Lane centerline recognition method, device, equipment, storage medium and product

Abstract

The application discloses a lane center line recognition method, device, equipment, storage medium and product, relates to the automatic driving technical field, and discloses a lane center line recognition method, comprising the following steps: acquiring a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a last road image frame; determining a first coordinate point in the target coordinate point set and a second coordinate point in the first boundary range; removing the first coordinate point corresponding to the lane line, and splicing the target lane line based on the second coordinate point to obtain spliced lane line data. The application removes the repeated coordinate points of the target lane line in the new road image frame through the first boundary range of the target lane line in the last road image frame, avoids the situation that the coordinate sequence of the same lane line in different frames is inconsistent in direction, and improves the accuracy of lane line recognition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and particularly relates to a lane center line identification method and device, equipment, a storage medium and a product. BACKGROUND

[0002] Accurate detection of lane center lines in data segments plays a crucial role in vehicle navigation and control.

[0003] Generally, the related art performs image processing on road images to extract lane line features to determine lane lines. However, in practice, due to factors such as vehicle movement and environmental changes, the lane line coordinate points in each frame of road images change, which makes the coordinate sequence of the same lane line in different frames inconsistent in direction, and thus affects the accuracy of lane line identification.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a lane center line identification method, which aims to solve the technical problem of low accuracy of lane line identification due to inconsistent direction of the coordinate sequence of the same lane line in different frames.

[0006] To achieve the above purpose, the present application provides a lane center line identification method, which comprises:

[0007] obtaining a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame;

[0008] determining a first coordinate point in the target coordinate point set within the first boundary range and a second coordinate point outside the first boundary range;

[0009] de-duplicating the lane line corresponding to the first coordinate point, and splicing the target lane line based on the second coordinate point to obtain spliced lane line data.

[0010] Optionally, after the step of de-duplicating the lane line corresponding to the first coordinate point and splicing the target lane line based on the second coordinate point to obtain spliced lane line data, the method comprises:

[0011] determining the minimum coordinate value of each coordinate system corresponding to each first coordinate point, and determining the maximum coordinate value of each coordinate system corresponding to each second coordinate point;

[0012] determine a second boundary range of the target lane line in the current road image frame based on the minimum coordinate value of each coordinate system and the maximum coordinate value of each coordinate system, wherein the second boundary range is used to realize splicing of the target lane line in a next road image frame.

[0013] Optionally, after the step of obtaining the target coordinate point set of the target lane line in the current road image frame and the first boundary range of the target lane line in the previous road image frame, the method comprises:

[0014] constructing a global grid;

[0015] mapping each coordinate point in the target coordinate point set to the global grid to determine a corresponding perception map of the current road image frame;

[0016] The step of determining the first coordinate point in the target coordinate point set that is within the first boundary range and the second coordinate point in the target coordinate point set that is outside the first boundary range comprises:

[0017] determining the first coordinate point in the target coordinate point set that is within the first boundary range and the second coordinate point in the target coordinate point set that is outside the first boundary range based on the perception map.

[0018] Optionally, the step of mapping each coordinate point in the target coordinate point set to the global grid to determine a corresponding perception map of the current road image frame comprises:

[0019] determining a first distance between each coordinate point in the target coordinate point set and the vehicle, and saving each coordinate point in the target coordinate point set into a coordinate sequence in ascending order of the first distance to obtain a coordinate sequence of the target lane line;

[0020] mapping the coordinate sequence to a corresponding position in the grid to obtain an initial grid;

[0021] performing a thinning operation on the initial grid to obtain a target grid, and determining a corresponding perception map of the current road image frame based on the target grid.

[0022] Optionally, the step of performing a thinning operation on the initial grid to obtain a target grid comprises any one of the following:

[0023] performing a first thinning operation on the initial grid to obtain a target grid;

[0024] performing a first thinning operation on the initial grid, and performing a second thinning operation on the network after the first thinning operation to obtain a target grid, wherein the thinning operation comprises a floor operation or a rounding operation.

[0025] Optionally, the step of performing the thinning operation on the initial grid to obtain a target grid comprises:

[0026] sequentially calculating a second distance between adjacent coordinate points of the coordinate sequence in the initial grid;

[0027] judging whether the second distance is less than a preset distance threshold;

[0028] if the second distance is less than the preset distance threshold, deleting the coordinate point with a greater first distance among the adjacent coordinate points to obtain a thinned coordinate sequence, and returning to the step of sequentially calculating the second distance between adjacent coordinate points of the coordinate sequence in the initial grid until the second distance between adjacent coordinate points of the coordinate sequence in the initial grid is all less than the preset distance threshold to obtain a target grid.

[0029] In addition, to achieve the above object, the present application further provides a lane center line recognition device, which comprises:

[0030] an acquisition module, configured to acquire a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame;

[0031] a determination module, configured to determine a first coordinate point in the target coordinate point set within the first boundary range and a second coordinate point outside the first boundary range;

[0032] a de-duplication module, configured to perform de-duplication processing on a lane line corresponding to the first coordinate point, and perform splicing of the target lane line based on the second coordinate point to obtain spliced lane line data.

[0033] In addition, to achieve the above object, the present application further provides a lane center line recognition device, which comprises 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 lane center line recognition method as described above.

[0034] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the lane center line recognition method as described above.

[0035] In addition, to achieve the above object, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the lane center line recognition method as described above.

[0036] The one or more technical solutions provided in the application have at least the following technical effects:

[0037] In the related art, lane line features in road images are usually extracted by using image processing and machine learning algorithms, and complete lane lines are recognized and spliced. However, the coordinate points of lane lines in each frame of road images change with the movement of the vehicle and the change of the environment, so that the coordinate sequences of the same lane line in different frames may be inconsistent in direction, thereby causing low accuracy of lane line recognition. In comparison, the application obtains a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame; determines first coordinate points in the first boundary range and second coordinate points outside the first boundary range in the target coordinate point set; performs deduplication processing on the lane line corresponding to the first coordinate points, and splices the target lane line based on the second coordinate points to obtain spliced lane line data. It can be understood that the application needs to obtain the first boundary range of the target lane line in the previous road image frame, wherein the boundary range is determined according to the coordinate points of the target lane line in the previous road image frame. And each time the application receives a new road image frame, it determines the coincident coordinate points (i.e. first coordinate points) and non-coincident coordinate points (i.e. second coordinate points) between the target coordinate point set of the target lane line in the road image frame and the first boundary range, wherein the coincident coordinate points will cause the coordinate sequence of the lane center line to be abnormal, so deduplication is performed, and the target lane line is spliced according to the second coordinate points, which can avoid the situation that the coordinate sequences of the same lane line in different frames are inconsistent in direction. That is, by removing the duplicate coordinate points of the target lane line in the new road image frame through the first boundary range of the target lane line, it is ensured that the coordinate sequence of the target lane line will not have reverse points due to duplicate data, thereby improving the accuracy of lane line recognition. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the application and, together with the specification, serve to explain the principles of the application.

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, those skilled in the art can obtain other drawings from these drawings without creative labor.

[0040] Figure 1 A flowchart is provided for the first embodiment of the lane center line recognition method of the application;

[0041] Figure 2A flowchart provided for the second embodiment of the lane centerline recognition method of the present application is shown in FIG. 1.

[0042] Figure 3 A module structure diagram of the lane centerline recognition device of the embodiment of the present application is shown in FIG. 2.

[0043] Figure 4 A device structure diagram of the hardware running environment involved in the lane centerline recognition method of the embodiment of the present application is shown in FIG. 3.

[0044] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0046] In order to better understand the technical solutions of the present application, the specific embodiments will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0047] The main solution of the embodiment of the present application is: obtaining a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame; determining a first coordinate point in the first boundary range and a second coordinate point outside the first boundary range in the target coordinate point set; performing a de-duplication processing on the lane line corresponding to the first coordinate point, and performing a splicing of the target lane line based on the second coordinate point, to obtain the spliced lane line data.

[0048] In the embodiment, the lane centerline recognition device is taken as the execution subject, and for the convenience of description, it is referred to as "device" in the following.

[0049] In the related art, the lane line features in the road image are usually extracted by using image processing and machine learning algorithm, and the complete lane line is recognized and spliced. However, since the lane line coordinate points in each frame of road image change with the movement of the vehicle and the change of the environment, the coordinate sequence of the same lane line in different frames may appear inconsistent in direction, which further leads to low accuracy of lane line recognition.

[0050] The present application provides a solution to realize the splicing of the lane centerline, and further improve the accuracy of lane line recognition.

[0051] From the above embodiment, it can be seen that the present application removes the repeated coordinate points of the target lane line in the new road image frame by the cumulative boundary range of the target lane line, avoids the situation that the coordinate sequence of the same lane line in different frames may appear inconsistent in direction, and further improves the accuracy of lane line recognition.

[0052] It should be noted that the execution subject of the embodiment can 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 or the like, or an electronic device, a terminal system or the like capable of realizing the above functions. The following takes a lane center line recognition device as an example to describe the embodiment and the following embodiments.

[0053] Based on this, the application provides a lane center line recognition method, which refers to Figure 1 , Figure 1 The flowchart of the first embodiment of the lane center line recognition method of the application is shown in the figure.

[0054] In the embodiment, the lane center line recognition method comprises steps S100-S300:

[0055] In step S100, a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame are acquired.

[0056] It should be noted that the target coordinate point set refers to a coordinate point set on the lane line recognized by a lane line detection algorithm in the current road image frame, wherein the target coordinate point can be an end point, an inflection point or a point sampled according to a certain rule, which collectively defines the position and shape of the lane line in the image; the first boundary range refers to a boundary box determined according to the target lane line coordinate points in the previous road image frame of the current road image frame, and the boundary range is also the horizontal and vertical range of the lane line in the image, wherein the cumulative boundary range can be understood as the minimum circumscribed rectangle or polygon of the lane line in the image, which contains all parts of the lane line and can be used to represent the global position and coverage range of the lane line.

[0057] In a specific implementation, the application proposes to define a dictionary screen_lane_center_polyline for storing different lane center line splicing information, wherein the dictionary comprises key values and value values, the key value is a lane center line index, and the value value is a coordinate point list of the lane center line appearing in a scene segment, and reverse point elimination is performed based on the corresponding lane grid of the previous frame. Further, the application proposes to define a grid_scope for recording boundary information dictionaries of the same lane center line appearing in the historical frames at the most recent time, wherein the key value is a lane center line index, and the value value is a coordinate space range boundary of the same lane center line in the historical frames at the most recent time from the current frame, which is represented by x_min, x_max, y_min and y_max.

[0058] In specific implementation, the device obtains a road image through receiving an information collection module on the vehicle, wherein the road image comprises a plurality of image frames, and in an embodiment, the device can use a deep learning model such as a convolutional neural network to identify a target lane line in the image frames and determine coordinate points of the target lane line and a first boundary range.

[0059] In specific implementation, the device obtains a target coordinate point set of the target lane line in the current road image frame, comprising:

[0060] obtaining a current road image frame; extracting vehicle position information and an initial coordinate point set of the target lane line from the current road image frame; converting the initial coordinate point set of the target lane line from a global coordinate system to a local coordinate system with the vehicle as the origin based on the vehicle position information, to obtain a target coordinate point set of the target lane line.

[0061] In specific implementation, the device obtains an image of a road on which the vehicle travels at a current time from a vehicle-mounted camera, and the image contains visual information of the road, lane line, and environment around the vehicle. Further, the device can extract the accurate position and pose (including position coordinates and direction) of the vehicle on the road from the current road image frame through sensors (such as GPS, IMU, wheel speed sensor, etc.) of the vehicle or visual algorithms (such as feature matching, SLAM, etc.); the device can use a lane line detection algorithm (such as a deep learning-based model) to identify the target lane line from the image and extract a series of coordinate points on the target lane line to form an initial coordinate point set of the target lane line, which defines the position of the lane line in the image coordinate system.

[0062] In specific implementation, the device converts the initial coordinate point set of the target lane line from a global coordinate system to a local coordinate system with the vehicle as the origin. Specifically, this step involves coordinate transformation, and the purpose is to convert the points on the lane line from the global coordinate system (such as the road coordinate system) to the local coordinate system with the vehicle as the center. The purpose of this is to simplify subsequent processing, because in the local coordinate system, the position of the vehicle is fixed (origin), and the relative position relationship between the lane line and the vehicle becomes more intuitive. Further, the above conversion process needs to know the pose (position and direction) of the vehicle relative to the global coordinate system, and then apply geometric transformation (such as translation and rotation) to map the points on the lane line from the global coordinate system to the local coordinate system. This transformation can be achieved through matrix operations, including rotation matrix and translation vector, etc.

[0063] In specific implementation, after the conversion is completed, the device obtains a coordinate point set in the local coordinate system of the vehicle, which is the lane line coordinate point (i.e., the target coordinate point), and the target coordinate point describes the specific position and shape of the lane line relative to the vehicle.

[0064] In a specific implementation, the step of converting the initial coordinate point set of the target lane line from the global coordinate system to the local coordinate system with the vehicle as the origin based on the vehicle position information includes:

[0065] The vehicle coordinate value and the vehicle orientation angle in the vehicle position information are extracted, the coordinate translation value of each initial coordinate point is calculated by subtracting the vehicle coordinate value from the corresponding coordinate value of each initial coordinate point in the initial coordinate point set of the target lane line, the rotation angle of the target lane line is calculated based on the vehicle orientation angle, and the initial coordinate point set of the target lane line is converted from the global coordinate system to the local coordinate system with the vehicle as the origin based on the coordinate translation value and the rotation angle to obtain the target coordinate point set of the target lane line.

[0066] It should be noted that the vehicle coordinate is the position of the vehicle in the global coordinate system, which is usually represented as (x, y) coordinates, and the vehicle coordinate value is the value of the vehicle on the x-axis coordinate system and the value of the vehicle on the y-axis coordinate system; the vehicle orientation angle is the orientation of the vehicle relative to the global coordinate system, represented as an angle value, used to describe the pointing direction of the vehicle.

[0067] In a specific implementation, the device first obtains corresponding map data information (map_data_item) from the information of the road image frame. Then, the position information of the ego vehicle is extracted therefrom, including the X coordinate (ego_x), the Y coordinate (ego_y), and the orientation angle (ego_theta).

[0068] In a specific implementation, the coordinate point P on the target lane line lane_center is (global_x, global_y), and the coordinate position of any point P in the ego vehicle coordinate system is calculated as follows:

[0069] x_diff = global_x - ego_x;

[0070] y_diff = global_y - ego_y;

[0071] angle_cos = math.cos(ego_theta);

[0072] angle_sin = math.sin(ego_theta);

[0073] local_x = x_diff * angle_cos - y_diff * angle_sin;

[0074] local_y = x_diff * angle_sin + y_diff * angle_cos.

[0075] wherein, x_diff is the translation value of point P in the x direction relative to the ego vehicle, specifically, the difference between the global x coordinate of point P and the global x coordinate of the ego vehicle is calculated; y_diff is the translation value of point P in the y direction relative to the ego vehicle, specifically, the difference between the global y coordinate of point P and the global y coordinate of the ego vehicle is calculated; angle_cos refers to the cosine value of the heading angle of the ego vehicle; angle_sin refers to the sine value of the heading angle of the ego vehicle; local_x refers to the x coordinate of point P in the local coordinate system, specifically, the translation value in the x direction is multiplied by the cosine value, the translation value in the y direction is multiplied by the sine value, and the subtraction is obtained; local_y refers to the y coordinate of point P in the local coordinate system, specifically, the translation value in the x direction is multiplied by the sine value, the translation value in the y direction is multiplied by the cosine value, and the addition is obtained.

[0076] In a specific implementation, the above conversion process is to first translate point P to the position of the ego vehicle, and then rotate according to the heading angle of the ego vehicle, and finally obtain the position of point P in the local coordinate system with the ego vehicle as the origin.

[0077] Step S200, determining a first coordinate point in the first boundary range and a second coordinate point outside the first boundary range in the target coordinate point set;

[0078] In a specific implementation, the first coordinate point refers to the coordinate point in the target coordinate point set within the first boundary range, and the first coordinate point can be understood as the coordinate point that appears in the current image frame and is repeated in the last image frame. Since the repeated coordinate point will be repeatedly recorded in the coordinate sequence, the directionality will be confused, thereby affecting the directionality of the entire coordinate sequence and generating reverse points. That is, the repeated coordinate point will cause the coordinate sequence of the lane center line to be abnormal. By removing the repeated coordinate point, it can be ensured that the coordinate sequence of the target lane line will not appear reverse points due to repeated data.

[0079] Further, the second coordinate point refers to the coordinate point in the target coordinate point set outside the first boundary range, and the second coordinate point can be understood as the extension part of the lane line in the image.

[0080] Step S300, performing a de-duplication process on the lane line corresponding to the first coordinate point, and performing a splicing of the target lane line based on the second coordinate point to obtain the spliced lane line data.

[0081] In a specific implementation, the apparatus performs deduplication on the lane line corresponding to the first coordinate points, i.e., the apparatus removes or merges those repeated or redundant coordinate points, to ensure that the coordinate sequence of the target lane line does not have reverse points due to repeated data. The deduplication process can be achieved by checking the distance, angle or other geometric features between consecutive points to ensure the smoothness and continuity of the lane line.

[0082] Further, the apparatus stitches the target lane line based on the second coordinate points, i.e., the apparatus includes these points outside the boundary range into the representation of the lane line to expand the data of the lane line, wherein the stitching process involves coordinate transformation, interpolation or other geometric algorithms to ensure that the newly added points are geometrically consistent with the existing lane line data, thereby obtaining a continuous and complete lane line representation.

[0083] In a specific implementation, after the step of deduplicating the lane line corresponding to the first coordinate points and stitching the target lane line based on the second coordinate points to obtain the stitched lane line data, the method comprises:

[0084] determining the minimum coordinate values of each coordinate system respectively corresponding to each first coordinate point, and determining the maximum coordinate values of each coordinate system respectively corresponding to each second coordinate point; based on the minimum coordinate values of each coordinate system and the maximum coordinate values of each coordinate system, determining a second boundary range of the target lane line in the current road image frame, wherein the second boundary range is used to implement the stitching of the target lane line in the next road image frame.

[0085] In a specific implementation, the apparatus determines the minimum coordinate values of each coordinate system respectively corresponding to each first coordinate point, i.e., in the lane line detection process, for the second coordinate points outside the first boundary range (i.e., the points that do not exceed the boundary of the target lane line in the previous image frame), the apparatus needs to determine their minimum coordinate values in the respective coordinate systems. The apparatus determines the maximum coordinate values of each coordinate system respectively corresponding to each second coordinate point, i.e., in the lane line detection process, for the second coordinate points outside the first boundary range (i.e., those points that exceed the boundary of the current lane line), the apparatus needs to determine their maximum coordinate values in the respective coordinate systems. These coordinate values include the minimum x value, the minimum y value, the maximum x value, the maximum y value, etc., which represent the boundary range of the lane line in each direction.

[0086] Further, the minimum coordinate values of each coordinate system and the maximum coordinate values of each coordinate system are used to determine a second boundary range of the target lane line in the current road image frame, wherein the second boundary range is used to implement the stitching of the target lane line in the next road image frame.

[0087] It can be understood that the lane line splicing method is preferably used in a lane turning driving scenario (i.e., a lane line change scenario), and by using only the boundary range of the previous image frame, the lane center line splicing in the lane line change scenario is realized.

[0088] In the related art, lane line features in a road image are usually extracted by using image processing and machine learning algorithms, and a complete lane line is recognized and spliced. However, because the coordinate points of the lane line in each frame of the road image change with the movement of the vehicle and the change of the environment, the coordinate sequence of the same lane line in different frames may be inconsistent in direction, and thus the accuracy of lane line recognition is low. In comparison, the present application obtains a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame; determines first coordinate points in the first boundary range and second coordinate points outside the first boundary range in the target coordinate point set; performs deduplication processing on the lane line corresponding to the first coordinate points, and splices the target lane line based on the second coordinate points to obtain spliced lane line data. It can be understood that the present application needs to obtain the first boundary range of the target lane line in the previous road image frame, wherein the boundary range is determined according to the coordinate points of the target lane line in the previous road image frame. And each time a new road image frame is received, the present application determines the coincident coordinate points (i.e., the first coordinate points) and the non-coincident coordinate points (i.e., the second coordinate points) between the target coordinate point set of the target lane line in the road image frame and the first boundary range, wherein the coincident coordinate points will cause the coordinate sequence of the lane center line to be abnormal, and thus the coincident coordinate points are deduplicated, and the target lane line is spliced according to the second coordinate points, so that the coordinate sequence of the target lane line will not have reverse points due to repeated data, and thus the accuracy of lane line recognition is improved.

[0089] Based on the above first embodiment, the present application further proposes another embodiment, with reference to Figure 2 The lane center line recognition method comprises:

[0090] Step A100, obtaining a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame;

[0091] Step A100 is equivalent to step S100 described above, and thus is not described herein again.

[0092] Step A200, constructing a global grid;

[0093] In a specific implementation, constructing a global grid refers to creating a global grid model in the process of constructing a perception map, which can cover the entire road environment. The global grid as a basic framework of the map can be used to integrate and align data from different sensors and different time points to construct a continuous and consistent map representation.

[0094] Step A300, mapping each coordinate point in the target coordinate point set to the global grid to determine the perception map corresponding to the current road image frame;

[0095] In a specific implementation, the device maps each coordinate point in the target coordinate point set to the global grid to determine the perception map corresponding to the current road image frame, that is, converts each coordinate point on the lane line from its local coordinates in the image to global coordinates in the global grid. Specifically, the device converts points in the local coordinate system to the global coordinate system, which can understand and process these points in a unified reference frame.

[0096] Further, by mapping these points to the global grid, the device can construct a perception map of the current road image frame, which contains the position, shape and other related road information of the lane line.

[0097] In a specific implementation, the device maps each coordinate point in the target coordinate point set to the global grid to determine the perception map corresponding to the current road image frame, which includes:

[0098] Determine the first distance between each coordinate point in the target coordinate point set and the vehicle, and save each coordinate point in the coordinate sequence in ascending order of the first distance to obtain the coordinate sequence of the target lane line; map the coordinate sequence to the corresponding position in the grid to obtain an initial grid; perform a thinning operation on the initial grid to obtain a target grid, and determine the perception map corresponding to the current road image frame based on the target grid.

[0099] In a specific implementation, the device determines the first distance between each coordinate point in the target coordinate point set and the vehicle, that is, the device calculates the distance from the current position of the vehicle to each coordinate point on the target lane line. This distance refers to the straight-line distance from the vehicle to each coordinate point, which can be used for subsequent sorting and grid construction.

[0100] In a specific implementation, the device sequentially saves each coordinate point into a coordinate sequence in ascending order of the first distance, obtaining the coordinate sequence of the target lane line, that is, the device sorts the coordinate points in ascending order of their distance from the vehicle according to the calculated distance and saves them into a sequence. In this way, a distance-sorted coordinate sequence can be obtained, which can be used for subsequent lane line splicing and map construction.

[0101] In a specific implementation, the device maps the coordinate sequence to corresponding positions in a grid to obtain an initial grid, that is, the device maps each coordinate point in the sorted coordinate sequence to a predefined grid. This grid can be a two-dimensional grid system, and each grid represents a region in the map. In this way, an initial grid containing all lane line information can be constructed.

[0102] It should be noted that the thinning operation refers to reducing the number of points in the grid to simplify the grid and improve processing efficiency. It is usually achieved by removing redundant points or merging similar points. Thinning operations can include floor operations or rounding operations, as well as other algorithms such as Voxel Grid filtering.

[0103] In a specific implementation, the device determines a perception map corresponding to the current road image frame based on the target grid, that is, the device determines the perception map of the current road image frame using the target grid after thinning processing. The perception map is a representation of the road environment in an autonomous driving system, which contains the position, shape, and other related road information of the lane line.

[0104] In a specific implementation, the step of the device performing a thinning operation on the initial grid to obtain a target grid includes any of the following:

[0105] performing a first thinning operation on the initial grid to obtain a target grid;

[0106] performing a first thinning operation on the initial grid and performing a second thinning operation on the grid after the first thinning operation to obtain a target grid, wherein the thinning operation includes a floor operation or a rounding operation.

[0107] In a specific implementation, the device performs a first thinning operation on the initial grid, wherein the thinning operation refers to reducing the number of points in the grid to simplify the grid and improve processing efficiency. The first thinning operation can be a floor operation or a rounding operation, depending on the specific application requirements and algorithm design, to obtain a target grid. The target grid refers to the grid obtained after the first thinning operation. This grid is more sparse than the initial grid, but still retains the key information of the lane line.

[0108] Further, the device can perform a second thinning operation on the basis of the first thinning operation to achieve higher processing efficiency or meet specific application requirements. Specifically, the thinning operation includes rounding down or rounding up, that is, the first thinning operation and the second thinning operation are not the same, and the first thinning operation can be a rounding down operation and the second thinning operation can be a rounding up operation, or the first thinning operation can be a rounding up operation and the second thinning operation can be a rounding down operation.

[0109] In a specific implementation, the step of performing a thinning operation on the initial grid to obtain a target grid includes:

[0110] The second distance between adjacent coordinate points in the coordinate sequence in the initial grid is sequentially calculated, it is determined whether the second distance is less than a preset distance threshold, if the second distance is less than the preset distance threshold, a coordinate point with a larger first distance is deleted from the adjacent coordinate points to obtain a thinned coordinate sequence, and the step of sequentially calculating the second distance between adjacent coordinate points in the coordinate sequence in the initial grid is returned until the second distance between adjacent coordinate points in the coordinate sequence in the initial grid is less than the preset distance threshold, and a target grid is obtained.

[0111] First, in the initial grid, the device calculates the second distance between adjacent coordinate points in the coordinate sequence, where the distance refers to the straight-line distance between two adjacent coordinate points. Second, the device compares the calculated second distance with a preset distance threshold, where the threshold is determined according to specific application requirements and algorithm design to control the density of thinning. Then, if the second distance is less than the preset distance threshold, it indicates that the distance between the two adjacent coordinate points is too close, and one of the two points can be deleted to reduce redundancy, and the specific deleted point is the point with a larger first distance (i.e., the point farther from the vehicle) in the two adjacent coordinate points. Further, after the redundant coordinate point is deleted, a thinned coordinate sequence is obtained, and the first step is returned to recalculate the second distance between adjacent coordinate points in the thinned coordinate sequence. This process is repeated until the second distance between all adjacent coordinate points in the coordinate sequence is greater than or equal to the preset distance threshold. At this time, the obtained coordinate sequence is the target grid after thinning.

[0112] In a specific implementation, the above process is a thinning process on the coordinate sequence in the initial grid to reduce redundant coordinate points and improve processing efficiency. The thinning process is achieved by calculating the distance between adjacent coordinate points and comparing it with the preset distance threshold.

[0113] In step A400, based on the perception map, a first coordinate point in the target coordinate point set within the first boundary range and a second coordinate point outside the first boundary range are determined.

[0114] In a specific implementation, the device determines, on the perception map, a first coordinate point in the coordinate point set that is within the accumulated boundary range and a second coordinate point that is outside the accumulated boundary range.

[0115] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the lane center line identification method of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0116] The present application also provides a lane center line identification device, which refers to Figure 3 The lane center line identification device comprises:

[0117] The acquisition module 10 is configured to acquire a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame.

[0118] The determination module 20 is configured to determine a first coordinate point in the target coordinate point set that is within the first boundary range and a second coordinate point that is outside the first boundary range.

[0119] The de-duplication module 30 is configured to perform de-duplication processing on a lane line corresponding to the first coordinate point and perform splicing of a target lane line based on the second coordinate point to obtain spliced lane line data.

[0120] Optionally, the lane center line identification device further comprises:

[0121] The coordinate value determination module is configured to determine minimum coordinate values of respective coordinate systems corresponding to respective first coordinate points and maximum coordinate values of respective coordinate systems corresponding to respective second coordinate points.

[0122] The boundary range determination module is configured to determine a second boundary range of a target lane line in a current road image frame based on the minimum coordinate values of the respective coordinate systems and the maximum coordinate values of the respective coordinate systems, wherein the second boundary range is used to realize splicing of the target lane line in a next road image frame.

[0123] Optionally, the lane center line identification device further comprises:

[0124] The construction module is configured to construct a global grid.

[0125] The mapping module is configured to map each coordinate point in the target coordinate point set to the global grid to determine a corresponding perception map of the current road image frame.

[0126] Optionally, the determination module 20 comprises:

[0127] The coordinate point determination module is used to determine, based on the perception map, a first coordinate point within the first boundary range and a second coordinate point outside the first boundary range in the target coordinate point set.

[0128] Optionally, the mapping module includes:

[0129] The coordinate sequence determination module is used to determine the first distance between each coordinate point in the target coordinate point set and the vehicle, and save each coordinate point in the coordinate sequence in ascending order based on the first distance to obtain the coordinate sequence of the target lane line;

[0130] A coordinate mapping module is used to map the coordinate sequence to corresponding positions in the grid to obtain an initial grid.

[0131] The thinning module is used to perform a thinning operation on the initial grid to obtain a target grid, and based on the target grid, determine the corresponding perception map of the current road image frame.

[0132] Optionally, the thinning module includes:

[0133] A primary thinning module is used to perform a first thinning operation on the initial mesh to obtain the target mesh;

[0134] The secondary thinning module is used to perform a first thinning operation on the initial mesh and a second thinning operation on the mesh after the first thinning operation to obtain the target mesh. The thinning operation includes a down-rounding operation or a rounding-to-the-floor operation.

[0135] Optionally, the thinning module includes:

[0136] The distance calculation module is used to sequentially calculate the second distance between adjacent coordinate points in the coordinate sequence of the initial grid;

[0137] The judgment module is used to determine whether the second distance is less than a preset distance threshold;

[0138] The iterative thinning module is used to delete the coordinate points with larger first distances among the adjacent coordinate points if the second distance is less than a preset distance threshold, to obtain a thinned coordinate sequence, and return to the step of sequentially calculating the second distance between adjacent coordinate points in the coordinate sequence of the initial grid, until the second distance between adjacent coordinate points in the coordinate sequence of the initial grid is less than the preset distance threshold, thus obtaining the target grid.

[0139] The lane center line recognition device provided by the present application can solve the technical problem of lane center line recognition. Compared with the prior art, the lane center line recognition device provided by the present application has the same beneficial effects as the lane center line recognition method provided by the above-mentioned embodiments, and other technical features of the lane center line recognition device are the same as the features disclosed in the above-mentioned embodiments, which will not be repeated here.

[0140] The present application provides a lane center line recognition device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the lane center line recognition method in the above-mentioned embodiment one.

[0141] Reference will be made to the following description of the drawings Figure 4 which shows a structural schematic diagram of a lane center line recognition device suitable for implementing the embodiments of the present application. The lane center line recognition device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 4 The lane center line recognition device shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0142] As Figure 4As shown, the lane centerline recognition device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the lane centerline recognition device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 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), a speaker, a vibrator, etc.; the 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 centerline recognition device to communicate with other devices wirelessly or by wire to exchange data. Although the lane centerline recognition device with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0143] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0144] The lane centerline recognition device provided by the present disclosure adopts the lane centerline recognition method in the above-mentioned embodiments, and can solve the technical problem of lane centerline recognition. Compared with the prior art, the lane centerline recognition device provided by the present disclosure has the same beneficial effects as the lane centerline recognition method provided by the above-mentioned embodiments, and other technical features in the lane centerline recognition device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0145] It should be understood that portions of the application disclosed can be implemented in hardware, software, firmware, or combinations thereof. In the description of the embodiments above, specific features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0146] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any changes or modifications that can be made to the application in accordance with the principles of the application would be readily apparent to persons skilled in the art and the generic principles of the application defined herein are intended to include all such changes and modifications. The scope of the application is therefore intended to be defined only by the scope of the claims presented and equivalents thereof.

[0147] The application provides a computer-readable storage medium having stored thereon computer-readable program instructions (i.e., computer programs) for performing the lane centerline recognition method in the above-described embodiments.

[0148] The computer-readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer diskette, 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 the present embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium can be transmitted in any suitable medium, including but not limited to electrical wires, optical fibers, RF (Radio Frequency), and the like, or any suitable combination thereof.

[0149] The above-described computer-readable storage medium can be included in the lane centerline recognition device; or can exist separately and not be assembled into the lane centerline recognition device.

[0150] The above-described computer-readable storage medium carries one or more programs, which, when executed by the lane centerline recognition device, cause the lane centerline recognition device to recognize the lane centerline.

[0151] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can 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 the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0152] The flow diagrams and the block diagrams in the drawings are meant as methodological and functional description of implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0153] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0154] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer programs) for executing the lane center line identification method described above, and can solve the technical problem of lane center line identification. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the lane center line identification method provided by the above embodiments, which will not be described here.

[0155] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the lane centerline identification method as described above.

[0156] The computer program product provided by the application can solve the technical problem of lane centerline identification. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the lane centerline identification method provided by the above-mentioned embodiments, and will not be described here.

[0157] The above only describes some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or the like made by using the content of the application specification and drawings within the technical concept of the application is included in the patent protection scope of the application.

Claims

1. A method of identifying a center line of a lane, characterized by, The method for identifying the lane center line comprises: obtaining a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame; determining first coordinate points in the target coordinate point set within the first boundary range and second coordinate points outside the first boundary range; performing deduplication processing on lane lines corresponding to the first coordinate points and performing splicing of the target lane line based on the second coordinate points to obtain spliced lane line data; after the step of performing deduplication processing on lane lines corresponding to the first coordinate points and performing splicing of the target lane line based on the second coordinate points to obtain spliced lane line data, the method comprises: determining minimum coordinate values of respective coordinate systems corresponding to the respective first coordinate points and maximum coordinate values of the respective coordinate systems corresponding to the respective second coordinate points; based on the minimum coordinate values of the respective coordinate systems and the maximum coordinate values of the respective coordinate systems, determining a second boundary range of the target lane line in the current road image frame, wherein the second boundary range is used to realize splicing of the target lane line in a next road image frame.

2. The method of identifying a centerline of a lane according to claim 1, wherein, after the step of obtaining a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame, the method comprises: constructing a global grid; mapping each coordinate point in the target coordinate point set to the global grid to determine a corresponding perception map of the current road image frame; the step of determining first coordinate points in the target coordinate point set within the first boundary range and second coordinate points outside the first boundary range comprises: based on the perception map, determining first coordinate points in the target coordinate point set within the first boundary range and second coordinate points outside the first boundary range.

3. The method of claim 2, wherein the step of mapping each coordinate point in the target coordinate point set to the global grid to determine a corresponding perception map of the current road image frame comprises: determining a first distance between each coordinate point in the target coordinate point set and a vehicle, and saving each coordinate point in a coordinate sequence in ascending order of the first distance to obtain a coordinate sequence of the target lane line; mapping the coordinate sequence to a corresponding position in the grid to obtain an initial grid; performing a thinning operation on the initial grid to obtain a target grid, and determining a corresponding perception map of the current road image frame based on the target grid.

4. The method of claim 3, wherein the step of performing a thinning operation on the initial grid to obtain a target grid comprises any one of the following: performing a first thinning operation on the initial grid to obtain a target grid; performing a first thinning operation on the initial grid and performing a second thinning operation on the network after the first thinning operation to obtain a target grid, wherein the thinning operation includes a floor operation or a rounding operation.

5. The method of claim 3, wherein the lane centerline is identified by: the step of performing a thinning operation on the initial grid to obtain a target grid comprises: successively calculating a second distance between adjacent coordinate points in the coordinate sequence of the initial grid; determining whether the second distance is less than a preset distance threshold; if the second distance is less than the preset distance threshold, deleting the coordinate point with a larger first distance in the adjacent coordinate points to obtain a thinned coordinate sequence, and returning to the step of sequentially calculating the second distance between the adjacent coordinate points of the coordinate sequence in the initial grid until the second distance between the adjacent coordinate points of the coordinate sequence in the initial grid is greater than or equal to the preset distance threshold, to obtain a target grid.

6. A device for recognizing a center line of a lane, characterized by The device comprises: an acquisition module configured to acquire a target coordinate point set of a target lane line in a current road image frame and a first boundary range of the target lane line in a previous road image frame; a determination module configured to determine a first coordinate point in the target coordinate point set within the first boundary range and a second coordinate point outside the first boundary range; a deduplication module configured to perform deduplication processing on a lane line corresponding to the first coordinate point and perform splicing of the target lane line based on the second coordinate point to obtain spliced lane line data. After the step of performing deduplication processing on the lane line corresponding to the first coordinate point and performing splicing of the target lane line based on the second coordinate point to obtain spliced lane line data, the method comprises: determining minimum coordinate values of each coordinate system respectively corresponding to each first coordinate point and maximum coordinate values of each coordinate system respectively corresponding to each second coordinate point; determining a second boundary range of the target lane line in the current road image frame based on the minimum coordinate values of the coordinate systems and the maximum coordinate values of the coordinate systems, wherein the second boundary range is used to realize splicing of the target lane line in a next road image frame.

7. A lane centerline recognition device characterized by comprising: The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the lane center line identification method according to any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the lane center line identification method according to any one of claims 1 to 5.

9. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by a processor to implement the steps of the lane center line identification method according to any one of claims 1 to 5.

Images