Lane change identification method and device, equipment, storage medium and product

Abstract

The invention discloses a lane changing recognition method, device and equipment, a storage medium and a product, and relates to the technical field of intelligent driving. Determining a current lane scene, wherein the current lane scene comprises a lane separation scene and / or a lane combination scene; according to the driving map topological relation information and the driving scene target data frame, lane separation lane change identification is carried out on the lane separation scene, and / or lane combination lane change identification is carried out on the lane combination scene. Therefore, the behavior recognition accuracy of the intelligent driving system during lane separation and lane combination of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a lane change recognition method, device, equipment, storage medium and product. Background Art

[0002] With the rapid development of intelligent driving technology, lane change recognition of traffic participants (vehicles, agents) has become one of the key technologies in this field. Accurate recognition of lane change behavior is crucial for vehicle intention recognition and trajectory prediction, which is directly related to the safety and reliability of intelligent driving systems.

[0003] In existing technologies, lane change recognition usually relies on vehicle trajectory data and behavior pattern analysis. These methods can identify the vehicle's lane change behavior to a certain extent, but they are often limited by sensor accuracy, environmental factors, and data processing capabilities. Especially in complex traffic scenarios, such as merging lanes or separating lanes, existing technologies have difficulty accurately capturing the vehicle's lane change behavior, resulting in insufficient accuracy of the prediction model during reasoning.

[0004] The defects of the existing technology are mainly manifested in the following aspects: first, the insufficient understanding of the lane topology makes it difficult to accurately identify the vehicle's lane change in the scenario of lane merging or separation; second, the existing algorithms often lack sufficient consideration when dealing with the lane correlation between consecutive frames, which leads to misjudgment or omission of the vehicle's lane change behavior when tracking the continuous movement of the vehicle during lane separation or identification.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a lane change recognition method, device, equipment, storage medium and computer program product, aiming to improve the accuracy of the intelligent driving system's behavior recognition of vehicles when performing lane separation and / or lane merging.

[0007] To achieve the above objectives, the present application proposes a lane change recognition method, the method comprising:

[0008] Obtain driving map topology relationship information and driving scene target data frame;

[0009] Determining a current lane scenario, wherein the current lane scenario includes a lane separation scenario and / or a lane merging scenario;

[0010] The lane separation and lane change recognition is performed on the lane separation scenario according to the driving map topological relationship information and the driving scene target data frame, and / or the lane merging and lane change recognition is performed on the lane merging scenario.

[0011] In one embodiment, the driving map topology relationship information includes lane information, the driving scene target data frame includes a scene current frame and a scene previous frame, and after the step of obtaining the driving map topology relationship information and the driving scene target data frame, the step further includes:

[0012] Determine a vehicle lane in a current frame and a lane sequence in a current frame according to the current frame of the scene and the lane information;

[0013] A vehicle lane in a previous frame and a lane sequence in a previous frame are determined according to a previous frame of the scene and the lane information.

[0014] In one embodiment, the driving scene target data frame further includes a historical frame and a future frame, and the step of performing lane separation lane change recognition for the lane separation scene and / or performing lane merging lane change recognition for the lane merging scene according to the driving map topological relationship information and the driving scene target data frame includes:

[0015] Calculate a first stability of the vehicle corresponding to the lane sequence of the current frame and a second stability of the vehicle corresponding to the lane sequence of the previous frame based on the historical frame, the future frame and the lane information;

[0016] Based on the first vehicle stability and the second vehicle stability, performing lane separation and lane change recognition on the lane separation scenario; and / or

[0017] Based on the first vehicle stability and the second vehicle stability, lane merging and lane change recognition is performed on the lane merging scenario.

[0018] In one embodiment, the lane information includes a lane orientation angle, and the step of performing lane separation and lane change recognition on the lane separation scenario based on the first stability of the vehicle and the second stability of the vehicle includes:

[0019] Obtaining vehicle and lane binding data in the future frame;

[0020] Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the future frame as the future frame associated lane;

[0021] Determining whether the future frame associated lane is consistent with the previous frame vehicle lane;

[0022] If the future frame associated lane is inconsistent with the previous frame vehicle lane, determining whether the first vehicle stability and the second vehicle stability both exceed a preset stability threshold;

[0023] If both the first vehicle stability and the second vehicle stability exceed a preset stability threshold, lane separation recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

[0024] In one embodiment, the step of performing lane merging and lane change recognition on the lane merging scenario based on the first stability of the vehicle and the second stability of the vehicle includes:

[0025] Obtaining vehicle and lane binding data in the historical frame;

[0026] Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the historical frame as the historical frame associated lane;

[0027] Determining whether the lane associated with the historical frame is consistent with the vehicle lane of the previous frame;

[0028] If the lane associated with the historical frame is inconsistent with the vehicle lane of the previous frame, determining whether both the first stability of the vehicle and the second stability of the vehicle exceed a preset stability threshold;

[0029] If both the first vehicle stability and the second vehicle stability exceed a preset stability threshold, lane merging recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

[0030] In one embodiment, the step of performing lane separation recognition based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame includes:

[0031] Determine whether a first difference between the orientation angle of the vehicle lane of the current frame and the orientation angle of the vehicle lane of the previous frame is greater than a preset angle threshold;

[0032] If the first difference is greater than a preset angle threshold, a result of the vehicle performing a lane separation lane change is obtained;

[0033] The step of performing lane merging recognition based on the orientation angle of the vehicle lane of the previous frame and the orientation angle of the vehicle lane of the current frame includes:

[0034] Determine whether a second difference between the orientation angle of the vehicle lane in the current frame and the orientation angle of the vehicle lane in the previous frame is greater than a preset angle threshold;

[0035] If the second difference is greater than the preset angle threshold, the result of the vehicle performing lane merging and lane changing is obtained.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a lane change recognition device, the lane change recognition device comprising:

[0037] An acquisition module is used to obtain driving map topology relationship information and driving scene target data frames;

[0038] A determination module, configured to determine a current lane scenario, wherein the current lane scenario includes a lane separation scenario and / or a lane merging scenario;

[0039] The recognition module is used to perform lane separation lane change recognition for the lane separation scenario and / or lane merging lane change recognition for the lane merging scenario according to the driving map topological relationship information and the driving scene target data frame.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a lane change 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 lane change recognition method described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which 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, the steps of the lane change recognition method described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the lane change recognition method described above are implemented.

[0043] One or more technical solutions proposed in the present application obtain driving map topological relationship information and driving scene target data frames; determine the current lane scene, and the current lane scene includes a lane separation scene and / or a lane merging scene; perform lane separation and lane change recognition for the lane separation scene according to the driving map topological relationship information and the driving scene target data frames, and / or perform lane merging and lane change recognition for the lane merging scene. Through the above solutions, the behavior of the vehicle in the lane separation scenario and the lane merging scenario is recognized, thereby improving the accuracy of the intelligent driving system in recognizing the behavior of the vehicle when performing lane separation and lane merging. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A flowchart diagram of the first embodiment of the lane change recognition method of the present application is provided;

[0047] Figure 2 A schematic diagram of lane types for the lane change recognition method of this application;

[0048] Figure 3 This is a schematic diagram of lane change recognition in a lane separation scenario of the lane change recognition method of this application;

[0049] Figure 4 This is a schematic diagram of lane change recognition in a lane merging scenario of the lane change recognition method of this application;

[0050] Figure 5 A flowchart diagram of the second embodiment of the lane change recognition method of the present application is provided;

[0051] Figure 6 This is a schematic diagram of the module structure of the lane change recognition device according to an embodiment of the present application;

[0052] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the lane change recognition method in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The main solution of the embodiment of this application is to propose an intelligent lane change recognition algorithm for high-precision map environment, specifically for the two complex scenarios of merging lanes and separating lanes. The logical flow and key technical points of the algorithm are as follows:

[0057] First, the algorithm constructs a detailed map topology in each frame of data, including lane information (lane_info) and the relationship between lanes (lane_to_lane). Lane information covers key parameters such as the track point coordinates of the lane, the midline point coordinates of the sub-segment, the start and end point coordinates, length, and direction. The relationship between lanes clarifies the adjacent lane information of the lane, including the left and right adjacent lanes and the front and following lanes.

[0058] Secondly, for each vehicle agent in each frame, the algorithm determines the lanes of the vehicle in the current frame and the previous frame through the vehicle lane binding algorithm and records the lane numbers. If the lane numbers in two consecutive frames are inconsistent, the vehicle is considered a candidate for lane change.

[0059] Then, the algorithm makes a specific judgment based on whether the lane is a merging lane or a split lane. If it is a split lane scenario, the algorithm calculates the stability of the lane sequence to which the vehicle belongs in the historical frame (prev_lane_rate) and predicts the lane sequence to which the vehicle belongs in the future frame. By comparing the current frame and the predicted lane sequence, combined with the stability threshold (rate_threshold), the heading angle difference (heading_diff) of the two lanes is further calculated, and the lane angle difference threshold (heading_threshold) is used to determine whether the lane change behavior occurs.

[0060] For the merging lane scenario, the algorithm has similar logic but in the opposite direction. It calculates the stability of the lane sequence (curr_lane_rate) of the vehicle in the current frame and reviews the branch lane sequence of the vehicle in the historical frame. It also combines the stability threshold and the lane orientation angle difference to determine the lane change behavior.

[0061] Finally, the algorithm achieved high-accuracy recognition of vehicle lane-changing behavior through the above steps, combined with high-precision map data and dynamic information of vehicles in time series, especially in complex traffic scenarios where lanes merge or separate. This solution significantly improves the accuracy and reliability of lane-changing recognition in intelligent driving systems through detailed lane topology construction and vehicle behavior analysis.

[0062] In existing technologies, lane change recognition usually relies on vehicle trajectory data and behavior pattern analysis. These methods can identify the vehicle's lane change behavior to a certain extent, but they are often limited by sensor accuracy, environmental factors, and data processing capabilities. Especially in complex traffic scenarios, such as merging lanes or separating lanes, existing technologies are difficult to accurately capture the vehicle's lane change behavior, resulting in insufficient accuracy of the prediction model during reasoning.

[0063] The defects of the existing technology are mainly manifested in the following aspects: First, the insufficient understanding of the lane topology makes it difficult to accurately identify the vehicle's lane changes in the scenario of lane merging or separation; second, the existing algorithms often lack sufficient consideration when dealing with the lane correlation between consecutive frames, which makes it difficult to ensure the continuity and consistency of the vehicle's lane changing behavior in a dynamic traffic environment. Most importantly, it is difficult for the existing technology to accurately identify the behavior of a vehicle separating or merging from one lane to another, which leads to the continuous movement of the vehicle during lane separation or identification, and it is easy to misjudge or miss the lane change behavior.

[0064] The present application provides a solution, by obtaining driving map topological relationship information and driving scene target data frames; determining the current lane scene, the current lane scene including the lane separation scene and the lane merging scene; performing lane separation and lane change recognition for the lane separation scene according to the driving map topological relationship information and the driving scene target data frames, and performing lane merging and lane change recognition for the lane merging scene according to the driving map topological relationship information and the driving scene target data frames. The above scheme is used to recognize the behavior of the vehicle in the lane separation scenario and the lane merging scenario, thereby improving the accuracy of the intelligent driving system in recognizing the behavior of the vehicle when performing lane separation and lane merging.

[0065] It should be noted that the execution subject of this embodiment may be a computing service device with lane change recognition, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a lane change recognition system, etc. The following takes the lane change recognition system as an example to illustrate this embodiment and the following embodiments.

[0066] Based on this, the embodiment of the present application provides a lane change recognition method, referring to Figure 1 , Figure 1 Schematic diagram of the flow chart of the first embodiment of the lane change recognition method of the present application.

[0067] In this embodiment, the lane change recognition method includes steps S1000 to S3000:

[0068] Step S1000: Acquire driving map topology relationship information and driving scene target data frame;

[0069] It should be noted that obtaining the topological relationship information of the driving map is the basis for vehicle lane change recognition in the embodiment, which involves collecting and organizing detailed information on the lane, including but not limited to the lane number, trajectory point coordinates, sub-segment centerline point coordinates, starting point coordinates, end point coordinates, length, direction, etc. This information constitutes the lane information (lane_info), which is the prerequisite for lane change recognition. At the same time, the relationship information between lanes (lane_to_lane) is also crucial. It includes the left and right adjacent lane information and the front and subsequent lane information of the lane. This information helps to understand the location and relationship of the lanes in the road network.

[0070] In addition, it should be noted that the driving scene target data frame includes the current scene frame and the previous scene frame, which provides a continuity analysis basis for lane change recognition in time series. By analyzing the vehicle position changes between consecutive frames, it is possible to more accurately determine whether the vehicle has changed lanes.

[0071] For example, in a specific implementation, the system first obtains lane information and vehicle location information through a high-precision map API or sensor data collection, and then pre-processes the data to ensure the accuracy and availability of the data.

[0072] Step S2000: determining a current lane scenario, where the current lane scenario includes a lane separation scenario and / or a lane merging scenario;

[0073] It should be noted that determining the current lane scenario is a key step in achieving lane change recognition. The lane separation scenario refers to the situation where the vehicle separates from one lane to another, while the lane merging scenario refers to the situation where multiple lanes merge into one lane. Lane change recognition in these two scenarios has different characteristics and processing logic.

[0074] In addition, it should be noted that the implementation of the scene analysis of lane separation or merging depends on the in-depth understanding and analysis of the lane topology relationship information. By identifying the predecessor and successor relationship of the lane, the system can determine the specific scene of the current vehicle, thereby providing the correct scene context for the subsequent lane change recognition.

[0075] For example, determine whether the current lane is a merging lane or a separating lane, such as Figure 2 As shown, when a preceding lane is divided into multiple subsequent lanes, it is a separated lane; when multiple preceding lanes are merged into one subsequent lane, it is a merged lane. In a specific implementation, the system automatically determines whether the vehicle is in a lane separation or lane merging scenario by analyzing lane information and vehicle position changes, and records this determination result for use in subsequent steps.

[0076] Step S3000: performing lane separation lane change recognition for the lane separation scenario and / or performing lane merging lane change recognition for the lane merging scenario according to the driving map topology relationship information and the driving scenario target data frame.

[0077] It should be noted that this step is the core of the lane change recognition algorithm, which involves the recognition of lane change behaviors in two scenarios: lane separation and lane merging. In the lane separation scenario, the system needs to analyze the stability of the vehicle's lane sequence in the historical frame and predict the vehicle's lane sequence in the future frame to determine the occurrence of lane change behavior. In the lane merging scenario, the system needs to analyze the stability of the vehicle's lane sequence in the current frame and review the lane sequence in the historical frame to recognize the vehicle's lane change behavior.

[0078] In addition, it should be noted that this step also involves the calculation of vehicle stability, which is achieved by analyzing the number of times the vehicle appears in the lane sequence in the historical frame and the future frame. The calculation result of vehicle stability will serve as an important basis for judging lane change behavior.

[0079] For example, in a specific implementation, the system first calculates the lane sequence stability of the vehicle in the current frame and the previous frame, and then identifies the lane change behavior in the lane separation and lane merging scenarios based on these stability indicators and the difference in lane orientation angles. If the vehicle's stability and orientation angle difference both meet the preset conditions, the system will conclude that the vehicle has changed lanes.

[0080] In a feasible implementation manner, step S1000 may include steps S1100 to S1200:

[0081] Step S1100: determining a vehicle lane in the current frame and a lane sequence in the current frame according to the current frame of the scene and the lane information;

[0082] Step S1200: Determine the vehicle lane of the previous frame and the lane sequence of the previous frame according to the previous frame of the scene and the lane information.

[0083] It should be noted that determining the lanes and lane sequences of the vehicle in the current frame and the previous frame is the basis for accurate lane change recognition. Lane sequence refers to a sequence of multiple lanes determined based on the relationship between the preceding and succeeding lanes in the map topology. This process involves accurate tracking of the vehicle position and matching it with lane information, with the goal of constructing the vehicle's lane change history in a time series, such as Figure 3As shown, in the previous frame pre_frame of the current frame, the lane pre_frame_lane where the vehicle is located is in lane sequence 1. Here, the lane sequence refers to a lane sequence composed of multiple lanes determined based on the previous and subsequent relationships of lanes in the map topology. The lane cur_frame_lane where the vehicle is located in the current frame frame is in lane sequence 2 or lane sequence 3 (there may be more than two branches, two are used as examples here), where lane sequence 1, lane sequence 2, and lane sequence 3 are all calculated by the map topology at the frame level. The lane change behavior of the vehicle is identified by the change of the lane sequence between consecutive frames. Specifically, by comparing the lane sequences in the current frame and the previous frame, the lane change process of the vehicle can be captured. The effect of this step is to provide the necessary time and space information for lane change recognition, so that the system can further analyze the behavior pattern of the vehicle.

[0084] In addition, it should be noted that this process requires the system to have efficient data processing capabilities and accurate lane matching algorithms. The system must be able to quickly extract relevant information from the driving map and match it with the actual position of the vehicle to determine the exact lane and lane sequence where the vehicle is located. More specifically, through the vehicle lane binding algorithm, the lane where the vehicle is located in the current frame frame is calculated, and its lane number is recorded as cur_frame_lane_id current lane number. And further calculate the lane where the vehicle is located in the previous frame pre_frame of the current frame, and its lane number is recorded as pre_frame_lane previous frame lane number of the previous frame. If the cur_frame_lane_id current lane number and the pre_frame_lane previous frame lane number are not equal, the vehicle may have changed lanes, but it is only a candidate for lane change and needs to be further judged.

[0085] For example, in one feasible implementation, the system first receives driving scene data from the sensor, including images or position information of the current frame and the previous frame. Then, the system uses the built-in lane recognition algorithm to determine the exact lane position of the vehicle in these frames based on the lane topology in the high-precision map. By analyzing this position information, the system can track the lane changes of the vehicle to determine whether the vehicle has changed lanes and provide data support for further lane change recognition analysis. This overall solution combines high-precision map data with real-time vehicle position information to achieve accurate recognition of lane change behavior in lane separation and lane merging scenarios.

[0086] In a feasible implementation manner, the driving scene target data frame further includes a historical frame and a future frame, and step S3000 may include steps S3100 to S3300:

[0087] Step S3100: Calculating a first stability of the vehicle corresponding to the lane sequence of the current frame and a second stability of the vehicle corresponding to the lane sequence of the previous frame based on the historical frame, the future frame and the lane information;

[0088] It should be noted that the calculation of vehicle stability is performed by analyzing the frequency of the vehicle's lane sequence in the historical frame and the future frame. The first stability of the vehicle reflects the stability of the vehicle in the lane sequence of the current frame, while the second stability of the vehicle reflects the stability of the vehicle in the lane sequence of the previous frame. The stability calculation is achieved by counting the number of times the vehicle belongs to a specific lane sequence in the historical frame and the future frame considered, and then the stability ratio is obtained by dividing this number by the number of frames considered (consider_points).

[0089] In addition, it should be noted that the purpose of this step is to quantitatively evaluate the persistence of the vehicle in a specific lane sequence, so as to provide a basis for lane change recognition. If a vehicle frequently appears in a lane sequence within a certain time range, then its stability is high, indicating that the vehicle is stable in the lane sequence.

[0090] In a specific implementation, the system collects the vehicle's position information in historical frames and future frames, and matches it with the lane information in the high-precision map to determine the lane sequence the vehicle is in. The system then counts the number of times the vehicle appears in a specific lane sequence in these frames and calculates the vehicle's stability based on this.

[0091] For example, if the current lane is a split lane, for the split lane scenario, refer to Figure 3 As shown, considering several historical frames (consider_points) of the current frame, the number of times pre_lane_count that the lane to which the vehicle belongs in the considered historical frames is in lane sequence 1 is calculated, and prev_lane_rate is defined to be equal to pre_lane_count divided by consider_points. Then prev_lane_rate represents the stability of the vehicle in lane sequence 1, that is, the first stability of the current vehicle lane in the lane separation scenario.

[0092] If the current lane is a merging lane, for merging lane scenarios, such as Figure 4As shown, in the current frame frame, the lane cur_frame_lane where the vehicle is located is in lane sequence 3, where lane sequence refers to a lane sequence consisting of multiple lanes determined based on the relationship between the preceding and succeeding lanes in the map topology. In the previous frame pre_frame of the current frame, the lane prev_frame_lane where the vehicle is located is in lane sequence 1 or lane sequence 2 (there may be more than two branches merged, two examples are used here for illustration), where lane sequence 1, lane sequence 2, and lane sequence 3 are all calculated by the map topology at the frame level. Considering several future frames (consider_points) of the current frame, the number of times the lane to which the vehicle belongs in lane sequence 3 in the considered future frames is calculated, curr_lane_count, and curr_lane_rate is defined as curr_lane_count divided by consider_points, then curr_lane_rate represents the stability of the vehicle in lane sequence 3, that is, the first stability of the current vehicle lane in the lane merging scenario.

[0093] Step S3200: performing lane separation and lane change recognition on the lane separation scenario based on the first stability of the vehicle and the second stability of the vehicle;

[0094] It should be noted that lane separation and lane change recognition is performed after the vehicle stability is calculated. The purpose of this step is to determine whether the vehicle changes lanes from one lane sequence to another. The system determines whether a lane change occurs based on the values ​​of the first and second stability of the vehicle, as well as the difference in the orientation angle of the vehicle's lanes in the previous frame and the current frame.

[0095] In addition, it should be noted that if the lane sequence of the vehicle in the future frame is inconsistent with the previous frame, and both stability indicators exceed the preset stability threshold, the system will further compare the orientation angles of the lanes in the previous frame and the current frame. If the difference in the orientation angle exceeds the preset angle threshold, the system will recognize that the vehicle has performed a lane separation change.

[0096] Step S3300: Based on the first stability of the vehicle and the second stability of the vehicle, perform lane merging and lane change recognition on the lane merging scenario.

[0097] It should be noted that the process of lane merging and lane change recognition is similar to that of lane separation and lane change recognition, but it focuses on the lane sequence changes of the vehicle in the historical frame. The purpose of this step is to determine whether the vehicle has changed lanes from multiple lane sequences to the lane sequence of the current frame. The system will also make judgments based on the vehicle's stability and the difference in lane orientation angles.

[0098] In addition, it should be noted that if the lane sequence of the vehicle in the historical frame is inconsistent with the previous frame, and both stability indicators exceed the preset stability threshold, the system will calculate the difference in orientation angle between the lanes in the historical frame and the current frame. If this difference exceeds the preset angle threshold, the system will recognize that the vehicle has performed a lane merging change.

[0099] For example, in a specific implementation, the system first calculates the stability of the vehicle based on the vehicle's position information in the historical frame and the future frame, combined with the lane information. Then, based on these stability indicators and the difference in lane orientation angles, the system determines whether the vehicle has changed lanes in a lane separation or lane merging scenario. This process involves an in-depth analysis of the vehicle's dynamic behavior and a precise understanding of the lane topology to ensure the accuracy and reliability of lane change recognition.

[0100] The present embodiment provides a lane change recognition method, which obtains driving map topological relationship information and driving scene target data frames; determines the current lane scene, and the current lane scene includes a lane separation scene and a lane merging scene; performs lane separation lane change recognition on the lane separation scene according to the driving map topological relationship information and the driving scene target data frames, and performs lane merging lane change recognition on the lane merging scene according to the driving map topological relationship information and the driving scene target data frames. The above scheme is used to recognize the behavior of the vehicle in the lane separation scenario and the lane merging scenario, thereby improving the accuracy of the intelligent driving system in recognizing the behavior of the vehicle when performing lane separation and lane merging.

[0101] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , step S3200 of the lane change recognition method further includes steps S3210 to S3250:

[0102] Step S3210: Acquire vehicle and lane binding data in the future frame;

[0103] It should be noted that the purpose of obtaining vehicle and lane binding data in future frames is to predict the vehicle's lane behavior in the next few frames. This step involves analyzing the vehicle's trajectory in the predicted time domain and matching it with the lane information to determine the lane the vehicle may be in. In this way, the system can collect potential lane sequence information for the vehicle in subsequent frames.

[0104] In addition, it should be noted that the purpose of this step is to capture the short-term movement trend of the vehicle and provide forward-looking data support for lane change recognition. By analyzing the lane binding of the vehicle in future frames, the system can predict the vehicle's lane change intention and prepare in advance.

[0105] More specifically, before the system performs lane change recognition, it first constructs and obtains the map topology relationship at the frame level. For each frame, it includes lane information lane_info and lane-to-lane relationship information lane_to_lane.

[0106] Among them, lane_info is a dictionary, in which the key value is the lane number laneid, and the value value is the specific information of the lane, which is also composed of a dictionary. In this way, detailed information or required information of the lane can be quickly obtained through the lane number laneid.

[0107] The specific information of the lane mainly includes the track point coordinate information point_coords of the lane, which contains the coordinate information of all points in the lane; the centerline point coordinate information center_coods of the lane sub-segment, where the sub-segment is a segment composed of two adjacent coordinate points on the lane; the starting point coordinate information start of the lane; the end point coordinate information end of the lane; the length information length of the lane; the heading information heading of the lane, indicating the orientation of the lane in the odom coordinate system; the length information lengths of the lane sub-segment, the heading information headings of the lane sub-segment, and the number of the lane sub-segments.

[0108] lane_to_lane is a dictionary, where the key value is the lane number laneid, and the value value is the information related to the lane. It is also composed of a dictionary, including: the lane's left adjacent lane information left, the lane's right adjacent lane information right, the lane's previous adjacent lane information prev, and the lane's next adjacent lane information next. Through the constructed relationship between lanes, you can quickly obtain detailed information about the adjacent lanes of a specified lane.

[0109] When it is necessary to obtain the vehicle and lane binding data in the future frame, consider several frames in the future of the current frame (consider_points) and calculate the lane to which the vehicle belongs in each separated lane sequence (such as Figure 3 , here refers to the number of times the vehicle appears in lane sequence 2 or lane sequence 3), the number of times the vehicle appears in the lane sequence, that is, the vehicle and lane binding data. Here, the dictionary prev_lane_next_ids_counts is used to record the number of times each separated lane sequence appears, where the key value is the lane sequence id and the value is the number of times the vehicle appears in the corresponding lane sequence.

[0110] Step S3220: Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the future frame as the future frame associated lane;

[0111] It should be noted that the determination of the associated lane for the future frame is achieved by identifying the maximum value in the vehicle and lane binding data. The maximum value represents the lane that the vehicle is most likely to be in in the predicted frame. This step is a key step in the lane change recognition process because it is directly related to the judgment of the vehicle's lane change behavior.

[0112] In addition, it should be noted that the implementation of this step helps the system focus on the most likely lane changes, thereby improving the accuracy and efficiency of lane change recognition. The lane corresponding to the maximum value of the vehicle and lane binding data in the future frame is the lane associated with the future frame, that is, the lane sequence that appears the most times in the above dictionary prev_lane_next_ids_counts, recorded as lane sequence max1, and the lane sequence max is the lane associated with the future frame.

[0113] Step S3230: determining whether the future frame associated lane is consistent with the previous frame vehicle lane;

[0114] Step S3240: If the future frame associated lane is inconsistent with the previous frame vehicle lane, determining whether the first vehicle stability and the second vehicle stability both exceed a preset stability threshold;

[0115] Step S3250: If both the first stability of the vehicle and the second stability of the vehicle exceed a preset stability threshold, lane separation recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

[0116] In a feasible implementation manner, the step of performing lane separation recognition based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame may include steps A1000 to A2000:

[0117] Step A1000: determining whether a first difference between the orientation angle of the vehicle lane in the current frame and the orientation angle of the vehicle lane in the previous frame is greater than a preset angle threshold;

[0118] Step A2000: If the first difference is greater than a preset angle threshold, a result of the vehicle performing lane separation and lane change is obtained;

[0119] It should be noted that judging whether the lane associated with the future frame is consistent with the vehicle lane of the previous frame is to identify lane changes. If the two are inconsistent, it indicates that the vehicle may have lane changes, but subsequent judgment is still required. When the lane associated with the future frame is inconsistent with the vehicle lane of the previous frame, the system will further analyze the stability of the vehicle. Evaluate whether the first stability and the second stability of the vehicle both exceed the preset stability threshold. If the evaluation result of the vehicle stability indicates that the vehicle may change lanes, the system will perform lane separation recognition based on the orientation angle of the vehicle lane of the previous frame and the orientation angle of the vehicle lane of the current frame. This step is achieved by calculating the difference between the two orientation angles and comparing it with the preset angle threshold.

[0120] In a specific implementation, the system first collects and analyzes the predicted position data of the vehicle in the future frame, and matches it with the lane information in the high-precision map to obtain the vehicle and lane binding data. Then, the system identifies the lane corresponding to the maximum value of the vehicle binding data in the future frame as the future frame associated lane, and compares it with the lane in the previous frame. If the two are inconsistent, the system will calculate the stability of the vehicle in the current frame and the previous frame, and compare it with the threshold. Finally, if the stability exceeds the threshold, the system will identify the lane separation change behavior based on the difference in the orientation angle of the lanes in the two frames, thereby achieving accurate identification of the vehicle's lane change behavior.

[0121] For example, if the lane sequence to which the vehicle's lane in the current frame belongs (referred to as lane sequence current) does not belong to the same lane sequence as the above lane sequence max, then the candidate lane change is not true. If the lane sequence current does not belong to the same lane sequence max, then the number of times the lane appears on the lane sequence current in the future frame under consideration is further calculated as curr_lane_count, and curr_lane_rate is defined as curr_lane_count divided by consider_points, then curr_lane_rate represents the stability of the vehicle on the lane sequence current. Define a stability threshold rate_threshold. When the stability of the prev_lane_rate vehicle in lane sequence 1 is greater than rate_threshold, and the stability of the curr_lane_rate vehicle in the lane sequence to which the current frame vehicle belongs is greater than rate_threshold, further calculate the lane cur_frame_lane where the vehicle is located in the current frame frame, and extract the heading angle cur_frame_heading of the lane based on the map topology (the heading angle is the vector angle from the starting coordinate of the lane to the end coordinate). For the lane pre_frame_lane where the vehicle is located in the previous frame of the current frame, extract the heading angle pre_frame_heading of the lane based on the map topology, calculate cur_frame_heading minus pre_frame_heading value (denoted as heading_diff), normalize heading_diff to the interval [-pi, pi], and set the lane angle difference threshold heading_thrsdhold. If the absolute value of heading_diff is greater than heading_thrsdhold, then in this lane separation scenario, the candidate lane change behavior is considered true, otherwise the candidate lane change behavior is considered false.

[0122] In a feasible implementation manner, step S3300 further includes steps S3310 to S3350:

[0123] Step S3310: Acquire vehicle and lane binding data in the historical frame;

[0124] It should be noted that the purpose of obtaining the vehicle and lane binding data in the historical frame is to analyze the vehicle's driving path and lane changes over the past period of time. This step involves collecting the vehicle's position information in the historical frame and matching it with the lane data in the high-precision map to determine the lane the vehicle is in in each frame.

[0125] In addition, it should be noted that the purpose of this step is to collect historical behavior data of the vehicle, which is crucial for understanding the vehicle's driving pattern and predicting its future behavior.

[0126] When it is necessary to obtain the vehicle and lane binding data in the historical frame, consider several historical frames of the current frame (consider_points), calculate the lane to which the vehicle belongs in each branch lane sequence (such as Figure 4 , here refers to the number of times the vehicle appears in lane sequence 1 or lane sequence 2), the number of times the vehicle appears in the lane sequence, that is, the vehicle and lane binding data. Here, the dictionary curr_lane_next_ids_counts is used to record the number of times each branch lane sequence appears, where the key value is the lane sequence id and the value is the number of times the vehicle appears in the corresponding lane sequence.

[0127] Step S3320: Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the historical frame as the historical frame associated lane;

[0128] It should be noted that the determination of the lane associated with the historical frame is achieved by analyzing the vehicle and lane binding data in the historical frame and finding the maximum value in the data. The maximum value indicates the lane where the vehicle is most frequently or most stable in the historical frame, which provides an important basis for judging the driving trend of the vehicle. The lane corresponding to the maximum value of the vehicle and lane binding data in the historical frame is the lane associated with the historical frame, that is, the lane sequence that appears the most times in the above dictionary curr_lane_next_ids_counts (recorded as lane sequence max2).

[0129] In addition, it should be noted that this step helps to identify the main driving lane of the vehicle in the historical frame, providing key information for lane merging and lane change recognition.

[0130] Step S3330: determining whether the lane associated with the historical frame is consistent with the vehicle lane of the previous frame;

[0131] Step S3340: If the lane associated with the historical frame is inconsistent with the vehicle lane of the previous frame, determining whether the first stability of the vehicle and the second stability of the vehicle both exceed a preset stability threshold;

[0132] Step S3350: If both the first stability of the vehicle and the second stability of the vehicle exceed a preset stability threshold, lane merging recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

[0133] In a feasible implementation manner, the step of performing lane merging recognition based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame may include steps B1000 to B2000:

[0134] B1000: Determine whether a second difference between the orientation angle of the vehicle lane in the current frame and the orientation angle of the vehicle lane in the previous frame is greater than a preset angle threshold;

[0135] B2000: If the second difference is greater than the preset angle threshold, the result of the vehicle performing lane merging and lane changing is obtained.

[0136] It should be noted that the purpose of judging whether the lane associated with the historical frame is consistent with the vehicle lane of the previous frame is to detect whether the vehicle has changed lanes. If the two are inconsistent, it means that the vehicle may have changed lanes in the historical frame. When the lane associated with the historical frame is inconsistent with the vehicle lane of the previous frame, the system will further analyze the stability of the vehicle. If the evaluation result of the vehicle stability indicates that the vehicle may change lanes, the system will perform lane merging recognition based on the orientation angle of the vehicle lane of the previous frame and the orientation angle of the vehicle lane of the current frame. This step is achieved by calculating the difference between the two orientation angles and comparing it with the preset angle threshold.

[0137] In addition, it should be noted that if the difference in heading angles is greater than a preset angle threshold, the system will conclude that the vehicle has made a lane merging change. This step is a decisive link in the lane change recognition process, which determines the lane change behavior based on the dynamic behavior of the vehicle and the geometric properties of the lane.

[0138] In a specific implementation, the system first obtains the binding data of the vehicle and the lane based on the vehicle's position information in the historical frame and the high-precision map data. Then, the system identifies the lane corresponding to the maximum value of the binding data in the historical frame as the historical frame associated lane, and compares it with the lane in the previous frame. If the two are inconsistent, the system will calculate the stability of the vehicle in the current frame and the previous frame, and compare it with the threshold. Finally, if the stability exceeds the threshold, the system will identify the lane merging and lane changing behavior based on the difference in the orientation angles of the lanes in the two frames, thereby achieving accurate identification of the vehicle's lane changing behavior. This process is consistent with the principles of the lane change recognition algorithm described in the technical briefing, ensuring the consistency and logic of the algorithm implementation.

[0139] For example, if the lane sequence to which the lane of the vehicle in the previous frame of the current frame belongs (referred to as lane sequence prev) does not belong to the same as the lane sequence max, then the candidate lane change is not true. If the lane sequence prev does not belong to the same as the lane sequence max, then the number of times the vehicle appears in the lane sequence prev in the considered historical frame is further calculated, recorded as prev_lane_count, and prev_lane_rate is defined to be equal to prev_lane_count divided by consider_points. Then prev_lane_rate represents the stability of the vehicle in the lane sequence to which the lane of the vehicle in the previous frame of prev belongs. Define the stability threshold rate_threshold. When prev_lane_rate is greater than rate_threshold and curr_lane_rate is greater than rate_threshold, further calculate the lane cur_frame_lane where the vehicle is in the current frame frame, extract the orientation angle cur_frame_heading of the lane based on the map topology (the orientation angle is the vector angle from the starting coordinate of the lane to the end coordinate). For the lane pre_frame_lane where the vehicle is in the previous frame of the current frame, extract the orientation angle pre_frame_heading of the lane based on the map topology, calculate cur_frame_heading minus pre_frame_heading value (referred to as heading_diff), and normalize heading_diff to the interval [-pi, pi]. Set the lane angle difference threshold heading_thrsdhold. If the absolute value of heading_diff is greater than heading_thrsdhold, then in this merged lane scenario, the candidate lane change behavior is considered true, otherwise the candidate lane change behavior is considered false.

[0140] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the lane change recognition method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0141] Please refer to Figure 6 The present application further provides a lane change recognition device 60, the lane change recognition device comprising:

[0142] An acquisition module 61 is used to acquire driving map topology relationship information and driving scene target data frames;

[0143] A determination module 62, configured to determine a current lane scenario, wherein the current lane scenario includes a lane separation scenario and a lane merging scenario;

[0144] The identification module 63 is used to perform lane separation and lane change identification for the lane separation scenario according to the driving map topological relationship information and the driving scene target data frame, and to perform lane merging and lane change identification for the lane merging scenario according to the driving map topological relationship information and the driving scene target data frame.

[0145] The lane change recognition device provided by the present application adopts the lane change recognition method in the above embodiment, which can solve the technical problem of lane change recognition. Compared with the prior art, the beneficial effects of the lane change recognition device provided by the present application are the same as the beneficial effects of the lane change recognition method provided by the above embodiment, and other technical features in the lane change recognition device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0146] The present application provides a lane change recognition device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the lane change recognition method in the above-mentioned embodiment one.

[0147] Reference below Figure 7 , which shows a schematic diagram of the structure of a lane change recognition device suitable for implementing the embodiment of the present application. The lane change recognition device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The lane change recognition device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0148] like Figure 7As shown, the lane change recognition device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the lane change recognition device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the lane change recognition device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a lane change recognition device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0150] The lane change recognition device provided in the present application adopts the lane change recognition method in the above-mentioned embodiment. Compared with the prior art, the beneficial effects of the lane change recognition device provided in the present application are the same as the beneficial effects of the lane change recognition method provided in the above-mentioned embodiment, and other technical features in the lane change recognition device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0151] It should be understood that the various parts disclosed in this application can be implemented by 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 one or more embodiments or examples in a suitable manner.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the lane change recognition method in the above-mentioned embodiment.

[0154] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. 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 combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0155] The computer-readable storage medium may be included in the lane change recognition device; or may exist independently without being assembled into the lane change recognition device.

[0156] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0157] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0158] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0159] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above lane change recognition method, and can solve the technical problem of lane change recognition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the lane change recognition method provided in the above embodiment, and will not be elaborated here.

[0160] The present application also provides a computer program product, including a computer program, which implements the steps of the lane change recognition method as described above when executed by a processor.

[0161] The computer program product provided by the present application can solve the technical problem of lane change recognition. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the lane change recognition method provided by the above embodiment, which will not be described in detail here.

[0162] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A lane change recognition method, characterized in that: The method comprises: Obtain driving map topology relationship information and driving scene target data frame; Determining a current lane scenario, wherein the current lane scenario includes a lane separation scenario and / or a lane merging scenario; The lane separation and lane change recognition is performed on the lane separation scenario according to the driving map topological relationship information and the driving scene target data frame, and / or the lane merging and lane change recognition is performed on the lane merging scenario.

2. The method according to claim 1, characterized in that The driving map topology relationship information includes lane information, the driving scene target data frame includes a scene current frame and a scene previous frame, and after the step of obtaining the driving map topology relationship information and the driving scene target data frame, the step further includes: Determine a vehicle lane in a current frame and a lane sequence in a current frame according to the current frame of the scene and the lane information; A vehicle lane in a previous frame and a lane sequence in a previous frame are determined according to a previous frame of the scene and the lane information.

3. The method according to claim 2, characterized in that The driving scene target data frame also includes a historical frame and a future frame. The step of performing lane separation and lane change recognition on the lane separation scene and / or performing lane merging and lane change recognition on the lane merging scene according to the driving map topological relationship information and the driving scene target data frame includes: Calculate a first stability of the vehicle corresponding to the lane sequence of the current frame and a second stability of the vehicle corresponding to the lane sequence of the previous frame based on the historical frame, the future frame and the lane information; Based on the first vehicle stability and the second vehicle stability, performing lane separation and lane change recognition on the lane separation scenario; and / or Based on the first vehicle stability and the second vehicle stability, lane merging and lane change recognition is performed on the lane merging scenario.

4. The method as claimed in claim 3, characterized in that The lane information includes a lane orientation angle, and the step of performing lane separation and lane change recognition on the lane separation scenario based on the first vehicle stability and the second vehicle stability includes: Obtaining vehicle and lane binding data in the future frame; Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the future frame as the future frame associated lane; Determining whether the future frame associated lane is consistent with the previous frame vehicle lane; If the future frame associated lane is inconsistent with the previous frame vehicle lane, determining whether the first vehicle stability and the second vehicle stability both exceed a preset stability threshold; If both the first vehicle stability and the second vehicle stability exceed a preset stability threshold, lane separation recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

5. The method according to claim 3, characterized in that The step of performing lane merging and lane change recognition on the lane merging scenario based on the first stability of the vehicle and the second stability of the vehicle includes: Obtaining vehicle and lane binding data in the historical frame; Determine the lane corresponding to the maximum value of the vehicle and lane binding data in the historical frame as the historical frame associated lane; Determining whether the lane associated with the historical frame is consistent with the vehicle lane of the previous frame; If the lane associated with the historical frame is inconsistent with the vehicle lane of the previous frame, determining whether both the first stability of the vehicle and the second stability of the vehicle exceed a preset stability threshold; If both the first vehicle stability and the second vehicle stability exceed a preset stability threshold, lane merging recognition is performed based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame.

6. The method according to claim 4 or 5, characterized in that The step of performing lane separation recognition based on the orientation angle of the vehicle lane in the previous frame and the orientation angle of the vehicle lane in the current frame includes: Determine whether a first difference between the orientation angle of the vehicle lane of the current frame and the orientation angle of the vehicle lane of the previous frame is greater than a preset angle threshold; If the first difference is greater than a preset angle threshold, a result of the vehicle performing a lane separation lane change is obtained; The step of performing lane merging recognition based on the orientation angle of the vehicle lane of the previous frame and the orientation angle of the vehicle lane of the current frame includes: Determine whether a second difference between the orientation angle of the vehicle lane in the current frame and the orientation angle of the vehicle lane in the previous frame is greater than a preset angle threshold; If the second difference is greater than the preset angle threshold, the result of the vehicle performing lane merging and lane changing is obtained.

7. A lane change recognition device, characterized in that: The device comprises: An acquisition module is used to obtain driving map topology relationship information and driving scene target data frames; A determination module, configured to determine a current lane scenario, wherein the current lane scenario includes a lane separation scenario and / or a lane merging scenario; The recognition module is used to perform lane separation lane change recognition for the lane separation scenario and / or lane merging lane change recognition for the lane merging scenario according to the driving map topological relationship information and the driving scene target data frame.

8. A lane change recognition device, characterized in that: The device comprises: 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 lane change recognition method according to 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, the steps of the lane change recognition method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the lane change recognition method according to any one of claims 1 to 6 are implemented.

Images