Map lane line change detection method and device, equipment and storage medium

Abstract

The invention discloses a map lane line change detection method and device, equipment and a storage medium, and relates to the technical field of vehicle environment data mapping, and the map lane line change detection method comprises the steps: obtaining a map lane line and a sensing lane line; according to the areas where the map lane lines are located, the map lane lines are combined, and combined target map lane lines are obtained; associating the sensing lane line with a target map lane line to obtain an association result; when the association result is that the sensing lane line is associated with the target map lane line, determining whether the lane line type of the sensing lane line is consistent with the lane line type of the correspondingly associated target map lane line; and determining that the map lane line does not change under the condition that the lane line type of the perceived lane line is consistent with the lane line type of the correspondingly associated target map lane line. According to the method, the change of the map lane line is detected by associating the map lane line and the sensing lane line, and the robustness is improved through multi-frame statistical change information, so that the detection is more stable and reliable.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle environment data mapping, and in particular to a method, device, equipment and storage medium for detecting map lane line changes. Background Art

[0002] With the development of autonomous driving technology, accurate map information is essential for vehicle navigation and decision-making. As an important part of road infrastructure, accurate identification and change detection of lane lines are the key to achieving safe driving of autonomous vehicles. Therefore, developing an efficient and accurate map lane line change detection method is of great significance to the reliability and practicality of autonomous driving systems.

[0003] At present, the methods of detecting lane line changes on maps mainly rely on sensors carried by vehicles, such as cameras and lidar, to perceive the actual road conditions and compare them with the lane line data stored on the map. These methods usually involve image processing techniques, such as edge detection, feature extraction, etc., as well as machine learning algorithms to identify and classify lane lines. In addition, some methods also combine vehicle positioning information, such as GPS, IMU, etc., to improve the accuracy of detection.

[0004] Although existing map lane change detection methods can meet the needs to a certain extent, there are still some problems. First, these methods often require a lot of computing resources, especially when processing high-resolution images and performing complex machine learning inference. Second, the detection accuracy of existing methods will drop significantly in complex environments, such as bad weather or severe lane wear. In addition, as urban roads continue to change, existing methods also have limitations in updating map information in real time, resulting in map data that may become outdated. Therefore, how to improve the accuracy of map lane change detection has become an urgent problem to be solved. Summary of the invention

[0005] The purpose of this application is to provide a map lane line change detection method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the accuracy of map lane line change detection. To achieve the above purpose, this application proposes a map lane line change detection method, the method comprising:

[0006] Get map lane lines and sense lane lines;

[0007] According to the area where the map lane lines are located, the map lane lines are merged to obtain merged target map lane lines;

[0008] Associating the sensed lane line with the target map lane line to obtain an association result;

[0009] When the association result is that the perceived lane line is associated with the target map lane line, determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line;

[0010] When the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line, it is determined that the map lane line has not changed.

[0011] In one embodiment, merging the map lane lines according to the area where the map lane lines are located to obtain merged target map lane lines includes:

[0012] Performing feature classification on the map lane lines to determine feature vectors of the map lane lines;

[0013] Determine the area where the lane line of the map is located according to the feature vector;

[0014] When the area where the map lane line is located does not belong to the bifurcation area, the map lane line is merged according to the feature vector to obtain a merged target map lane line;

[0015] When the area where the map lane line is located belongs to a bifurcated area, the bifurcated map lane line and the merged map lane line are merged according to the feature vector to obtain a merged target map lane line.

[0016] In one embodiment, associating the sensed lane line with the target map lane line to obtain an association result includes:

[0017] Performing coordinate system conversion on the sensed lane line through positioning coordinates to obtain a target sensed lane line;

[0018] Based on the target sensing lane line, a target point is obtained;

[0019] Traversing the normal distances from the target point to the lane line of the target map to obtain a set of normal distances from the target point to the lane line of the target map;

[0020] Based on the normal distance set, obtaining a first normal distance;

[0021] If the first normal distance is less than or equal to a first preset distance threshold, the sensed lane line is associated with the target map lane line;

[0022] If the first normal distance is greater than the first preset distance threshold, the sensed lane line is not associated with the target map lane line, and the sensed lane line is recorded to add a lane line according to the sensed lane line.

[0023] In one embodiment, associating the sensed lane line with the target map lane line to obtain an association result includes:

[0024] If the target map lane line is not associated with the sensed lane line, obtaining a second normal distance between the target map lane line and the vehicle position;

[0025] If the second normal distance is less than or equal to a second preset distance threshold, the target map lane line is recorded to delete the lane line according to the target map lane line.

[0026] In one embodiment, when the association result is that the perceived lane line is associated with the target map lane line, determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line includes:

[0027] Acquire a first lane line type of the sensed lane line, and a second lane line type of a target map lane line associated with the sensed lane line;

[0028] If the first lane line type is inconsistent with the second lane line type, the target map lane line is recorded to modify the lane line according to the target map lane line.

[0029] In one embodiment, when the lane line type of the sensed lane line is consistent with the lane line type of the corresponding associated target map lane line, after determining that the map lane line has not changed, the method further includes:

[0030] Obtain the recorded sensed lane lines and the recorded target map lane lines, as well as the number of consecutive frames they exist;

[0031] If the continuous number of frames is less than or equal to the frame number threshold, the map lane line change detection is completed;

[0032] If the number of consecutive frames is greater than the frame number threshold, data reporting is performed.

[0033] In one embodiment, if the continuous number of frames is greater than the frame number threshold, after the data is reported, the method further includes:

[0034] Outputting the recorded sensed lane line and the recorded target map lane line;

[0035] or,

[0036] The sensor data within a preset time before and after the change is acquired, and the sensor data is packaged and cached for subsequent analysis.

[0037] In addition, to achieve the above purpose, the present application also proposes a map lane line change detection device, the device comprising:

[0038] The acquisition module is used to obtain the map lane lines and sense the lane lines;

[0039] A merging module, used for merging the map lane lines according to the area where the map lane lines are located, to obtain a merged target map lane line;

[0040] An association module, used to associate the sensed lane line with the target map lane line to obtain an association result;

[0041] a judgment module, configured to determine whether a lane line type of the perceived lane line is consistent with a lane line type of a correspondingly associated target map lane line when the association result is that the perceived lane line is associated with the target map lane line;

[0042] The determination module is used to determine that the map lane line has not changed when the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a map lane line change detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the map lane line change detection method as described above.

[0044] 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 map lane line change detection method described above are implemented.

[0045] 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, it implements the steps of the map lane line change detection method as described above.

[0046] One or more technical solutions proposed in this application have at least the following technical effects:

[0047] This application first provides a continuous and accurate map lane line representation by acquiring and merging lane line data. Then, by associating the perceived lane lines and map lane lines and checking their type consistency, it is possible to accurately identify which lane lines have changed. This method not only improves the accuracy of detection, but also improves the robustness of the system by reducing false positives and false negatives. Through the above method, this application can ensure the timely update of map data, thereby providing autonomous driving vehicles with safer and more reliable navigation information, effectively solving the accuracy and real-time problems existing in the prior art, and providing important technical support for the development of the autonomous driving field. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 A flowchart of the first embodiment of the method for detecting lane line changes in a map provided by the present application;

[0051] Figure 2 A flowchart diagram of the second embodiment of the map lane line change detection method of the present application;

[0052] Figure 3 A schematic diagram of a simplified process of a map lane line change detection method according to an embodiment of the present application;

[0053] Figure 4 This is a schematic diagram of the module structure of the map lane line change detection device according to an embodiment of the present application;

[0054] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the map lane line change detection method in the embodiment of the present application.

[0055] 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

[0056] 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.

[0057] 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.

[0058] With the advancement of autonomous driving technology, the demand for accurate map information is growing, especially the accurate identification and change detection of lane lines, which is crucial to ensure the safe driving of autonomous vehicles. At present, lane line change detection mainly relies on vehicle sensors, image processing technology and machine learning algorithms, combined with positioning information such as GPS. However, these methods face problems such as high consumption of computing resources, reduced detection accuracy in complex environments, and untimely map data updates. Therefore, developing an efficient and accurate map lane line change detection method to reduce resource consumption and improve the real-time performance of detection has become an urgent problem to be solved in the field of autonomous driving.

[0059] The main solution of the embodiment of the present application is: the present application first provides a continuous and accurate map lane line representation by acquiring and merging lane line data. Then, by associating the perceived lane lines and the map lane lines and checking their type consistency, it is possible to accurately identify which lane lines have changed. This method not only improves the accuracy of detection, but also improves the robustness of the system by reducing false positives and false negatives. The present application can ensure the timely update of map data through the above method, thereby providing safer and more reliable navigation information for autonomous driving vehicles, effectively solving the accuracy and real-time problems existing in the prior art, and providing important technical support for the development of the field of autonomous driving.

[0060] It should be noted that the execution subject of the embodiment of the present application may be a computing service device with data processing, 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, etc. The following takes a terminal equipped with a map lane line change detection method as an example to illustrate this embodiment and the following embodiments.

[0061] Based on this, the present application embodiment provides a map lane line change detection method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the map lane line change detection method of the present application.

[0062] In this embodiment, the map lane line change detection method includes steps S10 to S50:

[0063] Step S10, obtaining map lane lines and sensed lane lines;

[0064] It should be noted that map lane lines refer to lane line information stored in the map database. These lane line data are usually obtained through preliminary map collection and drawing work, and may come from professional map surveying and mapping vehicles, aerial photogrammetry, satellite remote sensing or crowdsourcing data collection. Map lane line information usually includes the geometric position, type (such as solid line, dashed line), direction and other attributes of the lane line, which provide basic structural information of the road for autonomous vehicles. Perceived lane lines refer to lane line information perceived in real time by sensors on autonomous vehicles. These sensors may include cameras, laser radar (LiDAR), millimeter wave radar, etc., which can capture images or point cloud data of the vehicle's surrounding environment in real time. Through image processing and computer vision technologies, such as edge detection, feature extraction, deep learning and other methods, the position, type and other relevant features of the lane line are identified from the perception data.

[0065] It is understandable that the present application extracts lane line information from a high-precision map. The map lane line information provides basic structural information of the road for autonomous vehicles and is the basis for vehicle navigation and decision-making. Perceiving lane lines is to identify the location, type and other characteristics of lane lines from data collected by sensors. Perceiving lane lines provides real-time road condition information for the autonomous driving system, which helps the system respond quickly to environmental changes. Obtaining map lane lines and perceiving lane lines provides the necessary data basis for detecting lane line changes. Through precise comparison and analysis, changes in lane lines can be identified in a timely manner, thereby providing the latest road information.

[0066] Step S20, merging the map lane lines according to the area where the map lane lines are located to obtain merged target map lane lines;

[0067] It should be noted that the target map lane line refers to the map lane line data after merging. This process is to solve the problem of segmentation or interruption of the map lane line at the data structure level. On actual roads, lane lines are usually continuous, but in map data, lane lines may be divided into multiple sections due to different collection, storage or data processing methods. The purpose of merging is to obtain a more continuous and complete lane line representation, which is closer to the actual situation and facilitates accurate comparison and analysis with the perceived lane lines.

[0068] It is understandable that this is a regional merging of lane line data stored in the map. The purpose is to merge lane line information that may have been divided into multiple independent segments due to data collection or storage methods into continuous and complete target map lane lines based on their geographic spatial adjacency and directional consistency. Doing so can more realistically reflect the continuity of the actual road and simplify the process of comparing and analyzing lane line data perceived in real time by vehicle sensors, thereby improving the accuracy and efficiency of lane line change detection. The merged lane lines eliminate redundancy and inconsistency in the data, providing a clear and coherent reference benchmark for subsequent lane line change detection.

[0069] As an example, according to the area where the map lane lines are located, the map lane lines are merged to obtain a merged target map lane line, including: feature classification of the map lane lines to determine the feature vector of the map lane lines; determining the area where the map lane lines are located according to the feature vector; when the area where the map lane lines are located does not belong to a bifurcation area, merging the map lane lines according to the feature vector to obtain a merged target map lane line; when the area where the map lane lines are located belongs to a bifurcation area, merging the bifurcated map lane lines and the merged map lane lines respectively according to the feature vector to obtain a merged target map lane line.

[0070] Among them, the feature classification step involves identifying and classifying various attributes of lane lines on the map. The basis for classification can include geometric features of lane lines (such as straight lines, curves), topological features (such as the connection and intersection relationship of lane lines), semantic features (such as the type of lane lines, such as solid lines, dashed lines, double yellow lines, etc.) and other related information (such as lane width, road surface markings, etc.). Through feature classification, lane lines can be divided into different categories for subsequent processing and analysis. The feature vector is a mathematical representation of feature classification, which quantifies the various features of lane lines into numerical form to form a vector. This vector contains key information describing the characteristics of lane lines, such as the starting and ending coordinates of lane lines, curvature, lane width, lane type, etc. The feature vector can be regarded as the "digital fingerprint" of the lane line, which captures the essential characteristics of the lane line so that the lane line can be effectively processed and compared by the computer system. Through feature classification and feature vectors, we can simplify the complex information of lane lines into a set of quantifiable and comparable data. This provides a basis for subsequent lane line merging, association and change detection. For example, when merging lane lines, the feature vector can be used to determine which lane line segments are geometrically adjacent and have the same direction, so that they can be merged into a continuous lane line. Similarly, when associating the perceived lane line with the target map lane line, the feature vector can also be used to calculate the similarity between the two to determine whether they match. Through this process, the accuracy and efficiency of lane line detection can be improved, thereby providing more reliable road information for the autonomous driving system.

[0071] Specifically, feature extraction and classification are performed on the map lane lines to determine the feature vector of each lane line, which contains the geometric, topological and semantic features of the lane line. Then, the specific area where the lane line is located is determined based on these feature vectors, such as whether it is located at the fork or confluence of the road. For lane lines in non-bifurcated areas, the system will directly merge them according to the feature vectors to form continuous target map lane lines. In the bifurcated area, the system will perform special processing to merge the bifurcated and confluent lane lines respectively to accurately reflect the complex road structure in this area. In the end, whether it is a simple or complex road area, the accurately merged target map lane lines can be obtained, providing accurate map data for subsequent lane line change detection.

[0072] Step S30, associating the sensed lane line with the target map lane line to obtain an association result;

[0073] It should be noted that the association result refers to the output result obtained after the lane line perceived by the vehicle sensor in real time (perceived lane line) is carefully compared and matched with the lane line stored in the high-precision map (target map lane line) through a specific algorithm during the process of lane line change detection. This association result describes the corresponding relationship between the perceived lane line and the target map lane line.

[0074] It is understandable that this step refers to using a specific algorithm to match the lane line data detected by the vehicle sensor in real time with the lane line data stored in the high-precision map to determine the corresponding relationship between them. This process will output a correlation result, which provides an important basis for judging whether the lane line has changed. Data matching is used to verify whether the actual road conditions are consistent with the map information, ensuring that the autonomous driving system can accurately identify and respond to lane line changes.

[0075] As an example, the perceived lane line is associated with the target map lane line to obtain an association result, including: converting the coordinate system of the perceived lane line through positioning coordinates to obtain a target perceived lane line; obtaining a target point based on the target perceived lane line; traversing the normal distance from the target point to the target map lane line to obtain a normal distance set from the target point to the target map lane line; obtaining a first normal distance based on the normal distance set; if the first normal distance is less than or equal to a first preset distance threshold, the perceived lane line is associated with the target map lane line; if the first normal distance is greater than the first preset distance threshold, the perceived lane line is not associated with the target map lane line, and the perceived lane line is recorded to add a lane line according to the perceived lane line.

[0076] Among them, the target perceived lane line refers to the perceived lane line after the coordinate system conversion. Since the perceived lane line data captured by the on-board sensor is usually relative to the vehicle's own coordinate system, it is necessary to convert these data into the same coordinate system as the map lane line data (usually a global coordinate system, such as a GPS coordinate system) to facilitate accurate comparison and matching. The target point refers to a specific point on the target perceived lane line, which is usually used to calculate the distance with the target map lane line. The target point can be a sampling point on the perceived lane line or a point with a specific meaning, such as the starting point, end point or turning point of the lane line. The normal distance set refers to the distance set obtained after the normal distance from the target point to multiple target map lane lines, and this set contains multiple distance values. The first normal distance refers to the minimum value obtained from all normal distances from the target point to the target map lane line. This distance is used to obtain the map lane line closest to the perceived lane line. The first preset distance threshold is a pre-set distance value used to determine whether the perceived lane line is close enough to the target map lane line, and can be set to 1.5m in specific applications. If the first normal distance is less than or equal to this threshold, the perceived lane line is considered to be associated with the target map lane line, that is, they match in spatial position. If it is greater than this threshold, they are considered to be unassociated and the map may need to be updated to reflect the new lane line information.

[0077] Specifically, the perceived lane lines detected by the on-board sensors are converted from the vehicle coordinate system to the map coordinate system to form target perceived lane lines, and then key target points are extracted from them, and the normal distances from these points to the target map lane lines are calculated to form a normal distance set. By analyzing this set, the minimum normal distance, that is, the first normal distance, is determined, and the target map lane line with the closest distance is determined. If this distance is within the preset threshold, it indicates that the perceived lane lines correspond closely to the map lane lines, so they are associated. If the threshold is exceeded, they are considered to be mismatched, and the system will record the perceived lane lines so that new lane lines may need to be added to the map in the future. This process achieves accurate matching of perceived lane lines with map lane lines through precise spatial analysis, providing a reliable basis for lane line change detection.

[0078] As an example, the perceived lane line is associated with the target map lane line to obtain an association result, including: if the target map lane line is not associated with the perceived lane line, obtaining a second normal distance of the target map lane line from the vehicle position; if the second normal distance is less than or equal to a second preset distance threshold, recording the target map lane line to delete the lane line according to the target map lane line.

[0079] Among them, the second normal distance refers to the vertical distance between the unassociated target map lane line and the vehicle position. If this distance is very small, it means that although the perceived lane line does not match the target map lane line, the target map lane line is still close to the vehicle, which may indicate that there is an extra lane line on the map. The second preset distance threshold is a pre-set threshold used to determine whether the target map lane line is close enough to the vehicle to consider deleting it from the map. If the second normal distance is less than or equal to this threshold, even if the perceived lane line does not match the target map lane line, the system may believe that the target map lane line no longer represents the actual road conditions, so this lane line needs to be recorded for deletion from the map.

[0080] Specifically, when the map lane line fails to successfully match the perceived lane line, the system will calculate the vertical distance from the map lane line to the vehicle position, that is, the second normal distance. If this distance is less than or equal to the second preset distance threshold set in advance, it indicates that the map lane line is still near the vehicle, which may mean that this lane line no longer exists on the actual road. Therefore, the system will record this target map lane line for subsequent deletion on the map to ensure the accuracy and update of map information. This step can identify and process lane lines that may have disappeared on the actual road, and decide whether these lane lines need to be removed from the map by measuring the proximity of the map lane line to the vehicle.

[0081] Step S40, when the association result is that the perceived lane line is associated with the target map lane line, determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line;

[0082] It should be noted that lane line type refers to the classification of lane lines in road traffic markings, which are based on the physical characteristics and functions of lane lines. The determination of lane line types is very important for traffic management and vehicle navigation because it affects driving behavior and road use rules. In lane line detection systems, identifying these lane line types is crucial to ensure that vehicles comply with traffic rules and drive safely. Through image data collected by sensors such as cameras and radars on vehicles, combined with computer vision and machine learning technology, lane line types can be identified and classified. Comparing the type of perceived lane lines with the target map lane lines helps to determine whether the lane lines have changed, thereby ensuring the accuracy of map data and vehicle navigation safety.

[0083] It is understandable that when the association result shows that the perceived lane line successfully matches the target map lane line, the next step is to verify whether the types of the two lane lines are consistent, that is, to compare whether they are both solid lines, dashed lines, double lines, etc., or whether they have other specific traffic sign attributes. This verification process is important for ensuring the accuracy of lane line information and updating map data, because it can help the system determine whether the actual road markings are consistent with the map information, thereby providing correct navigation information for the autonomous driving vehicle. This step is to further confirm whether the perceived lane line and the map lane line are completely consistent by comparing the types of lane lines to ensure the accuracy of the lane line data.

[0084] As an example, when the lane line type of the perceived lane line is consistent with the corresponding target map lane line, after determining that the map lane line has not changed, it also includes: obtaining recorded perceived lane lines and recorded target map lane lines, and the number of consecutive frames therein; if the number of consecutive frames is less than or equal to a frame number threshold, completing the map lane line change detection; if the number of consecutive frames is greater than the frame number threshold, reporting data.

[0085] Among them, recording the perceived lane lines and recording the target map lane lines refer to the perceived lane lines and target map lane lines recorded by the system during the detection and judgment process. The number of continuous frames refers to the number of times the recorded perceived lane lines and target map lane lines appear in consecutive video frames or data frames. The frame number threshold is a pre-set threshold used to determine whether the lane line changes are sufficiently stable and persistent. If the number of appearances of the recorded perceived lane lines and target map lane lines in consecutive frames (the number of consecutive frames) is less than or equal to this threshold, the system will consider the lane line changes to be temporary or unstable and no further action is required.

[0086] Specifically, the perceived lane lines and target map lane lines recorded in the previous detection process are reviewed, and the continuity and reliability of lane line changes are evaluated by counting the number of times these lane lines appear in consecutive video frames or data frames, that is, the number of consecutive frames. If this number of frames is less than or equal to the pre-set frame number threshold, it indicates that the change is not stable or continuous, so the detection is completed and it is considered that no further action is needed. On the contrary, if the number of consecutive frames exceeds the frame number threshold, it means that the lane line change is persistent. At this time, the system will report the data and send these change information to the map server to update the map data to ensure the accuracy of the map and the navigation accuracy of the autonomous driving system.

[0087] As an example, if the continuous number of frames is greater than the frame number threshold, after data reporting, it also includes: outputting the recorded perceived lane line and the recorded target map lane line; or, obtaining sensor data within a preset time before and after the change, packaging and caching the sensor data for subsequent analysis.

[0088] The preset time threshold refers to a time range preset by the system, which is used to define the collection of sensor data for analysis within a certain period of time before and after the change point. For example, if the preset time threshold is set to "1 minute", the system will collect sensor data within 1 minute of the change point (the time point when the number of consecutive frames exceeds the frame number threshold). Sensor data includes but is not limited to GNSS, IMU, wheel speed, and perception information.

[0089] Specifically, in the final stage of the map lane change detection process, if it is determined after continuous frame verification that the lane has indeed changed, the system will perform one of two possible operations: one is to directly output the specific data of the recorded perceived lane lines and target map lane lines when on the cloud, so that these specific lane lines can be immediately viewed or edited; or, the second is to collect data from vehicle sensors within a preset time range when on the vehicle side, encapsulate these data into a data packet, and then output this data packet for more in-depth analysis or for updating high-precision maps.

[0090] Step S50, when the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line, determining that the map lane line has not changed.

[0091] Understandably, when the perceived lane line is successfully associated with the target map lane line in spatial position, and their lane line types (such as solid line, dashed line, etc.) are also exactly the same, we can conclude that the map lane line in that area has not changed. This means that the map data is still accurate for this particular lane line, so no update or modification is required. This judgment is very important for maintaining the accuracy of map data and reducing unnecessary map update operations. It ensures that the autonomous driving system can rely on the latest and verified lane line information for navigation and decision-making.

[0092] This embodiment provides a method for detecting changes in map lane lines. First, by acquiring and merging lane line data, a continuous and accurate map lane line representation is provided. Then, by associating the perceived lane lines and the map lane lines and checking their type consistency, it is possible to accurately identify which lane lines have changed. This method not only improves the accuracy of detection, but also improves the robustness of the system by reducing false positives and false negatives. The above method can ensure timely updating of map data, thereby providing safer and more reliable navigation information for autonomous driving vehicles, effectively solving the accuracy and real-time problems existing in the prior art, and providing important technical support for the development of the field of autonomous driving.

[0093] 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 refer to the above introduction, and will not be repeated later. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the map lane line change detection method of the present application. Step S40 of the map lane line change detection method includes steps S41 to S42:

[0094] Step S41, obtaining a first lane line type of the sensed lane line, and a second lane line type of a target map lane line associated with the sensed lane line;

[0095] It should be noted that the first lane line type refers to the lane line type determined by the lane line perceived in real time by the sensors of the autonomous driving vehicle. For example, the lane line image data captured by sensors such as cameras and lidars is processed by image processing and computer vision algorithms to identify the lane line type, such as solid line, dotted line, double line, etc. The second lane line type refers to the lane line type of the target map lane line extracted from high-precision map data. These data are usually collected by professional surveying and mapping vehicles or by other means during the map making process and stored in the map database. When performing lane line change detection, the system retrieves the lane line that matches the perceived lane line position from the map and obtains its type information.

[0096] It can be understood that this is to extract lane line type information from two different data sources: on the one hand, the first lane line type of the perceived lane line is determined by real-time perception and analysis of road conditions by vehicle sensors, which usually includes processing images captured by cameras or lidar to identify the current state of the lane line, such as solid line, dotted line, etc.; on the other hand, the second lane line type of the target map lane line that matches the perceived lane line is retrieved from the high-precision map database, which is based on the lane line attributes pre-recorded in the map. By comparing these two lane line types, it can be determined whether there is a difference between the perceived lane line and the map lane line, and then decide whether it is necessary to update the map data or adjust the vehicle's driving strategy. The consistency of the lane line information is verified by comparing the actual road perception data with the lane line type in the map data.

[0097] Step S42: If the first lane line type is inconsistent with the second lane line type, the target map lane line is recorded to modify the lane line according to the target map lane line.

[0098] It is understandable that when the comparison finds that the first lane line type perceived by the vehicle sensor in real time does not match the second lane line type stored in the high-precision map, the system will record the information of the target map lane line. This recording behavior is for the subsequent necessary updates or modifications to the map to ensure the accuracy and real-time nature of the map data, so that the autonomous driving vehicle can rely on the latest road information in the subsequent navigation and decision-making process, improving the safety and reliability of driving. From the previously obtained perceived lane line associated with the map lane line, it can be seen that the perceived lane line may have changed in type, that is, it is different from the map lane line, so recording the map lane line is the basis for the next modification.

[0099] This embodiment first provides basic data for lane line change detection by using the first lane line type of the perceived lane line obtained by the vehicle sensor and the second lane line type of the target map lane line associated with the perceived lane line. Then, the first lane line type is compared with the second lane line type to identify whether there is a difference between the perceived lane line and the map lane line. This comparison process is a key link in determining whether the lane line has changed, which directly affects the subsequent lane line update decision. Finally, when the first lane line type is inconsistent with the second lane line type, the information of the target map lane line is recorded to provide necessary data support for subsequent map updates, ensuring that the map data can reflect the actual changes of the road in a timely manner, and improving the accuracy and reliability of the map data. This embodiment realizes rapid detection and response to lane line changes through precise lane line type acquisition, comparison and recording processes. The recorded data is used to update the map data, ensuring that the autonomous driving vehicle can make correct navigation decisions in complex and changeable road environments, and improving the practicality and safety of the autonomous driving system.

[0100] For example, to help understand the implementation process of the map lane line change detection method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flowchart of a map lane line change detection method is provided, specifically:

[0101] First, two sets of data are obtained: map lane lines and sensed lane lines. The map lane lines are extracted from high-precision maps, while the sensed lane lines are detected in real time by on-board sensors. Secondly, the map lane lines are regionally merged, including feature classification of lane lines, determining feature vectors, and merging lane lines based on these feature vectors to form continuous target map lane lines. Next, the sensed lane lines are associated with the target map lane lines. This involves converting the sensed lane lines to the map coordinate system and calculating the normal distance from the point on the sensed lane line to the target map lane line. If this distance is less than or equal to the preset distance threshold, the two are considered to be associated. If the sensed lane line is associated with the target map lane line, the system will further compare the lane line types of the two. If the types are consistent, the system will determine that the map lane line has not changed. If the lane line types are inconsistent, or the sensed lane line is not associated with the target map lane line, the system will record these lane lines and add, delete or modify the lane lines on the map as needed. Finally, after determining that the lane line types are consistent, the system will also check the number of times these lane lines appear in consecutive frames. If the number of consecutive frames exceeds the preset frame threshold, the system will report the data. The entire flowchart reflects an automated lane change detection and response system that continuously monitors and compares actual road conditions with map data to ensure the accuracy and timeliness of map information, thereby supporting the navigation and decision-making of autonomous vehicles.

[0102] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the map lane line change detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0103] This application also provides a map lane line change detection device, please refer to Figure 4 , the map lane line change detection device comprises:

[0104] An acquisition module 10 is used to acquire map lane lines and sense lane lines;

[0105] A merging module 20, configured to merge the map lane lines according to the areas where the map lane lines are located, to obtain merged target map lane lines;

[0106] An association module 30 associates the sensed lane line with the target map lane line to obtain an association result;

[0107] A judgment module 40, configured to determine whether the lane line type of the perceived lane line is consistent with the lane line type of the corresponding associated target map lane line when the association result is that the perceived lane line is associated with the target map lane line;

[0108] The determination module 50 is used to determine that the map lane line has not changed when the lane line type of the perceived lane line is consistent with the lane line type of the corresponding associated target map lane line.

[0109] The map lane line change detection device provided by the present application adopts the map lane line change detection method in the above embodiment, which can solve the technical problem of how to improve the accuracy of map lane line change detection. Compared with the prior art, the beneficial effects of the map lane line change detection device provided by the present application are the same as the beneficial effects of the map lane line change detection method provided by the above embodiment, and the other technical features in the map lane line change detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0110] The present application provides a map lane line change detection 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 map lane line change detection method in the above-mentioned embodiment one.

[0111] Reference below Figure 5 , which shows a schematic diagram of the structure of a map lane line change detection device suitable for implementing the embodiment of the present application. The map lane line change detection 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 5 The map lane change detection 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.

[0112] like Figure 5As shown, the map lane line change detection device may include a processing device 1001 (such as 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 map lane line change detection device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other 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 touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the map lane line change detection device to communicate with other devices wirelessly or by wire to exchange data. Although the map lane line change detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0113] 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.

[0114] The map lane line change detection device provided by the present application adopts the map lane line change detection method in the above embodiment, which can solve the technical problem of how to improve the accuracy of map lane line change detection. Compared with the prior art, the beneficial effects of the map lane line change detection device provided by the present application are the same as the beneficial effects of the map lane line change detection method provided by the above embodiment, and the other technical features in the map lane line change detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0115] 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.

[0116] 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.

[0117] 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 map lane line change detection method in the above-mentioned embodiment.

[0118] 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.

[0119] The above-mentioned computer-readable storage medium may be included in the map lane line change detection device; or it may exist independently without being assembled into the map lane line change detection device.

[0120] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the map lane line change detection device, the map lane line change detection device enables the map lane line change detection device to: obtain map lane lines and perceived lane lines; merge the map lane lines according to the areas where the map lane lines are located to obtain merged target map lane lines; associate the perceived lane lines with the target map lane lines to obtain an association result; when the association result is that the perceived lane lines are associated with the target map lane lines, determine whether the lane line types of the perceived lane lines and the corresponding associated target map lane lines are consistent; when the lane line types of the perceived lane lines and the corresponding associated target map lane lines are consistent, determine that the map lane lines have not changed.

[0121] 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).

[0122] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart 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.

[0123] The modules involved in the embodiments described in this 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.

[0124] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned map lane line change detection method, and can solve the technical problem of how to improve the accuracy of map lane line change detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the map lane line change detection method provided in the above-mentioned embodiment, and will not be repeated here.

[0125] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned map lane line change detection method when executed by a processor.

[0126] The computer program product provided by this application can solve the technical problem of how to improve the accuracy of map lane line change detection. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the map lane line change detection method provided by the above embodiment, which will not be repeated here.

[0127] 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 map lane line change detection method, characterized in that: The method comprises: Get map lane lines and sense lane lines; According to the area where the map lane lines are located, the map lane lines are merged to obtain merged target map lane lines; Associating the sensed lane line with the target map lane line to obtain an association result; When the association result is that the perceived lane line is associated with the target map lane line, determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line; When the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line, it is determined that the map lane line has not changed.

2. The method according to claim 1, characterized in that The merging process of the map lane lines according to the area where the map lane lines are located to obtain the merged target map lane lines includes: Performing feature classification on the map lane lines to determine feature vectors of the map lane lines; Determine the area where the lane line of the map is located according to the feature vector; When the area where the map lane line is located does not belong to the bifurcation area, the map lane line is merged according to the feature vector to obtain a merged target map lane line; When the area where the map lane line is located belongs to a bifurcated area, the bifurcated map lane line and the merged map lane line are merged according to the feature vector to obtain a merged target map lane line.

3. The method according to claim 1, characterized in that The associating the sensed lane line with the target map lane line to obtain an association result includes: Performing coordinate system conversion on the sensed lane line through positioning coordinates to obtain a target sensed lane line; Based on the target sensing lane line, a target point is obtained; Traversing the normal distances from the target point to the lane line of the target map to obtain a set of normal distances from the target point to the lane line of the target map; Based on the normal distance set, obtaining a first normal distance; If the first normal distance is less than or equal to a first preset distance threshold, the sensed lane line is associated with the target map lane line; If the first normal distance is greater than the first preset distance threshold, the sensed lane line is not associated with the target map lane line, and the sensed lane line is recorded to add a lane line according to the sensed lane line.

4. The method according to claim 1, characterized in that The associating the sensed lane line with the target map lane line to obtain an association result includes: If the target map lane line is not associated with the sensed lane line, obtaining a second normal distance between the target map lane line and the vehicle position; If the second normal distance is less than or equal to a second preset distance threshold, the target map lane line is recorded to delete the lane line according to the target map lane line.

5. The method according to claim 1, characterized in that When the association result is that the perceived lane line is associated with the target map lane line, determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line includes: Acquire a first lane line type of the sensed lane line, and a second lane line type of a target map lane line associated with the sensed lane line; If the first lane line type is inconsistent with the second lane line type, the target map lane line is recorded to modify the lane line according to the target map lane line.

6. The method according to claim 1, characterized in that In the case where the lane line type of the sensed lane line is consistent with the lane line type of the corresponding associated target map lane line, after determining that the map lane line has not changed, the method further includes: Obtain the recorded sensed lane lines and the recorded target map lane lines, as well as the number of consecutive frames they exist; If the continuous number of frames is less than or equal to the frame number threshold, the map lane line change detection is completed; If the number of consecutive frames is greater than the frame number threshold, data reporting is performed.

7. The method according to claim 6, characterized in that If the continuous number of frames is greater than the frame number threshold, after the data is reported, the method further includes: Outputting the recorded sensed lane line and the recorded target map lane line; or, The sensor data within a preset time before and after the change is acquired, and the sensor data is packaged and cached for subsequent analysis.

8. A map lane line change detection device, characterized in that: The device comprises: An acquisition device, used to acquire map lane lines and sense lane lines; A merging device, used for merging the map lane lines according to the area where the map lane lines are located, to obtain a merged target map lane line; An associating device, used to associate the sensed lane line with the target map lane line to obtain an associating result; A judgment device, used for determining whether the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line when the association result is that the perceived lane line is associated with the target map lane line; The determination device is used to determine that the map lane line has not changed when the lane line type of the perceived lane line is consistent with the corresponding associated target map lane line.

9. A map lane line change detection 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 map lane line change detection method according to any one of claims 1 to 7.

10. 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 map lane line change detection method according to any one of claims 1 to 7 are implemented.

Images