U-turn scenario recognition method and related device

Abstract

The application discloses a U-turn scene recognition method and related equipment thereof, and relates to the technical field of vehicles.The U-turn scene recognition method comprises the following steps: acquiring a historical scene segment; when there is an intersection scene in the historical scene segment, determining a scene recognition result based on each frame of data in the historical scene segment, so as to avoid mistaking the data of a non-key road section as a U-turn scene (for example, a vehicle reversing scene); the scene recognition result can be that there is a left U-turn scene in the historical scene segment, and / or there is a right U-turn scene in the historical scene segment, and / or there is no U-turn scene in the historical scene segment; the application only needs to acquire the historical scene segment, and accurately obtains the scene recognition result about the U-turn of the vehicle in the historical scene segment through the above method, so that the data about the U-turn of the vehicle is simply acquired.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method for recognizing U-turn scenarios and related equipment. Background Technology

[0002] With the development of intelligent driving technology, the demand for data from real traffic scenarios is increasing. This data from real traffic scenarios can not only be used to train and validate autonomous driving algorithms, but also to improve vehicle perception, decision-making, and control algorithms.

[0003] High-quality data from real-world traffic scenarios can significantly improve the accuracy of autonomous driving algorithms, vehicle perception, decision-making, and control algorithms. However, due to technical limitations in the data collection process, as well as the relatively rare and complex nature of U-turns, obtaining data on U-turn scenarios is quite difficult. Summary of the Invention

[0004] The main purpose of this application is to provide a U-turn scene recognition method and related equipment, which aims to solve the technical problem of the high difficulty in acquiring data on vehicle turning scenes.

[0005] To achieve the above objectives, this application proposes a U-shaped turn scene recognition method, which includes:

[0006] Obtain historical scene fragments;

[0007] When an intersection scene exists in the historical scene segment, the scene recognition result is determined based on the data of each frame in the historical scene segment;

[0008] The scene recognition results include whether the historical scene segment contains a left U-turn scene, a right U-turn scene, and / or no U-turn scene.

[0009] In one embodiment, the step of determining the scene recognition result based on the frame data in the historical scene segment includes:

[0010] Determine whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame. The target frame includes the starting frame, and the preset frame is spaced apart from the target frame by a preset frame length.

[0011] If it exists, the change in the vehicle's driving direction is determined based on the vehicle heading angles corresponding to the target frame and the preset frame, respectively.

[0012] The scene recognition result is determined based on the changes in the vehicle's driving direction.

[0013] In one embodiment, the step of determining whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame includes:

[0014] Determine whether the vehicle speed corresponding to the target frame data is less than a preset speed threshold;

[0015] If the vehicle speed is greater than or equal to a preset speed threshold, then based on the vehicle position information corresponding to each frame, the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame is calculated sequentially.

[0016] Sum the distances traveled by each vehicle to obtain the total distance traveled.

[0017] If the total driving distance is greater than or equal to the preset driving distance, then it is determined that there is a possibility that the vehicle in each frame between the target frame and the preset frame may make a U-turn.

[0018] In one embodiment, the step of determining the change in vehicle travel direction based on the vehicle heading angles corresponding to the target frame and the preset frame respectively includes:

[0019] Calculate the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame, respectively;

[0020] Based on the angle difference, the change in the vehicle's driving direction in the corresponding scene sub-segment from the target frame to the preset frame is determined.

[0021] In one embodiment, after determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference, the method further includes:

[0022] Update the target frame to a frame that slides backward a preset number of frames, return to the step of determining whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame, until the preset frame is the end frame, and obtain the changes in the vehicle's driving direction in multiple scene sub-segments corresponding to the start frame to the end frame.

[0023] In one embodiment, the step of determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference includes:

[0024] The angle difference is normalized.

[0025] If the normalized angle difference is within the first angle range, then the change in the vehicle's driving direction is determined to be a left U-turn.

[0026] If the normalized angle difference is within the second angle range, then the change in the vehicle's driving direction is determined to be a right U-turn.

[0027] If the normalized angle difference is within the third angle range, then the change in the vehicle's driving direction is determined to be that no U-turn has occurred.

[0028] There is no overlap between the first angle interval, the second angle interval, and the third angle interval.

[0029] In one embodiment, the step of determining the scene recognition result based on the change in the vehicle's driving direction includes:

[0030] Based on the changes in the vehicle's driving direction in multiple scene sub-segments corresponding to the start frame to the end frame, the scene recognition results of the multiple scene sub-segments are determined;

[0031] After determining the scene recognition result based on the change in the vehicle's driving direction, the method further includes:

[0032] Based on a target scene sub-segment where a vehicle makes a U-turn, determine the moment when the vehicle makes the U-turn.

[0033] In one embodiment, after the step of acquiring historical scene fragments, the method further includes:

[0034] Determine whether intersection signage information exists in each frame of data;

[0035] If it exists, the target distance between the intersection and the vehicle is calculated based on the intersection sign information;

[0036] When the target distance is less than a preset distance threshold, it is determined that there is an intersection scene in the historical scene segment.

[0037] In one embodiment, the intersection signage information includes traffic light information, which includes the first coordinates of at least one traffic light in a global coordinate system. The step of calculating the target distance between the intersection and the vehicle based on the intersection signage information includes:

[0038] Convert the first coordinates into a second coordinate in the vehicle body coordinate system;

[0039] Based on the second coordinates, calculate the first longitudinal distance between at least one traffic light and the vehicle;

[0040] Based on the first longitudinal distance, determine whether there is a target traffic light ahead of the vehicle;

[0041] If it exists, the minimum longitudinal distance in the first longitudinal distance corresponding to the target traffic light shall be taken as the target distance between the intersection and the vehicle;

[0042] The step of determining whether there is a target traffic light ahead of the vehicle based on the first longitudinal distance includes:

[0043] When the first longitudinal distance is greater than zero, the corresponding target traffic light is determined to be in front of the vehicle.

[0044] In one embodiment, the intersection signage information further includes zebra crossing information, which includes the third coordinates of all corner points of at least one zebra crossing corresponding to a rectangle in the global coordinate system. The step of calculating the target distance between the intersection and the vehicle based on the intersection signage information includes:

[0045] The third coordinate is converted into a fourth coordinate in the vehicle body coordinate system;

[0046] Based on the fourth coordinate, calculate the second longitudinal distance between each corner point and the vehicle;

[0047] Based on the second longitudinal distance, determine whether there is a target zebra crossing in front of or under the vehicle;

[0048] If it exists, the minimum longitudinal distance in the second longitudinal distance corresponding to the target zebra crossing shall be taken as the target distance between the intersection and the vehicle.

[0049] The step of determining whether a target zebra crossing exists in front of or below the vehicle based on the second longitudinal distance includes:

[0050] If at least one corner of the target zebra crossing is at a second longitudinal distance greater than or equal to zero from the vehicle, then the target zebra crossing is determined to be in front of or under the vehicle.

[0051] If all corner points of the target zebra crossing are less than zero from the second longitudinal distance of the vehicle, then the target zebra crossing is determined to be behind the vehicle.

[0052] Furthermore, to achieve the above objectives, this application also proposes a U-shaped turn scene recognition device, which includes:

[0053] The acquisition module is used to acquire historical scene fragments;

[0054] The recognition module is used to determine the scene recognition result based on the data of each frame in the historical scene segment when an intersection scene exists in the historical scene segment. The scene recognition result includes whether a left U-turn scene, a right U-turn scene, and / or no U-turn scene exists in the historical scene segment.

[0055] In addition, to achieve the above objectives, this application also proposes a U-turn scene recognition device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the U-turn scene recognition method described above.

[0056] 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 U-shaped turn scene recognition method described above.

[0057] 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 U-shaped turn scene recognition method described above.

[0058] One or more technical solutions proposed in this application have at least the following technical effects:

[0059] This application obtains historical scene fragments; when an intersection scene exists in the historical scene fragment, it determines the scene recognition result based on the data of each frame in the historical scene fragment, avoiding misidentifying data of non-critical road segments as U-turn scenes (e.g., vehicle reversing scenes); the scene recognition result may be that a left U-turn scene exists in the historical scene fragment, and / or a right U-turn scene exists in the historical scene fragment, and / or no U-turn scene exists in the historical scene fragment; this application only needs to obtain historical scene fragments and accurately obtain the scene recognition result of vehicle U-turns in the historical scene fragments through the above method, thereby easily obtaining data about vehicle U-turns. Attached Figure Description

[0060] 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.

[0061] 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.

[0062] Figure 1 This is a flowchart illustrating an embodiment of the U-shaped turn scene recognition method of this application.

[0063] Figure 2A simplified flowchart illustrating the U-shaped turn scene recognition method provided in Embodiment 1 of this application;

[0064] Figure 3 This is a schematic diagram of a scene provided in Embodiment 1 of the U-shaped turn scene recognition method of this application;

[0065] Figure 4 This is a flowchart illustrating Embodiment 2 of the U-shaped turn scene recognition method of this application;

[0066] Figure 5 This is a flowchart illustrating Embodiment 3 of the U-shaped turn scene recognition method of this application;

[0067] Figure 6 This is a schematic diagram of the module structure of the U-shaped turn scene recognition device according to an embodiment of this application;

[0068] Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the U-shaped turn scene recognition method in this application embodiment.

[0069] 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

[0070] 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.

[0071] 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.

[0072] 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 a U-shaped turn scene recognition device. The following description uses a U-shaped turn scene recognition device as an example to illustrate this embodiment and the subsequent embodiments.

[0073] Based on this, the embodiments of this application provide a method for recognizing U-shaped turning scenes, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the U-shaped turn scene recognition method of this application.

[0074] In this embodiment, the U-shaped turn scene recognition method includes steps S10~S20:

[0075] Step S10: Obtain historical scene fragments;

[0076] It should be noted that with the development of intelligent driving technology, the demand for data from real traffic scenarios is increasing. This data from real traffic scenarios can not only be used to train and validate autonomous driving algorithms, but also to improve vehicle perception, decision-making, and control algorithms.

[0077] High-quality data from real-world traffic scenarios can significantly improve the accuracy of autonomous driving algorithms, vehicle perception, decision-making, and control algorithms. However, due to technical limitations in the data collection process, as well as the relatively rare and complex nature of U-turns, obtaining data on U-turn scenarios is quite difficult.

[0078] To address the aforementioned issues, this embodiment acquires historical scene fragments to offline identify whether U-turn scenarios exist within these fragments. This allows the historical scene fragments with scene recognition results to serve as effective sample data for training and validating autonomous driving algorithms, vehicle perception algorithms, driving decision-making algorithms, and vehicle control algorithms.

[0079] Specifically, historical scene fragments can be historically collected vehicle driving records or vehicle driving information generated through simulation. Historical scene fragments include multiple frames of data, and the scene information corresponding to each frame of data can include dynamic perception information collected by sensors such as cameras and radar, or static map information obtained by matching historically collected vehicle latitude and longitude with high-precision maps. Among them, dynamic perception information includes historically collected road images, timestamps, vehicle position information (e.g., vehicle coordinates in the global coordinate system), vehicle speed and acceleration, vehicle direction and U-turn angle, vehicle travel direction, vehicle steering wheel angle, driver operation (e.g., braking, accelerator force, gear shifting, etc.), etc. Static map information includes traffic sign information on the road, and information on the position and behavior of other vehicles, pedestrians, obstacles, etc.

[0080] Step S20: When there is an intersection scene in the historical scene segment, the scene recognition result is determined based on the data of each frame in the historical scene segment. The scene recognition result includes whether there is a left U-turn scene, a right U-turn scene, and / or no U-turn scene in the historical scene segment.

[0081] Since U-turns typically occur at intersections, to improve the recognition efficiency of U-turn scenarios in historical scene segments, this embodiment only continues to recognize U-turn scenarios in historical scene segments if an intersection scenario is confirmed to exist in the historical scene segment; if no intersection scenario exists in the historical scene segment, then the historical scene segment is not recognized for U-turn scenarios, and the historical scene segment is discarded as training data.

[0082] Specifically, the specific implementation method for determining the scene recognition result of the historical scene segment based on the data of each frame in the historical scene segment can be: determining the scene recognition result of the historical scene segment based on the dynamic perception information and static map information corresponding to each frame in the historical scene segment.

[0083] The scene recognition results of the historical scene segments include the presence of a left U-turn, a right U-turn, and / or the absence of a U-turn scene in the historical scene segments. Therefore, historical scene segments with scene recognition results can be used as training data.

[0084] Since historical scene segments include multiple frames of data, the scene recognition results of historical scene segments can also be scenes of vehicles making a left U-turn, scenes of vehicles making a right U-turn, and / or scenes where there is no U-turn, respectively, in each frame of data. In order to increase the amount of data, each frame of data with scene recognition results can be used as training data.

[0085] Specifically, please refer to Figure 2 Step S20 includes steps A1 to A3:

[0086] Step A1: Determine whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame. The target frame includes the starting frame, and the preset frame is spaced apart from the target frame by a preset frame length.

[0087] Since historical scene segments include multiple frames of data, in order to improve data processing efficiency, we can first determine whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame. If there is no possibility of a U-turn, we can skip further recognition of the scene sub-segments between the target frame and the preset frame, thereby saving computing resources and time. If there is a possibility of a U-turn, we can further perform scene recognition on the scene sub-segments between the target frame and the preset frame.

[0088] In this context, let M be the total number of frames in the historical scene segment. The preset frame length (frame_size) is determined based on the time required for the vehicle to complete a U-turn. Specifically, the preset frame length can be 50 frames or 100 frames, etc. The target frame (frame_i) includes the starting frame and other frames. The preset frame is spaced apart from the target frame by a preset frame length. It can be understood that when the target frame is frame 0, the preset frame can be frame 100, and when the target frame is frame 20, the preset frame can be frame 120.

[0089] That is, to determine whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame.

[0090] The specific implementation of determining whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame can be as follows:

[0091] Determine whether the vehicle speed corresponding to the target frame data is less than a preset speed threshold; if the vehicle speed is greater than or equal to the preset speed threshold, then based on the vehicle position information corresponding to each frame, calculate the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame; sum the travel distances of each vehicle to obtain the total travel distance; if the total travel distance is greater than or equal to the preset travel distance, then determine that there is a possibility of a U-turn for the vehicles corresponding to each frame from the target frame to the preset frame.

[0092] It should be noted that since a vehicle can only perform a U-turn operation when its speed meets certain conditions, this embodiment determines whether the vehicle speed corresponding to the target frame is less than a preset speed threshold (vel_static) to exclude the case where the vehicle is stationary, thereby avoiding further U-turn judgment and reducing the waste of computing resources.

[0093] The preset speed threshold (distance_static) can be 0.5m / s or 0.7m / s, etc. Since U-turns are more difficult than regular turns, vehicles usually reduce their speed when attempting a U-turn. Furthermore, the speed at which a vehicle might make a U-turn is lower than the speed at which it might turn left or right. For example, if the speed corresponding to frame 20 (the target frame) is less than 0.5m / s, the vehicle is considered stationary, and no further scene recognition is performed on that frame; that is, scene recognition from frame 20 to frame 120 is skipped. If the speed corresponding to frame 20 (the target frame) is greater than or equal to 0.5m / s, the vehicle is considered to have the potential to make a U-turn or turn left or right.

[0094] Furthermore, if the vehicle speed corresponding to the target frame is greater than or equal to a preset speed threshold, then based on the vehicle position information corresponding to each frame, the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame is calculated sequentially, and the total travel distance (dis_sum) is obtained by summing the travel distances of each vehicle. It can be understood that since the vehicle's direction of travel may change during the reversing process, in order to avoid misjudging the reversing scene as a U-turn scene during the scene recognition process, this embodiment needs to calculate the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame, and then calculate the total travel distance, rather than calculating the difference in vehicle position between the target frame and the preset frame.

[0095] Specifically, if the scene from the target frame to the preset frame corresponds to a reversing scene (short-distance movement, such as a slight backward adjustment) , then the calculated total travel distance of the vehicle from the target frame to the preset frame is usually less than the total travel distance of the vehicle from the target frame to the preset frame in a U-turn scene. (Refer to...) Figure 3 Therefore, in order to avoid the autonomous driving algorithm obtained from training and verification being unable to accurately distinguish between reversing scenarios and U-turn scenarios, this embodiment needs to be based on the total driving distance from the target frame to the preset frame during the process of identifying U-turn scenarios.

[0096] To complete an effective U-turn, a vehicle not only needs to travel a certain distance but also needs a certain amount of time. This embodiment calculates the vehicle's travel distance between consecutive frames from the target frame to the preset frame, taking into account both time and space factors, to ensure that the detected action is a continuous one. For example, during the reversing process, some of the vehicle's travel routes may overlap, meaning that the reversing process is not a continuous action.

[0097] Furthermore, if the total driving distance is less than the preset driving distance, it is determined that there is no possibility of the vehicle making a U-turn in the frames between the target frame and the preset frame; this eliminates the possibility of misjudging a vehicle reversing as a U-turn, and further scene recognition is not performed on the scene sub-segment corresponding to the target frame to the preset frame, reducing the waste of computing resources; if the total driving distance is greater than or equal to the preset driving distance, it is determined that there is a possibility of the vehicle making a U-turn in the frames between the target frame and the preset frame, and further scene recognition can be performed on the scene sub-segment corresponding to the target frame to the preset frame.

[0098] The preset driving distance (distance_static) can be 15m or 17m, etc., because the distance required for a vehicle to make a U-turn is longer than that required for a vehicle to turn. For example, if the vehicle's driving distance from frame 0 to frame 100 is less than 15m, it is considered that the vehicle is in a low-speed driving condition or a turning condition from frame 0 to frame 100, and no further scene recognition is performed on that frame. For example, if the vehicle's driving distance from frame 0 to frame 100 is greater than or equal to 15m, it is considered that the vehicle may have made a U-turn from frame 0 to frame 100, and further scene recognition can be performed on that frame.

[0099] Specifically, the vehicle position information and vehicle coordinate information can be the vehicle coordinates coordinate_start(start_x, start_y) in the target frame (frame_i) and the vehicle coordinates coordinate_i(i_x, i_y) in the preset frame (frame_i+1). Based on the vehicle position information corresponding to each frame, the specific implementation of calculating the vehicle travel distance from the target frame to the preset frame can be: calculating the straight-line distance dist between coordinate_start and coordinate_i. If dis_sum is less than distance_static, it is considered that the vehicle from the target frame to the preset frame is insufficient to complete the U-turn operation.

[0100] It is understood that by setting a preset speed threshold and a preset driving distance, this embodiment can effectively filter out frames that are unlikely to make a U-turn, ensuring that only frames that may actually have a U-turn scenario are identified. This embodiment only needs to obtain historical scene segments and accurately obtain the scene recognition results of vehicle U-turns in the historical scene segments through the above method, thereby easily obtaining data on vehicle U-turns.

[0101] Step A2: If it exists, determine the change in the vehicle's driving direction based on the vehicle heading angles corresponding to the target frame and the preset frame, respectively.

[0102] It should be noted that the vehicle heading angle can be obtained through the vehicle box or the vehicle speed. Specifically, the vehicle bounding box is usually detected by visual or distance sensors such as cameras and radar, so the vehicle heading angle can be calculated based on the vehicle bounding box. The vehicle heading angle can also be derived by analyzing the vehicle's velocity vector (including velocity magnitude and direction).

[0103] Because the vehicle's direction of travel can change rapidly during reversing, such as when it alternates between forward and backward movements, even if the total travel distance is greater than or equal to the preset travel distance, it is still possible to misjudge this reversing scenario as a U-turn. Furthermore, since the vehicle's heading angle reflects changes in its direction of travel, this embodiment, upon determining the possibility of a U-turn in the vehicle's direction of travel in each frame between the target frame and the preset frame, determines the change in the vehicle's direction of travel in the corresponding scene sub-segment from the target frame to the preset frame based on the vehicle's heading angle corresponding to the target frame and the preset frame, respectively.

[0104] Step A3: Determine the scene recognition result based on the change in the vehicle's driving direction.

[0105] Furthermore, by analyzing changes in the vehicle's direction of travel, it is possible to determine whether the vehicle is involved in a left U-turn, a right U-turn, or / or not involved in a U-turn scenario, thus obtaining the scene recognition result.

[0106] In this embodiment, historical scene segments are acquired. When an intersection scene exists within the historical scene segment, the scene recognition result is determined based on the data of each frame in the historical scene segment. This avoids misidentifying data from non-critical road sections as U-turn scenes, thereby obtaining accurate scene recognition results for vehicle U-turns within the historical scene segments. Furthermore, by setting preset speed thresholds and preset driving distances, frames that are unlikely to involve U-turns can be effectively filtered out, ensuring that only frames that genuinely suggest U-turns are recognized. This embodiment only requires acquiring historical scene segments and accurately obtaining scene recognition results for vehicle U-turns within those segments using the above method, thus easily obtaining data related to vehicle U-turns.

[0107] 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 4 After step S10, steps B1 to B3 are also included:

[0108] Step B1: Determine whether intersection sign information exists in each frame of data;

[0109] To improve the efficiency and accuracy of intersection scene recognition, this embodiment first determines whether there is intersection signage information in each frame of data; if it exists, the probability that there is an intersection in the scene corresponding to that frame is higher, and if it does not exist, the probability that there is an intersection in the scene corresponding to that frame is lower.

[0110] The specific implementation method for determining whether there is intersection sign information in each frame of data can be: based on the road image in the dynamic perception information, identify whether there is intersection sign information in each frame of data through a preset target recognition model; or it can be to determine whether there is intersection sign information in the traffic sign information in the static map information corresponding to each frame of data.

[0111] The intersection signage information can include speed bumps, intersection warning signs, traffic lights (red and green lights), zebra crossings, etc.

[0112] Step B2: If it exists, calculate the target distance between the intersection and the vehicle based on the intersection sign information;

[0113] It is understandable that since vehicles usually make U-turns when they are about to reach an intersection, in order to effectively filter frames that are unlikely to make U-turns, this embodiment calculates the target distance between the intersection and the vehicle based on the intersection sign information. The intersection sign information includes the coordinate information of the intersection sign. This embodiment can calculate the target distance between the intersection and the vehicle based on the coordinate information of the intersection sign and the coordinate information of the vehicle.

[0114] Specifically, for each frame of data, there may be traffic light information and / or zebra crossing information. If a frame contains traffic light information, then the specific implementation method for calculating the target distance between the intersection and the vehicle based on the intersection sign information can be:

[0115] The first coordinates are converted into second coordinates in the vehicle body coordinate system; based on the second coordinates, the first longitudinal distances between at least one traffic light and the vehicle are calculated; based on the first longitudinal distances, it is determined whether there is a target traffic light in front of the vehicle; if there is, the minimum longitudinal distance among the first longitudinal distances corresponding to the target traffic light is taken as the target distance between the intersection and the vehicle.

[0116] It is understandable that for each frame of data, in this embodiment, when there is traffic light information in the road perception information, since there may be multiple sets of traffic light information at the same time, this embodiment can use the minimum distance from the vehicle to each traffic light as the target distance; if there is only one set of traffic light information, then the distance between that traffic light and the vehicle is directly used as the target distance.

[0117] It should be noted that the traffic light information includes the first coordinates of at least one traffic light in the global coordinate system.

[0118] Because the position and orientation of a vehicle change constantly as it moves in the global coordinate system, this may lead to cumulative errors in the distance between the traffic light and the vehicle calculated based on the global coordinate system. In contrast, the vehicle's own coordinate system always uses the vehicle's own position as a reference point, which can more accurately reflect the vehicle's real-time motion state, thereby reducing the cumulative errors caused by dynamic driving.

[0119] Since U-turns typically occur at a specific distance from an intersection, the accumulated errors in the distance between the traffic lights and the vehicles may affect the accuracy and efficiency of judging U-turn scenarios. In this embodiment, the first coordinate of at least one traffic light in the global coordinate system is converted into the second coordinate in the vehicle's body coordinate system.

[0120] Specifically, a specific implementation method for converting the first coordinates into the second coordinates in the vehicle body coordinate system can be: translating the point in the global coordinate system to the corresponding position in the vehicle body coordinate system.

[0121] Alternatively, a more specific implementation of converting the first coordinates into the second coordinates in the vehicle body coordinate system can be: converting the first coordinates based on a rotation matrix to obtain the second coordinates in the vehicle body coordinate system.

[0122] Specifically, assuming the first coordinates are the coordinates of point P (global_x, global_y), the vehicle's coordinates in the global coordinate system are (base_x, base_y), and the vehicle's heading angle is base_theta; a specific implementation method for transforming the first coordinates based on the rotation matrix to obtain the second coordinates in the vehicle's body coordinate system can be:

[0123] First, calculate the relative position difference between point P and the vehicle:

[0124] x_diff = global_x - base_x;

[0125] y_diff = global_y - base_y;

[0126] Secondly, calculate the cosine value of the vehicle's heading angle, angle_cos, and the sine value, angle_sin:

[0127] angle_cos=math.cos(base_theta);

[0128] angle_sin=math.sin(base_theta);

[0129] Finally, the first coordinates are transformed using the rotation matrix to obtain the second coordinates (local_x, local_y) of point P in the vehicle body coordinate system:

[0130] local_x=x_diff angle_cos-y_diff angle_sin;

[0131] local_y=x_diff angle_sin+y_diff angle_cos;

[0132] Furthermore, local_x represents the longitudinal distance of the traffic light relative to the vehicle, and local_y represents the lateral distance of the traffic light relative to the vehicle; therefore, based on the second coordinate of at least one traffic light in the vehicle's body coordinate system, the first longitudinal distance between at least one traffic light and the vehicle can be accurately calculated.

[0133] Furthermore, in this embodiment, based on the first longitudinal distance, it is determined whether there is a target traffic light in front of the vehicle. Specifically, when the first longitudinal distance is greater than zero, it is determined that the corresponding target traffic light is in front of the vehicle; when the first longitudinal distance is equal to zero, it is determined that the corresponding target traffic light is parallel to the vehicle; and when the first longitudinal distance is greater than zero, it is determined that the corresponding target traffic light is behind the vehicle.

[0134] Because a vehicle makes a U-turn accurately usually before entering an intersection, that is, when the traffic light is in front of the vehicle.

[0135] To improve judgment efficiency, this embodiment uses the minimum distance (traffic_local_x_min) in the first longitudinal distance corresponding to the target traffic light in front of the vehicle as the target distance between the intersection and the vehicle.

[0136] If traffic light information (traffic_lights_infos) is not present in a certain frame, then the minimum longitudinal distance (traffic_local_x_min) and minimum lateral distance (traffic_local_y_min) from the traffic light to the vehicle are both assigned large positive values ​​(such as 10000) to indicate that there is no intersection ahead.

[0137] In addition, for each frame of data, when there is crosswalk information (crosswalks_infos) in the road perception information, since there may be multiple sets of crosswalk information at the same time, this embodiment can use the minimum distance from the vehicle to each crosswalk as the target distance.

[0138] Specifically, the method for calculating the target distance between the intersection and the vehicle based on the intersection signage information can be as follows: converting the third coordinate into a fourth coordinate in the vehicle's body coordinate system; calculating the second longitudinal distance between each corner point and the vehicle based on the fourth coordinate; determining whether there is a target zebra crossing in front of or below the vehicle based on the second longitudinal distance; if so, taking the minimum longitudinal distance among the second longitudinal distances corresponding to the target zebra crossing as the target distance between the intersection and the vehicle.

[0139] It should be noted that the zebra crossing information includes the third coordinates of all corner points of at least one zebra crossing corresponding to the rectangle in the global coordinate system.

[0140] Since U-turns typically occur at a specific distance from an intersection, the accuracy of calculating the target distance between the vehicle and the intersection is crucial for identifying U-turn scenarios. Furthermore, because a vehicle may pass a crosswalk during a U-turn, or may begin its U-turn while on a crosswalk, this embodiment requires calculating the distances between the vehicle and all corner points of the rectangle corresponding to each crosswalk, rather than just one corner point. This avoids misjudging a crosswalk as being behind a vehicle if one corner point is behind it, when in fact other corner points may be in front of the vehicle (i.e., misjudging a crosswalk below the vehicle as being behind it).

[0141] Meanwhile, in order to avoid the cumulative error causing the distance error between the traffic light and the vehicle to affect the accuracy and efficiency of the judgment in the U-turn scenario, this embodiment converts the third coordinates of all corner points of at least one zebra crossing corresponding to the rectangle in the global coordinate system into the fourth coordinates in the vehicle body coordinate system.

[0142] Assuming that all corner points of the rectangle corresponding to each zebra crossing are point_1, point_2, point_3, and point_4, using the coordinate transformation method described above, the four corner points point_1, point_2, point_3, and point_4 are converted into the fourth coordinates local_piont_1(local_x, local_y), local_piont_2(local_x, local_y), local_piont_3(local_x, local_y), and local_piont_4(local_x, local_y) in the vehicle body coordinate system, respectively. Here, local_x represents the longitudinal distance of the corner point from the vehicle, and local_y represents the lateral distance of the corner point from the vehicle. Therefore, based on the fourth coordinates, the second longitudinal distance between each corner point and the vehicle can be accurately calculated.

[0143] Furthermore, this embodiment determines whether a target zebra crossing exists in front of or below the vehicle based on the second longitudinal distance. Specifically, if at least one corner of the target zebra crossing has a second longitudinal distance greater than or equal to zero from the vehicle, the target zebra crossing is determined to be in front of or below the vehicle; if all corners of the target zebra crossing have a second longitudinal distance less than zero from the vehicle, the target zebra crossing is determined to be behind the vehicle.

[0144] If all corner points of the target zebra crossing have a second longitudinal distance greater than zero from the vehicle, then the target zebra crossing is determined to be in front of the vehicle.

[0145] Because a vehicle makes a U-turn accurately usually before entering an intersection, that is, when the traffic light is in front of the vehicle.

[0146] To improve judgment efficiency, this embodiment uses the minimum longitudinal distance (crosswalks_local_x_min) in the second longitudinal distance corresponding to the target zebra crossing as the target distance between the intersection and the vehicle.

[0147] If traffic light information (traffic_lights_infos) is not present in a certain frame, then the minimum longitudinal distance (crosswalks_local_x_min) and minimum lateral distance (crosswalks_local_y_min) from the traffic light to the vehicle are both assigned large positive values ​​(such as 10000) to indicate that there is no intersection ahead.

[0148] If a frame contains both traffic light information and zebra crossing information, the minimum distance in the first longitudinal distance corresponding to the target zebra crossing can be used as the target distance between the intersection and the vehicle, or the minimum distance in the second longitudinal distance corresponding to the target traffic light can be used as the target distance between the intersection and the vehicle, or the smaller distance between the minimum distance in the first longitudinal distance and the minimum distance in the second longitudinal distance can be used as the target distance.

[0149] Step B3: When the target distance is less than a preset distance threshold, it is determined that there is an intersection scene in the historical scene segment.

[0150] It is understood that if the minimum distance in the first longitudinal distance corresponding to the target zebra crossing is less than a preset distance threshold, or the minimum distance in the second longitudinal distance corresponding to the target traffic light is less than a preset distance threshold (valid_dist_threshold), then the vehicle is considered to be close enough to the intersection, and the intersection is considered a valid intersection.

[0151] That is, if traffic_local_x_min is less than valid_dist_threshold, or crosswalks_local_x_min is less than valid_dist_threshold, then the frame is considered to have a valid intersection; otherwise, the frame does not have a valid intersection. If all frames in the historical scene segment do not have valid intersections, then the historical scene segment will not be further identified for vehicle U-turn scenarios.

[0152] This embodiment accurately identifies whether there are valid intersections in historical scene segments through the above method, thereby improving the accuracy of data acquisition regarding vehicle turning scenarios.

[0153] 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 Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5 Step A2 also includes steps C1 to C2:

[0154] Step C1: Calculate the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame, respectively;

[0155] It should be noted that when it is determined that there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame, it is still impossible to determine whether a U-turn actually occurred or not. This embodiment accurately captures the change of the vehicle's driving direction from the target frame to the preset frame by calculating the angle difference between the vehicle's heading angles corresponding to the target frame and the preset frame respectively.

[0156] For example, calculate the angle difference (theta_end - theta_start) between the vehicle heading angle (theta_start) corresponding to the target frame (frame_i) and the vehicle heading angle (theta_end) corresponding to the preset frame (frame_i+100).

[0157] Step C2: Based on the angle difference, determine the change in the vehicle's driving direction in the corresponding scene sub-segment from the target frame to the preset frame;

[0158] Since the angle difference can reflect the change in the vehicle's driving direction from the target frame to the preset frame, this embodiment can determine the change in the vehicle's driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference. For example, when the angle difference is within a certain range, it can be considered that the vehicle has made a U-turn; if it is not within that range, it can be considered that the vehicle has not made a U-turn.

[0159] Alternatively, the specific implementation method for determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference can also be:

[0160] The angle difference is normalized; if the normalized angle difference is within the first angle interval, the change in the vehicle's driving direction is determined to be a left U-turn; if the normalized angle difference is within the second angle interval, the change in the vehicle's driving direction is determined to be a right U-turn; if the normalized angle difference is within the third angle interval, the change in the vehicle's driving direction is determined to be no U-turn; wherein, there is no intersection between the first angle interval, the second angle interval, and the third angle interval.

[0161] It should be noted that, in scenarios where a vehicle turns left or right, the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame may be - 2 3 6 In order to facilitate the subsequent judgment of the driving operation type corresponding to the angle difference, this embodiment normalizes the angle difference to make the judgment of the change in the vehicle's driving direction more intuitively, simply and accurately.

[0162] The normalization of the angle difference can be achieved by normalizing the angle difference to the same quantization standard, for example, by normalizing the angle difference to [0, 2]. )or(- , ) etc.; specifically, the angle difference is normalized to [0, 2 The calculation formula within the range can be: Normalized angle difference (theta_diff) = (theta_end - theta_start + 2) )% (2 ).

[0163] Correspondingly, a first angle interval, a second angle interval, and a third angle interval can be set to represent the intervals containing the corresponding angle differences in the scene. There is no overlap between the first angle interval, the second angle interval, and the third angle interval. It can be understood that the first angle interval can be... The second angular interval can be The third angle interval can be and That is, there is no intersection between the first angle interval, the second angle interval, and the third angle interval.

[0164] It is understandable that, since the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame is normalized to the same quantization standard, the change in the vehicle's driving direction can be determined simply by comparing the angles, without causing - 6 In situations where the same standard cannot be directly used for comparison at the same angle, this improves data processing efficiency.

[0165] Specifically, if the normalized angle difference is within the first angle range, the change in the vehicle's driving direction is determined to be a left U-turn; if the normalized angle difference is within the second angle range, the change in the vehicle's driving direction is determined to be a right U-turn; if the normalized angle difference is within the third angle range, the change in the vehicle's driving direction is determined to be no U-turn. It can be understood that if the normalized angle difference is within the third angle range, the change in the vehicle's driving direction may be straight, left turn, right turn, or stationary.

[0166] Furthermore, after determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference, the following steps can be taken: update the target frame to a frame that slides backward a preset number of frames, return to the step of determining whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame, until the preset frame is the end frame, thereby obtaining the change in vehicle driving direction in multiple scene sub-segments from the start frame to the end frame.

[0167] Since the above only determines whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame, and the change of the vehicle's driving direction in the scene sub-segment between the target frame and the preset frame, in order to determine the change of the vehicle's driving direction in multiple scene sub-segments from the start frame to the end frame, the target frame can be updated to a frame that slides backward a preset number of frames, and the step of determining whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame can be returned until the preset frame is the end frame.

[0168] The preset frame number can be less than the frame number corresponding to the preset frame length, thereby increasing the number of scene sub-segments identified without missing the identification of each frame of data in the historical scene segments; the preset frame number can also be equal to the frame number corresponding to the preset frame length, reducing repeated scenes and improving scene recognition efficiency; the preset frame number can also be greater than the frame number corresponding to the preset frame length but less than (N-100 frames), thereby reducing the number of scene sub-segments to be identified and improving data processing efficiency.

[0169] In order to increase the number of identified scene sub-segments without missing the identification of each frame of data in the historical scene segments, this embodiment can return to the step of judging whether the vehicle has the possibility of making a U-turn in each frame between the target frame and the preset frame every 20 frames or every 50 frames, until the preset frame is the end frame (that is, until all frames have been traversed).

[0170] Furthermore, the specific implementation of determining the scene recognition result based on the change in the vehicle's driving direction can be: determining the scene recognition result of the multiple scene sub-segments based on the change in the vehicle's driving direction in the multiple scene sub-segments corresponding to the start frame to the end frame.

[0171] It can be understood that if the vehicle's direction of travel changes in the scene sub-segment from frame 0 to frame 100 as a left U-turn, the vehicle's direction of travel changes in the scene sub-segment from frame 20 to frame 120 as no U-turn occurs, ..., and the vehicle's direction of travel changes in the scene sub-segment from frame (N-100) to frame N as a right U-turn, then the corresponding scene recognition results from frame 0 to frame 100 are: a scene with a vehicle making a left U-turn; the scene recognition results from frame 20 to frame 120 are: a scene with no vehicle making a U-turn occurs, ..., and the scene recognition results from frame (N-100) to frame N are: a scene with a vehicle making a right U-turn occurs.

[0172] Furthermore, after determining the scene recognition result based on the change in the vehicle's driving direction, it is also possible to: determine the moment of the vehicle's U-turn based on a target scene sub-segment where a U-turn is possible.

[0173] Since the changes in the vehicle's driving direction in multiple scene sub-segments from the start frame to the end frame are obtained through the above method, the U-turn time corresponding to the target scene sub-segment where a vehicle U-turn occurs can be determined.

[0174] For example, the target scene sub-segments containing vehicle U-turns include the scene sub-segments corresponding to frames 0 to 100, frames 80 to 180, ..., and frames (N-100) to N. In order to obtain high-quality training data, the vehicle U-turn times (including the vehicle left U-turn times and the vehicle right U-turn times) can be determined based on the above target scene sub-segments containing vehicle U-turns. For example, the vehicle left U-turn times are frames 0 to 100, and the vehicle right U-turn times are frames (N-100) to N.

[0175] This embodiment can quickly locate vehicle left U-turn and vehicle right U-turn scenarios in historical scene segments using the above method, and can accurately locate the time of the vehicle left U-turn and the time of the vehicle right U-turn; thereby obtaining more detailed data about vehicle turning scenarios.

[0176] This application also provides a U-shaped turn scene recognition device, please refer to... Figure 6 The U-shaped turn scene recognition device includes:

[0177] Module 10 is used to acquire historical scene fragments;

[0178] The recognition module 20 is used to determine the scene recognition result based on the data of each frame in the historical scene segment when there is an intersection scene in the historical scene segment. The scene recognition result includes whether there is a left U-turn scene, a right U-turn scene, and / or no U-turn scene in the historical scene segment.

[0179] In one embodiment, the identification module 20 includes:

[0180] The first judgment submodule is used to determine whether there is a possibility of a U-shaped turn in the vehicle corresponding to each frame between the target frame and the preset frame. The target frame includes the starting frame, and the preset frame is spaced apart from the target frame by a preset frame length.

[0181] The determination submodule is used to determine the change in the vehicle's driving direction based on the vehicle heading angles corresponding to the target frame and the preset frame, if such a submodule exists.

[0182] The recognition submodule is used to determine the scene recognition result based on the changes in the vehicle's driving direction.

[0183] In one embodiment, the first determination submodule includes:

[0184] The judgment unit is used to determine whether the vehicle speed corresponding to the target frame data is less than a preset speed threshold.

[0185] The first calculation unit is used to calculate the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame, based on the vehicle position information corresponding to each frame, if the vehicle speed is greater than or equal to a preset speed threshold.

[0186] The summation unit is used to sum the distances traveled by each vehicle to obtain the total distance traveled.

[0187] The second determining unit is used to determine the possibility that the vehicle corresponding to each frame between the target frame and the preset frame has a U-shaped turn if the total driving distance is greater than or equal to the preset driving distance.

[0188] In one embodiment, the determining submodule includes:

[0189] The second calculation unit is used to calculate the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame, respectively.

[0190] The second determining unit is used to determine the change in the vehicle's driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference.

[0191] After the step of determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference, the determining sub-module further includes:

[0192] The return unit is used to update the target frame to a frame that slides backward a preset number of frames, and return to the step of determining whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame, until the preset frame is the end frame, so as to obtain the change of the vehicle's driving direction in multiple scene sub-segments from the start frame to the end frame.

[0193] In one embodiment, the second determining unit includes:

[0194] A normalization subunit is used to normalize the angle difference;

[0195] The first determining subunit is used to determine that the change in the vehicle's driving direction is a left U-turn if the normalized angle difference is within the first angle range.

[0196] The second determining subunit is used to determine that the change in the vehicle's driving direction is a right U-turn if the normalized angle difference is within the second angle range.

[0197] The third determining subunit is used to determine that the change in the vehicle's driving direction is not a U-turn if the normalized angle difference is within the third angle interval.

[0198] There is no overlap between the first angle interval, the second angle interval, and the third angle interval.

[0199] In one embodiment, the identification submodule includes:

[0200] The third determining unit is used to determine the scene recognition result of the multiple scene sub-segments based on the changes in the vehicle driving direction in the multiple scene sub-segments corresponding to the starting frame to the ending frame;

[0201] After the step of determining the scene recognition result based on the change in the vehicle's driving direction, the U-shaped turn scene recognition device further includes:

[0202] The first determining module is used to determine the moment when a vehicle makes a U-turn based on a target scene sub-segment where a U-turn scenario exists.

[0203] In one embodiment, after the step of acquiring historical scene fragments, the U-shaped turn scene recognition device further includes:

[0204] The judgment module is used to determine whether intersection sign information exists in each frame of data;

[0205] The calculation module is used to calculate the target distance between the intersection and the vehicle based on the intersection signage information, if such a distance exists.

[0206] The second determining module is used to determine that an intersection scene exists in the historical scene segment when the target distance is less than a preset distance threshold.

[0207] In one embodiment, the intersection signage information includes traffic light information, the traffic light information including the first coordinates of at least one traffic light in a global coordinate system, and the calculation module includes:

[0208] The first transformation submodule is used to convert the first coordinates into second coordinates in the vehicle body coordinate system;

[0209] The first calculation submodule is used to calculate the first longitudinal distance between at least one traffic light and the vehicle based on the second coordinates;

[0210] The second judgment submodule is used to determine whether there is a target traffic light in front of the vehicle based on the first longitudinal distance;

[0211] The first setting submodule is used to, if it exists, take the minimum longitudinal distance in the first longitudinal distance corresponding to the target traffic light as the target distance between the intersection and the vehicle.

[0212] The second judgment submodule includes:

[0213] The fourth determining unit is used to determine that the corresponding target traffic light is in front of the vehicle when the first longitudinal distance is greater than zero.

[0214] In one embodiment, the intersection signage information further includes zebra crossing information, which includes the third coordinates of all corner points of at least one zebra crossing corresponding to a rectangle in the global coordinate system. The calculation module includes:

[0215] The second transformation submodule is used to convert the third coordinate into a fourth coordinate in the vehicle body coordinate system;

[0216] The second calculation submodule is used to calculate the second longitudinal distance between each corner point and the vehicle based on the fourth coordinate.

[0217] The third judgment submodule is used to determine whether there is a target zebra crossing in front of or under the vehicle based on the second longitudinal distance;

[0218] The second setting submodule is used to, if it exists, take the minimum longitudinal distance in the second longitudinal distance corresponding to the target zebra crossing as the target distance between the intersection and the vehicle.

[0219] The third judgment submodule includes:

[0220] The sixth determining unit is used to determine that the target zebra crossing is in front of or under the vehicle if at least one corner of the target zebra crossing is greater than or equal to zero in the second longitudinal distance between the target zebra crossing and the vehicle.

[0221] The seventh determining unit is used to determine that the target zebra crossing is behind the vehicle if all corner points of the target zebra crossing are less than zero in the second longitudinal distance from the vehicle.

[0222] The U-turn scene recognition device provided in this application, employing the U-turn scene recognition method in the above embodiments, can solve the technical problem of the high difficulty in acquiring data related to vehicle turning scenes. Compared with the prior art, the beneficial effects of the U-turn scene recognition device provided in this application are the same as those of the U-turn scene recognition method provided in the above embodiments, and other technical features in the U-turn scene recognition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0223] This application provides a U-turn 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 U-turn scene recognition method in the above embodiment 1.

[0224] The following is for reference. Figure 7 The diagram illustrates a structural schematic of a U-turn scene recognition device suitable for implementing embodiments of this application. The U-turn scene recognition device in this application may include, but is not limited to, mobile terminals such as mobile phones, tablets, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The U-shaped turn 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.

[0225] like Figure 7As shown, the U-turn 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 U-turn 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. The communication device 1009 allows the U-turn scene recognition device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show U-turn scene recognition devices with various systems, it should be understood that implementing or having all of the systems shown is not required. More or fewer systems may be implemented alternatively.

[0226] 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.

[0227] The U-turn scene recognition device provided in this application, employing the U-turn scene recognition method in the above embodiments, can solve the technical problem of the high difficulty in acquiring data related to vehicle turning scenes. Compared with the prior art, the beneficial effects of the U-turn scene recognition device provided in this application are the same as those of the U-turn scene recognition method provided in the above embodiments, and other technical features in this U-turn scene recognition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0228] 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.

[0229] 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 technical scope 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 protection of the claims.

[0230] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the U-turn scene recognition method in the above embodiments.

[0231] 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, 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, 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.

[0232] The aforementioned computer-readable storage medium may be included in the U-turn scene recognition device; or it may exist independently and not be assembled into the U-turn scene recognition device.

[0233] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the U-turn scene recognition device, cause the U-turn scene recognition device to perform the aforementioned U-turn scene recognition method.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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 U-turn scene recognition method, which can solve the technical problem of the high difficulty in acquiring data on vehicle turning scenes. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the U-turn scene recognition method provided in the above embodiments, and will not be repeated here.

[0238] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the U-turn scene recognition method described above.

[0239] The computer program product provided in this application can solve the technical problem of the high difficulty in acquiring data on vehicle turning scenarios. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the U-shaped turn scene recognition method provided in the above embodiments, and will not be repeated here.

[0240] 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 content of this application specification and drawings, 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 U-shaped turns, characterized in that, The U-shaped turn scene recognition method includes: Obtain historical scene fragments; When there is an intersection scene in the historical scene segment, it is determined whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame. The target frame includes the starting frame, and the preset frame is spaced apart from the target frame by a preset frame length. If it exists, the change in the vehicle's driving direction is determined based on the vehicle heading angles corresponding to the target frame and the preset frame, respectively. Based on the changes in the vehicle's driving direction, a scene recognition result is determined, wherein the scene recognition result includes the presence of a left U-turn scene, a right U-turn scene, and / or the absence of a U-turn scene in the historical scene segment; The step of determining whether there is a possibility of a U-turn for the vehicle in each frame between the target frame and the preset frame includes: Determine whether the vehicle speed corresponding to the target frame data is less than a preset speed threshold; If the vehicle speed is greater than or equal to a preset speed threshold, then based on the vehicle position information corresponding to each frame, the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame is calculated sequentially to take into account both time and space factors. Sum the distances traveled by each vehicle to obtain the total distance traveled. If the total driving distance is greater than or equal to the preset driving distance, then it is determined that there is a possibility that the vehicle in each frame between the target frame and the preset frame may make a U-turn.

2. The U-shaped turn scene recognition method as described in claim 1, characterized in that, The step of determining the change in vehicle direction based on the vehicle heading angles corresponding to the target frame and the preset frame includes: Calculate the angle difference between the vehicle heading angles corresponding to the target frame and the preset frame, respectively; Based on the angle difference, the change in the vehicle's driving direction in the corresponding scene sub-segment from the target frame to the preset frame is determined.

3. The U-shaped turn scene recognition method as described in claim 2, characterized in that, After determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference, the method further includes: Update the target frame to the frame that slides back two frames, return to the step of determining whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame, until the preset frame is the end frame, and obtain the changes in the vehicle's driving direction in multiple scene sub-segments corresponding to the start frame to the end frame.

4. The U-shaped turn scene recognition method as described in claim 2, characterized in that, The step of determining the change in vehicle driving direction in the corresponding scene sub-segment from the target frame to the preset frame based on the angle difference includes: The angle difference is normalized. If the normalized angle difference is within the first angle range, then the change in the vehicle's driving direction is determined to be a left U-turn. If the normalized angle difference is within the second angle range, then the change in the vehicle's driving direction is determined to be a right U-turn. If the normalized angle difference is within the third angle range, then the change in the vehicle's driving direction is determined to be that no U-turn has occurred. There is no overlap between the first angle interval, the second angle interval, and the third angle interval.

5. The U-shaped turn scene recognition method as described in claim 3, characterized in that, The step of determining the scene recognition result based on the change in the vehicle's driving direction includes: Based on the changes in the vehicle's driving direction in multiple scene sub-segments corresponding to the start frame to the end frame, the scene recognition results of the multiple scene sub-segments are determined; After determining the scene recognition result based on the change in the vehicle's driving direction, the method further includes: Based on a target scene sub-segment where a vehicle makes a U-turn, determine the moment when the vehicle makes the U-turn.

6. The U-shaped turn scene recognition method as described in claim 1, characterized in that, Following the step of acquiring historical scene fragments, the method further includes: Determine whether intersection signage information exists in each frame of data; If it exists, the target distance between the intersection and the vehicle is calculated based on the intersection signage information; When the target distance is less than a preset distance threshold, it is determined that there is an intersection scene in the historical scene segment.

7. The U-shaped turn scene recognition method as described in claim 6, characterized in that, The intersection signage information includes traffic light information, which includes the first coordinates of at least one traffic light in a global coordinate system. The step of calculating the target distance between the intersection and the vehicle based on the intersection signage information includes: Convert the first coordinates into a second coordinate in the vehicle body coordinate system; Based on the second coordinates, calculate the first longitudinal distance between at least one traffic light and the vehicle; Based on the first longitudinal distance, determine whether there is a target traffic light ahead of the vehicle; If it exists, the minimum longitudinal distance in the first longitudinal distance corresponding to the target traffic light shall be taken as the target distance between the intersection and the vehicle; The step of determining whether there is a target traffic light ahead of the vehicle based on the first longitudinal distance includes: When the first longitudinal distance is greater than zero, the corresponding target traffic light is determined to be in front of the vehicle.

8. The U-shaped turn scene recognition method as described in claim 6, characterized in that, The intersection signage information also includes zebra crossing information, which includes the third coordinates of all corner points of at least one zebra crossing's corresponding rectangle in the global coordinate system. The step of calculating the target distance between the intersection and the vehicle based on the intersection signage information includes: The third coordinate is converted into a fourth coordinate in the vehicle body coordinate system; Based on the fourth coordinate, calculate the second longitudinal distance between each corner point and the vehicle; Based on the second longitudinal distance, determine whether there is a target zebra crossing in front of or under the vehicle; If it exists, the minimum longitudinal distance in the second longitudinal distance corresponding to the target zebra crossing shall be taken as the target distance between the intersection and the vehicle. The step of determining whether a target zebra crossing exists in front of or below the vehicle based on the second longitudinal distance includes: If at least one corner of the target zebra crossing is at a second longitudinal distance greater than or equal to zero from the vehicle, then the target zebra crossing is determined to be in front of or under the vehicle. If all corner points of the target zebra crossing are less than zero from the second longitudinal distance of the vehicle, then the target zebra crossing is determined to be behind the vehicle.

9. A U-shaped turn scene recognition device, characterized in that, The U-shaped turn scene recognition device includes: The acquisition module is used to acquire historical scene fragments; The identification module includes: The first judgment submodule is used to determine whether there is a possibility of a U-shaped turn for the vehicle in each frame between the target frame and the preset frame when there is an intersection scene in the historical scene segment. The target frame includes the starting frame, and the preset frame is spaced apart from the target frame by a preset frame length. The determination submodule is used to determine the change in the vehicle's driving direction based on the vehicle heading angles corresponding to the target frame and the preset frame, if such a submodule exists. The recognition submodule is used to determine the scene recognition result based on the change in the vehicle's driving direction, wherein the scene recognition result includes the presence of a left U-turn scene, a right U-turn scene, and / or the absence of a U-turn scene in the historical scene segment; The first judgment submodule includes: The judgment unit is used to determine whether the vehicle speed corresponding to the target frame data is less than a preset speed threshold. The first calculation unit is used to calculate the vehicle travel distance between each pair of consecutive frames from the target frame to the preset frame based on the vehicle position information corresponding to each frame if the vehicle speed is greater than or equal to a preset speed threshold, so as to consider both time and space factors at the same time. The summation unit is used to sum the distances traveled by each vehicle to obtain the total distance traveled. The second determining unit is used to determine the possibility that the vehicle corresponding to each frame between the target frame and the preset frame has a U-shaped turn if the total driving distance is greater than or equal to the preset driving distance.

10. A U-shaped turn scene recognition device, characterized in that, The U-turn scene recognition 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 U-turn scene recognition method as described in any one of claims 1 to 8.

11. 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 U-shaped turn scene recognition method as described in any one of claims 1 to 8.

12. 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 U-turn scene recognition method as described in any one of claims 1 to 8.

Images