if the horizontal coordinate range of the boundary values ​​is [0, 5] and the vertical coordinate range is [0, 5], then the size of the global grid is 5x5.

[0130] Step A220: Map each coordinate in the coordinate sequence to the global grid to obtain the target grid;

[0131] Step A230: Based on the target grid, find the center lines of the first lane and the second lane that have overlapping areas, determine the number of times the center lines of the first lane and the second lane overlap, and determine whether the number of overlaps is greater than or equal to a preset overlap threshold.

[0132] Step A240: If the number of overlaps is greater than or equal to a preset overlap threshold, add the first lane centerline and the second lane centerline to the same lane centerline set; or, if the number of overlaps is less than the preset overlap threshold, add the first lane centerline and the second lane centerline to different lane centerline sets respectively.

[0133] It should be noted that in the perception map, the perception results of the same sensor for the same lane line are not the same at different times. For example, at the first time, the perception result corresponding to lane line 1 is lane line 1, while at the second time, the perception result corresponding to lane line 1 becomes lane line 2, which reduces the accuracy of the perception animation.

[0134] It is understandable that if the number of overlaps between the center lines of the first lane and the center lines of the second lane is greater than or equal to a preset overlap threshold, it indicates that the two lane lines may be the same lane line. Therefore, the center lines of the first lane and the center lines of the second lane are placed in the same set of lane center lines.

[0135] Step A250: Determine the corresponding perception map for the current frame based on the set of all lane centerlines.

[0136] Understandably, placing lane centerlines with high overlap into the same set of lane centerlines can result in a more accurate perception map.

[0137] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 The step of mapping each coordinate in the coordinate sequence to the global grid to obtain the target grid further includes any one of steps A221 to A222:

[0138] Step A221: Map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain the initial grid. Perform the first thinning operation on the initial grid to obtain the target grid.

[0139] Step A222: Map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain the initial grid. Perform a first thinning operation on the initial grid and a second thinning operation on the grid after the first thinning operation to obtain the target grid. The corresponding thinning operation includes a floor operation and a rounding operation.

[0140] Taking rounding down as an example, firstly, the int (round down) operator is used to transform the coordinate point to the corresponding position (temp_x, temp_y) in the grid, where temp_x = int(temp_x) - int(x_min), temp_y = int(temp_y) - int(y_min), and (temp_x, temp_y) represents the grid position corresponding to the previous coordinate point.

[0141] A list `polyline` is constructed to store the coordinates of the new lane centerline after thinning. If the list `polyline` is empty, `point` is added to the list, and the position (temp_x, temp_y) in the grid is set to 1. No further checks are performed on this coordinate point. Here, `point` represents the coordinates on the lane centerline. If the list `polyline` is not empty, further checks are required on this coordinate point. The specific steps are as follows:

[0142] Check the grid position value (temp_x, temp_y) corresponding to the current coordinate point. If it is 0, it means that the coordinate point appears for the first time at the grid position (temp_x, temp_y), and this position is marked as 1. If it is 1, it means that the coordinate point has already been marked, so skip this point. If the coordinate point appears for the first time at the grid position (temp_x, temp_y), further determination is needed to determine whether to retain the coordinate point.

[0143] Furthermore, if the distance between the current coordinate point and the previously added point in the polyline list is less than 1, the two points are considered too close, and the current point can be ignored, thus achieving thinning. Otherwise, the current coordinate point is added to the polyline list and marked in the grid.

[0144] Understandably, in path planning, excessively dense waypoints not only increase the burden of computation and storage, but may also lead to path redundancy and reduced efficiency. Therefore, it is necessary to perform sparse processing while preserving the shape features and trajectory information of the path to ensure the accuracy and real-time performance of path planning.

[0145] In this embodiment, by thinning the computation, the amount of computation is reduced, the computational efficiency is improved, and thus, real-time performance is guaranteed.

[0146] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the intersection lane scene recognition method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0147] This application also provides an intersection lane scene recognition device, please refer to... Figure 4 The intersection lane scene recognition device includes:

[0148] Acquisition module 10, the acquisition module is used to acquire scene data;

[0149] The first determining module 20 is used to traverse the frames in the scene data that contain separated lane elements or merged lane elements, take the traversed frame as the current frame, and determine the corresponding perception map based on the current frame.

[0150] The second determining module 30 is used to determine the start frame and end frame corresponding to the set of lane center lines in the perception map. Based on the start frame, the end frame and the perception map, the module determines the intersection lane scene corresponding to the first lane center line and the second lane center line in the set of lane center lines. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane center lines contains two or more sets of lane center lines with overlapping areas. The number of overlaps between the first lane center line and the second lane center line is greater than or equal to a preset overlap number threshold.

[0151] In one embodiment, the second determining module includes:

[0152] The first calculation unit is used to calculate the first projection distance from the vehicle to the center line of the first lane based on the start frame, the end frame and the perception map, to obtain the first projection distance corresponding to each frame from the start frame to the end frame, and to calculate the second projection distance from the vehicle to the center line of the second lane, to obtain the second projection distance corresponding to each frame from the start frame to the end frame.

[0153] The second calculation unit is used to calculate the sum of the first projection distance and the second projection distance corresponding to the same frame, and obtain multiple sets of third projection distances;

[0154] The third calculation unit is used to calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value.

[0155] The first determining unit is configured to determine the intersection lane scene corresponding to the first lane centerline and the second lane centerline as a merged lane scene if the third projection distance corresponding to the starting frame is greater than the average value and the third projection distance corresponding to the ending frame is less than the average value; and to determine the intersection lane scene corresponding to the first lane centerline and the second lane centerline as a separated lane scene if the third projection distance corresponding to the starting frame is less than the average value and the third projection distance corresponding to the ending frame is greater than the average value.

[0156] In one embodiment, the first determining module includes:

[0157] The second determining unit is used to determine multiple sets of coordinate sequences of lane center lines based on the scene data.

[0158] The first construction unit is used to construct a global grid, map each coordinate in the coordinate sequence to the global grid, and determine the corresponding perception map for the current frame.

[0159] In one embodiment, the first determining module further includes:

[0160] The third determining unit is used to determine the boundary value of the lane centerline based on the coordinate sequence, and to construct a global grid based on the boundary value;

[0161] The first mapping unit is used to map each coordinate in the coordinate sequence to the global grid to obtain the target grid;

[0162] The search unit is used to search for the center lines of the third lane and the fourth lane that have overlapping areas based on the target grid, and to determine the number of times the center lines of the third lane and the fourth lane overlap, and to determine whether the number of overlaps is greater than or equal to a preset overlap threshold.

[0163] The addition unit is used to add the center line of the third lane and the center line of the fourth lane to the same set of lane center lines if the number of overlaps is greater than or equal to a preset overlap threshold; or, if the number of overlaps is less than the preset overlap threshold, add the center line of the third lane and the center line of the fourth lane to different sets of lane center lines respectively.

[0164] The fourth determining unit is used to determine the corresponding perception map for the current frame based on the set of all lane centerlines.

[0165] In one embodiment, the first determining module further includes:

[0166] The second mapping unit is used to map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain the initial grid, and to perform the first thinning operation on the initial grid to obtain the target grid.

[0167] The third mapping unit is used to map each coordinate in the coordinate sequence to the corresponding position in the grid to obtain an initial grid. The initial grid is subjected to a first thinning operation, and the grid after the first thinning operation is subjected to a second thinning operation to obtain a target grid. The corresponding thinning operation includes a floor operation.

[0168] In one embodiment, the first determining module further includes:

[0169] The fifth determining unit is used to determine vehicle position information based on the scene data, wherein the vehicle position information includes vehicle coordinates and vehicle heading angle;

[0170] The second construction unit is used to construct a vehicle coordinate system based on the vehicle location information;

[0171] The sixth determining unit is used to obtain multiple coordinates corresponding to the center line of each lane, and determine the first distance from each coordinate to the vehicle based on the vehicle coordinate system;

[0172] The storage unit is used to save each coordinate in ascending order based on the first distance to the coordinate sequence, thereby obtaining multiple sets of lane centerline coordinate sequences.

[0173] In one embodiment, the first determining module further includes:

[0174] The extraction unit is used to extract the vehicle coordinates and vehicle heading angle from the vehicle location information;

[0175] The setting unit is used to set the vehicle coordinates as the origin, set the direction corresponding to the vehicle heading angle as the positive y-axis direction, and construct the vehicle coordinate system corresponding to each set of local perception type map data based on the origin and the positive y-axis direction.

[0176] The intersection lane scene recognition device provided in this application, employing the intersection lane scene recognition method in the above embodiments, can solve the technical problem of intersection lane scene recognition. Compared with the prior art, the beneficial effects of the intersection lane scene recognition device provided in this application are the same as those of the intersection lane scene recognition method provided in the above embodiments, and other technical features in the intersection lane scene recognition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0177] This application provides an intersection lane scene recognition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the intersection lane scene recognition method in the above embodiment 1.

[0178] The following is for reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the intersection lane scene recognition device in the embodiments of this application. The intersection lane scene recognition device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The intersection lane scene recognition device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0179] like Figure 5 As shown, the intersection lane scene recognition device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the intersection lane scene recognition device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the intersection lane scene recognition device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show intersection lane scene recognition devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0180] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0181] The intersection lane scene recognition device provided in this application, employing the intersection lane scene recognition method in the above embodiments, can solve the technical problem of intersection lane scene recognition. Compared with the prior art, the beneficial effects of the intersection lane scene recognition device provided in this application are the same as those of the intersection lane scene recognition method provided in the above embodiments, and other technical features in this intersection lane scene recognition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0182] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0183] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0184] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the intersection lane scene recognition method in the above embodiments.

[0185] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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. In this embodiment, the computer-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 or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0186] The aforementioned computer-readable storage medium may be included in the intersection lane scene recognition device; or it may exist independently and not be installed in the intersection lane scene recognition device.

[0187] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the intersection lane scene recognition device, cause the intersection lane scene recognition device to:

[0188] Acquire scene data;

[0189] The frame containing separated lane elements or merged lane elements in the scene data is traversed, and the traversed frame is taken as the current frame. The corresponding perception map is determined based on the current frame.

[0190] The starting frame and ending frame corresponding to the set of lane centerlines in the perception map are determined. Based on the starting frame, the ending frame and the perception map, the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the set of lane centerlines is determined. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane centerlines contains two or more sets of lane centerlines with overlapping areas. The number of overlaps between the first lane centerline and the second lane centerline is greater than or equal to a preset overlap number threshold.

[0191] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone 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 remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0192] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0193] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0194] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described intersection lane scene recognition method, and is capable of solving the technical problem of intersection lane scene recognition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intersection lane scene recognition method provided in the above embodiments, and will not be repeated here.

[0195] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intersection lane scene recognition method described above.

[0196] The computer program product provided in this application can solve the technical problem of intersection lane scene recognition. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the intersection lane scene recognition method provided in the above embodiments, and will not be repeated here.

[0197] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for recognizing lane scenes at intersections, characterized in that, The intersection lane scene recognition method includes: Acquire scene data; The frame containing separated lane elements or merged lane elements in the scene data is traversed, and the traversed frame is taken as the current frame. The corresponding perception map is determined based on the current frame. The starting frame and ending frame corresponding to the set of lane centerlines in the perception map are determined. Based on the starting frame, the ending frame and the perception map, the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the set of lane centerlines is determined. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane centerlines contains two or more sets of lane centerlines with overlapping areas. The number of overlaps between the first lane centerline and the second lane centerline is greater than or equal to a preset overlap number threshold. The step of determining the intersection lane scene corresponding to the first lane centerline and the second lane centerline in the lane centerline set based on the start frame, the end frame, and the perception map includes: Based on the start frame, the end frame, and the perception map, calculate the first projected distance from the vehicle to the center line of the first lane to obtain the first projected distance corresponding to each frame from the start frame to the end frame, and calculate the second projected distance from the vehicle to the center line of the second lane to obtain the second projected distance corresponding to each frame from the start frame to the end frame. Calculate the sum of the first projection distance and the second projection distance corresponding to the same frame to obtain multiple sets of third projection distances; Calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value; If the third projection distance corresponding to the starting frame is greater than the average value, and the third projection distance corresponding to the ending frame is less than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is determined to be a merged lane scene; if the third projection distance corresponding to the starting frame is less than the average value, and the third projection distance corresponding to the ending frame is greater than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is a separated lane scene.

2. The intersection lane scene recognition method as described in claim 1, characterized in that, The step of determining the corresponding perception map based on the current frame includes: Based on the scenario data, determine multiple sets of coordinate sequences for lane centerlines; A global grid is constructed, and each coordinate in the coordinate sequence is mapped to the global grid to determine the corresponding perception map for the current frame.

3. The intersection lane scene recognition method as described in claim 2, characterized in that, The step of constructing a global grid, mapping each coordinate in the coordinate sequence to the global grid, and determining the corresponding perception map for the current frame includes: Based on the coordinate sequence, the boundary values ​​of the lane centerline are determined, and a global grid is constructed based on the boundary values. Each coordinate in the coordinate sequence is mapped to the global grid to obtain the target grid; Based on the target grid, find the center lines of the third lane and the fourth lane that have overlapping areas, determine the number of times the center lines of the third lane and the fourth lane overlap, and determine whether the number of overlaps is greater than or equal to a preset overlap threshold. If the number of overlaps is greater than or equal to a preset overlap threshold, the center line of the third lane and the center line of the fourth lane are added to the same set of lane center lines; or, if the number of overlaps is less than the preset overlap threshold, the center line of the third lane and the center line of the fourth lane are added to different sets of lane center lines respectively. Based on the set of all lane centerlines, determine the corresponding perception map for the current frame.

4. The intersection lane scene recognition method as described in claim 3, characterized in that, The step of mapping each coordinate in the coordinate sequence to the global grid to obtain the target grid further includes any one of the following: Each coordinate in the coordinate sequence is mapped to its corresponding position in the grid to obtain the initial grid. The first thinning operation is then performed on the initial grid to obtain the target grid. Each coordinate in the coordinate sequence is mapped to the corresponding position in the grid to obtain the initial grid. The initial grid is then subjected to a first thinning operation, and the grid after the first thinning operation is subjected to a second thinning operation to obtain the target grid. The corresponding thinning operation includes a floor operation.

5. The intersection lane scene recognition method as described in claim 2, characterized in that, The step of determining the coordinate sequence of multiple lane centerlines based on the scene data further includes: Based on the scene data, the vehicle location information is determined, wherein the vehicle location information includes the vehicle coordinates and the vehicle heading angle; Based on the vehicle location information, a vehicle coordinate system is constructed; Obtain multiple coordinates corresponding to the center line of each lane, and determine the first distance from each coordinate to the vehicle based on the vehicle coordinate system; Each coordinate is saved sequentially into a coordinate sequence based on the first distance in ascending order, resulting in multiple sets of coordinate sequences for the lane centerlines.

6. The intersection lane scene recognition method as described in claim 5, characterized in that, The step of constructing a vehicle coordinate system based on the vehicle location information further includes: Extract the vehicle coordinates and vehicle heading angle from the vehicle location information; The vehicle coordinates are set as the origin, and the direction corresponding to the vehicle heading angle is set as the positive y-axis. Based on the origin and the positive y-axis, a vehicle coordinate system is constructed for each set of local perception type map data.

7. A lane scene recognition device at an intersection, characterized in that, The intersection lane scene recognition device includes: The acquisition module is used to acquire scene data; The first determining module is used to traverse the frames in the scene data that contain separated lane elements or merged lane elements, take the traversed frame as the current frame, and determine the corresponding perception map based on the current frame. The second determining module is used to determine the start frame and end frame corresponding to the set of lane center lines in the perception map. Based on the start frame, the end frame and the perception map, the module determines the intersection lane scene corresponding to the first lane center line and the second lane center line in the set of lane center lines. The intersection lane scene includes a separated lane scene and a merged lane scene. The set of lane center lines contains two or more sets of lane center lines with overlapping areas. The number of overlaps between the first lane center line and the second lane center line is greater than or equal to a preset overlap number threshold. The second determining module is further configured to implement: Based on the start frame, the end frame, and the perception map, calculate the first projected distance from the vehicle to the center line of the first lane to obtain the first projected distance corresponding to each frame from the start frame to the end frame, and calculate the second projected distance from the vehicle to the center line of the second lane to obtain the second projected distance corresponding to each frame from the start frame to the end frame. Calculate the sum of the first projection distance and the second projection distance corresponding to the same frame to obtain multiple sets of third projection distances; Calculate the average value of the multiple sets of third projection distances, determine the magnitude of the third projection distance corresponding to the starting frame and the average value, and determine the magnitude of the third projection distance corresponding to the ending frame and the average value; If the third projection distance corresponding to the starting frame is greater than the average value, and the third projection distance corresponding to the ending frame is less than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is determined to be a merged lane scene; if the third projection distance corresponding to the starting frame is less than the average value, and the third projection distance corresponding to the ending frame is greater than the average value, then the intersection lane scene corresponding to the center line of the first lane and the center line of the second lane is a separated lane scene.

8. A lane scene recognition device at an intersection, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the intersection lane scene recognition method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the intersection lane scene recognition method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the intersection lane scene recognition method as described in any one of claims 1 to 6.

Images