Lane path-based stop line distance determination method, device, medium and program product

Abstract

The application provides a lane path-based stop line distance determination method, device, medium and program product. The method comprises the following steps: determining a region of interest, which comprises a plurality of lane regions, each lane region corresponding to a lane path; performing continuous processing on each lane path to generate a path reference curve constructed by a plurality of path points arranged continuously, and taking the intersection position of each path reference curve and the corresponding stop line as a starting point to calculate the path cumulative distance of each path point on the path reference curve to the corresponding stop line; constructing a distance mapping configuration table of the mapping relationship between the path points and the corresponding path cumulative distance; obtaining the position information of a target and generating the corresponding index key value according to the position information, querying the corresponding path cumulative distance in the distance mapping configuration table through the index key value, and determining the distance between the target and the corresponding stop line. The application realizes high real-time response efficiency while ensuring high-precision ranging.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method, device, medium and program product for determining stop line distance based on lane path. Background Technology

[0002] Vehicle-to-everything (V2X) technology deploys various sensor devices in road infrastructure, such as cameras, millimeter-wave radar, and lidar typically installed on the roadside, to perceive and collect information about road traffic scenarios in real time. This information includes parameters such as the location, type, size, and heading angle of traffic-related targets. The perception results are then transmitted to vehicle-side or cloud-based systems to support traffic operation analysis and decision-making. For example, on the vehicle side, the perceived information can be used to implement functions such as hazard warnings and overtaking assistance. On the cloud side, traffic signal timing strategies can be dynamically adjusted based on the distance between special targets and intersections to improve the passage efficiency of special vehicles.

[0003] In the aforementioned application scenarios, obtaining the distance information between the target and the road stop line is one of the crucial fundamental parameters. Currently, existing technologies typically estimate the distance between the target and the stop line by calculating the geometric straight-line distance between the target location and a fixed position in the lane, i.e., the Euclidean distance. When using this method, it is usually necessary to first determine the lane to which the target belongs, and then select the stop line position of the corresponding lane for distance calculation. However, Euclidean distance is essentially the straight-line distance between two points, and it only has good reference value in ideal straight-ahead lane scenarios. When the road has complex structures such as curves or irregular intersections, vehicles typically travel along the centerline path of the lane with a certain curvature. In this case, the straight-line distance between the target and the stop line is equivalent to the chord length of the arc of the path, which is difficult to accurately reflect the actual distance traveled by the vehicle to reach the stop line, i.e., the arc length distance. This leads to significant deviations in the distance measurement results, making it difficult to support the distance accuracy requirements of application scenarios such as cloud-based traffic signal timing.

[0004] Therefore, there is a lack of existing technologies that can accurately obtain the true distance between the target and the stop line in order to better meet the needs of vehicle-road cooperative systems for refined traffic control and auxiliary decision-making based on distance information. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application provides a method, device, medium, and program product for determining stop line distance based on lane path, which at least solves the problem in existing technologies of difficulty in accurately obtaining the distance from the target along the actual path of the lane to the stop line.

[0006] To achieve the above objectives and other advantages, some embodiments of this application provide the following aspects:

[0007] In a first aspect, some embodiments of this application provide a method for determining stop line distance based on lane path, including:

[0008] Determine the region of interest, which includes multiple lane regions, and each lane region corresponds to a lane path;

[0009] For each lane path, a continuous processing is performed to generate a path reference curve constructed from multiple consecutively arranged path points. The cumulative path distance from each path reference curve to the corresponding stop line is calculated, starting from the intersection of each path reference curve and the corresponding stop line.

[0010] Construct a distance mapping configuration table that maps the path points to the cumulative distances of the corresponding paths;

[0011] Obtain the target's location information and generate a corresponding index key value based on the location information. Use the index key value to query the corresponding cumulative path distance in the distance mapping configuration table to determine the distance between the target and the corresponding stop line.

[0012] Secondly, some embodiments of this application also provide an electronic device, the electronic device comprising:

[0013] One or more processors; and a memory storing computer program instructions that, when executed, cause the processors to perform the lane path-based stop line distance determination method as described above.

[0014] Thirdly, some embodiments of this application also provide a computer-readable storage medium having a computer program and / or instructions stored thereon, which, when executed by a processor, implement the lane path-based stop line distance determination method as described above.

[0015] Fourthly, some embodiments of this application also provide a computer program product, including a computer program and / or instructions, which, when executed by a processor, implement the lane path-based stop line distance determination method as described above.

[0016] Compared with existing technologies, the solution provided in this application constructs a path reference curve by performing continuous processing on the paths of each lane within the region of interest. This transforms the originally discrete map information into a mathematical model that can accurately simulate vehicle trajectories. Based on this model, the cumulative distance along the path is calculated. This fundamentally solves the ranging deviation caused by traditional Euclidean distance in scenarios with curves or complex intersections, ensuring the authenticity and accuracy of distance feedback. Furthermore, by pre-constructing a distance mapping configuration table that stores the cumulative distance mapping relationship between path points and corresponding stop lines, the complex spatial geometric calculation and curve integration process is transferred to the offline preprocessing stage. This allows for result retrieval in online real-time applications using only simple index keys, significantly reducing online computational complexity while maintaining distance calculation accuracy. This achieves both high-precision ranging and extremely high real-time response efficiency, thus providing more reliable and efficient distance parameter support for auxiliary decision-making such as traffic signal timing optimization in vehicle-road cooperative scenarios. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other implementation methods can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for determining stop line distance based on lane path, provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram illustrating the process of calculating the distance between path points on the path reference curve and generating the cumulative path distance in an embodiment of this application.

[0020] Figure 3 This is an example visualization of a map projected onto a bird's-eye view in an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of the lanes in the bird's-eye view coordinate system in the embodiments of this application;

[0022] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Some embodiments of this application relate to a method for determining stop line distance based on lane paths, applicable to roadside perception and cloud-based traffic control environments in vehicle-road cooperative transportation systems. In specific applications, road infrastructure typically deploys various sensing devices such as cameras, millimeter-wave radar, and lidar to perceive road traffic scenes in real time, acquiring spatial location information of various traffic participants on the road. Simultaneously, it combines high-precision maps or road topology data to obtain lane structure information and stop line location information. The roadside perception device or cloud processing unit fuses the perceived data and map data, identifying multiple lane regions and their corresponding lane paths within a preset region of interest, providing fundamental data support for subsequent calculations of the distance between targets and stop lines.

[0025] In a specific application scenario, this method can be applied to intersection traffic signal control systems. By acquiring the real-time position of each target vehicle in the lane and calculating its distance from the lane path to the stop line, it provides accurate distance parameters to support cloud-based traffic signal timing optimization, vehicle queue length estimation, or priority passage control for special vehicles. It can also be applied to vehicle-road cooperative assisted driving systems to provide the vehicle with more realistic distance information from the target to the intersection stop line, enabling functions such as hazard warning, speed guidance, and passage decision-making.

[0026] In its implementation, this method can be executed by a roadside computing unit, a cloud server, or an in-vehicle computing device. These computing devices typically include a processor, memory, and a communication interface. The processor executes computer program instructions stored in the memory to perform processes such as determining the region of interest, lane path continuity processing, calculating cumulative path distance, constructing a distance mapping configuration table, and querying the target distance. The memory stores map data, perception data, and the distance mapping configuration table. The communication interface is used for data interaction with roadside perception devices or in-vehicle terminals.

[0027] Reference Figure 1 As shown, the method may include the following steps:

[0028] Step S1: Determine the region of interest, which includes multiple lane regions, and each lane region corresponds to a lane path.

[0029] The region of interest (ROI) can be set based on the coverage area of ​​road intersections or object detection. For example, centered on the stop line at the intersection, a preset range can be determined in a spatial coordinate system using road structure information. This ROI covers the range of all lanes where vehicles may reach the stop line. Specifically, the boundary parameters of the ROI in the spatial coordinate system can be obtained based on high-precision map data or road topology data to define the lateral and longitudinal extent of the ROI.

[0030] After identifying the region of interest (ROI), the geometric information of each lane within the ROI is extracted from the map data. Based on the lane's physical boundaries, the ROI is divided into multiple lane regions, each corresponding to an actual lane on the road. A lane region can be defined by the lane's left and right boundary lines or a lane polygonal outline, representing the drivable space within that lane. For each lane region, its corresponding lane centerline or lane reference line is obtained as the lane path. The lane path consists of multiple nodes distributed along the lane's direction, describing the vehicle's trajectory direction within that lane. Through this process, multiple lane regions and their corresponding lane paths are formed within the ROI, providing fundamental data support for subsequent lane path continuity and density processing and target distance calculation.

[0031] Step S2: Perform continuous processing on the path of each lane to generate a path reference curve constructed from multiple consecutively arranged path points. Starting from the intersection of each path reference curve and the corresponding stop line, calculate the cumulative path distance from each path point on the path reference curve to the corresponding stop line.

[0032] The geometric information of the lane centerline corresponding to each lane path is obtained from map data or road topology data. The lane centerline is composed of multiple original centerline nodes distributed sequentially along the lane driving direction. Since the spacing between adjacent original centerline nodes is relatively large, in order to improve the continuity and accuracy of the path description, interpolation processing is performed between adjacent original centerline nodes based on the physical distance between nodes and the lane curvature characteristics to form a path reference curve composed of multiple continuously arranged path points, thereby realizing the continuous expression of the lane path.

[0033] In an optional embodiment, step S2 involves performing continuous processing on each lane path to generate a path reference curve constructed from multiple consecutively arranged path points, specifically including:

[0034] Step S201: Obtain multiple original centerline nodes on the centerline of the lane corresponding to the lane path.

[0035] Lane centerlines are typically composed of multiple discrete initial centerline nodes distributed sequentially along the lane's direction of travel. Each node has corresponding two-dimensional or three-dimensional coordinates in a spatial coordinate system, describing the lane's orientation on the road plane. For example, in an intersection scenario, straight lanes, left-turn lanes, and right-turn lanes each correspond to different lane centerlines, and each lane centerline is formed by sequentially connecting several initial centerline nodes to create an initial path profile. By obtaining these multiple initial centerline nodes, the discrete geometric representation of each lane centerline can be preliminarily determined, providing basic node data for subsequent path continuity processing.

[0036] Step S202: Interpolate the original centerline nodes based on the spacing between adjacent original centerline nodes to generate multiple interpolated nodes between adjacent original centerline nodes.

[0037] In an optional embodiment, step S202 specifically includes:

[0038] Step S2021: Determine the interpolation point resolution based on the curvature characteristics of the lane centerline.

[0039] In this embodiment, to ensure that the lane centerline achieves a matching path point density under different road conditions, the interpolation point resolution is adaptively determined based on the curvature characteristics of the lane centerline. Specifically, geometric analysis is performed on multiple original centerline nodes continuously distributed along the lane centerline. By selecting multiple adjacent nodes to construct a local fitting curve, the curvature value or radius of curvature of the corresponding road segment is calculated to characterize the degree of curvature of the lane centerline within that region.

[0040] When the radius of curvature corresponding to the lane centerline is detected to be greater than a preset threshold, the current road segment is determined to be a straight road segment. For example, when the radius of curvature R is greater than 500 meters, it indicates that the road direction in this area changes little. In this case, a larger interpolation point resolution is set as the spatial sampling step size, such as a range of 0.5 meters to 1.0 meters, that is, 1 to 2 path points are distributed per meter of physical distance. This increases the relative spacing between adjacent path points, thereby reducing the number of path points while ensuring the accuracy of the basic geometric feature description of the path, reducing the storage size of the subsequent distance mapping configuration table, and improving the efficiency of subsequent distance queries. When the centerline of the lane is detected to be... When the radius of curvature corresponding to the center line is greater than another preset threshold, the current road segment is determined to be a curved road segment or a turning area. For example, when the radius of curvature R is less than 50 meters, it indicates that there is obvious curvature or sharp turn in the area. In order to avoid the cumulative distance error caused by the approximation of curves with straight lines due to the sparse path points, the system reduces the interpolation point resolution accordingly and sets the spatial sampling step size to 0.1 meters (10 path points are evenly distributed on each meter of path) or smaller, so that the path points are more densely distributed. This allows the discretized path point sequence to accurately approximate the shape of the real lane curve and ensure the accuracy of the driving distance calculation results in the curved environment.

[0041] Step S2022: Calculate the physical distance between adjacent original centerline nodes on the lane centerline.

[0042] The original centerline node sequence along the lane centerline is traversed, and two adjacent original centerline nodes arranged along the lane's driving direction are selected as the node pairs to be processed. For any pair of adjacent original centerline nodes, their coordinate values ​​in the spatial coordinate system are obtained to characterize the geometric positional relationship of the nodes in the road plane. Subsequently, the physical distance between the two nodes is calculated based on the coordinate information of the adjacent original centerline nodes to obtain a distance parameter reflecting the actual spatial interval between adjacent nodes.

[0043] The physical distance *dis* between two adjacent original centerline nodes can be calculated using the following formula:

[0044]

[0045] Where (x0,y0) represents the coordinates of the starting node of the interval to be interpolated; and (x1,y1) represents the coordinates of the ending node of the interval to be interpolated.

[0046] Step S2023: Based on the interpolation point resolution and physical distance, determine the number of interpolation nodes to be generated between adjacent original centerline nodes.

[0047] After obtaining the physical distance *dis* between adjacent original centerline nodes and the interpolation point resolution *gridSize* of the corresponding road segment, the number of interpolation nodes to be generated within the adjacent node interval is determined based on their relationship. Specifically, the physical distance *dis* is compared with the interpolation point resolution *gridSize* to represent the number of path points to be deployed within the current distance range according to the preset spatial sampling step size. The calculation result is then rounded up to ensure that the spacing between interpolated path points is not greater than the set interpolation point resolution, thereby avoiding the problem of decreased path approximation accuracy due to insufficient number of nodes. The formula for calculating the number of interpolation nodes can be expressed as:

[0048]

[0049] Where num represents the number of interpolation nodes generated between two adjacent original centerline nodes; ceil represents the round-up function.

[0050] Step S2024: Determine the interpolation step size based on the number of interpolation nodes and the projection difference of adjacent original centerline nodes in the coordinate axis direction.

[0051] After determining the number of interpolation nodes to be generated between adjacent original centerline nodes, `num`, the positional changes of two adjacent original centerline nodes along each coordinate axis are calculated to determine the uniform distribution step size of the interpolation nodes in space. Specifically, the coordinate differences between adjacent original centerline nodes in the horizontal and vertical coordinate directions are obtained as the projection differences of the path along the two coordinate axes. The projection differences along the two coordinate axes are proportionally allocated to the number of interpolation nodes, `num`, to calculate the interpolation step size in the horizontal and vertical coordinate directions, ensuring that the interpolation nodes generated between two original nodes are uniformly arranged along the node connection direction. Through the above processing, it is ensured that each interpolation node is distributed in space at a fixed interval, thereby maintaining the continuity and smoothness of the path reference curve. The corresponding interpolation step size calculation formula can be expressed as:

[0052]

[0053]

[0054] Where, d x d y These represent the interpolation step size in the horizontal and vertical directions, respectively.

[0055] Step S2025: Based on the interpolation step size, generate interpolation nodes between adjacent original centerline nodes.

[0056] The interpolation step size d between adjacent original centerline nodes in each coordinate axis direction is obtained.x With d y Then, using the initial original centerline node as the reference point, the path point coordinates are recursively calculated according to the interpolation step size, thereby generating multiple interpolation nodes between two adjacent original centerline nodes. Specifically, starting from the coordinates of the initial original centerline node, the interpolation step size is accumulated sequentially along the direction of the line connecting adjacent nodes, generating new path point coordinates in each recursive process. In a specific embodiment, the coordinates of the i-th interpolation node can be obtained in the following way:

[0057]

[0058]

[0059] Where i is a positive integer, and i < num.

[0060] Through the above recursive method, multiple uniformly distributed interpolation nodes are generated sequentially between the two original centerline nodes, thereby filling the spatial gap between the original nodes and transforming the lane centerline from a sparse node sequence into a continuous and dense path point sequence.

[0061] Through the processing in steps S2021 to S2025, on the one hand, by using a larger interpolation resolution on straight road sections and a smaller interpolation resolution on curved road sections, the path point density is adaptively adjusted. This effectively controls the number of path points while ensuring the geometric approximation accuracy of the curved path, avoiding the storage and computational burden caused by invalid redundant data. On the other hand, by calculating the number of interpolation nodes based on the actual physical distance and uniformly generating interpolation nodes according to the coordinate projection direction, the path reference curve maintains continuity and scale consistency throughout the entire road section, thereby significantly improving the accuracy and stability of subsequent cumulative distance calculations along the path.

[0062] Step S203: Arrange the interpolation nodes and the original centerline nodes in the order of the lane driving direction to form a continuous sequence of path points to construct the path reference curve.

[0063] After generating interpolation nodes between adjacent original centerline nodes, the obtained original centerline nodes and corresponding interpolation nodes are integrated to construct a complete and continuous path point sequence. Specifically, the original centerline nodes corresponding to each lane path are used as the basic node set, and the generated interpolation nodes are sequentially inserted between the corresponding adjacent original centerline nodes, allowing the interpolation nodes to naturally connect adjacent original nodes in spatial position. Subsequently, the original centerline nodes and interpolation nodes are sequentially arranged according to the driving direction of the lane. The specific sorting rule can be based on the cumulative path distance of the nodes at the starting point of the path (i.e., the intersection with the stop line), with the node closest to the stop line as the starting node, and subsequent nodes arranged in ascending order along the lane extension direction; or it can be based on the original sequential index of the nodes on the lane centerline, thereby ensuring that the path point sequence strictly follows the actual driving direction of the vehicle.

[0064] Through steps S201-S203, the originally discrete centerline nodes with uneven node spacing are organically combined with the interpolated nodes to form a continuous sequence of path points along the lane travel direction. This constructs a complete and continuous path reference curve, making the path reference curve geometrically smoother and more coherent, avoiding path breaks or geometric approximation errors caused by sparse nodes. Simultaneously, by uniformly sorting the original and interpolated nodes according to the lane travel direction, the consistency and directional correctness of the path point sequence in spatial arrangement are ensured, allowing the constructed path reference curve to accurately reflect the actual driving trajectory of the vehicle on the road. This provides a stable and reliable path foundation for subsequent distance accumulation calculations and the construction of a distance mapping configuration table along the path.

[0065] In an optional embodiment, step S2, taking the intersection of each path reference curve and the corresponding stop line as the starting point, calculates the cumulative path distance from each path point on the path reference curve to the corresponding stop line, specifically including:

[0066] Step S204: Arrange the path points on the path reference curve in the direction away from the stop line to obtain an ordered sequence of path points with the starting point as the first node;

[0067] Step S205: Calculate the distance between two adjacent path points in the ordered path point sequence;

[0068] Step S206: Based on the distance between two adjacent path points, perform distance accumulation processing on each path point in the ordered path point sequence in turn to obtain the path length along the line of each path point relative to the starting point, which is used as the cumulative path distance.

[0069] Specifically, the geometric intersection between the path reference curve and the stop line is identified, and the path point corresponding to this intersection is determined as the starting point for calculating the cumulative path distance. The path points on the path reference curve are rearranged according to the lane travel direction, with the starting point serving as the first node of the ordered path point sequence. The remaining path points are arranged sequentially in order of gradually moving away from the stop line along the lane extension direction, thus forming an ordered path point sequence extending backward from the stop line.

[0070] The ordered sequence of path points is traversed, and two adjacent path points p in the sequence are selected in turn. i With p i+1 And calculate the physical distance Δd between the two path points based on their spatial coordinate information. i The Euclidean distance method can be used to calculate the spatial distance between adjacent path points by summing the squares of the coordinate differences along each coordinate axis and taking the square root. Since the lane centerline has been subjected to high-density interpolation in the preceding steps, the distance between adjacent path points is kept within a small range. Therefore, the distance between adjacent path points can approximate the actual arc length of the small path segment with high accuracy.

[0071] Using the starting node as the distance to zero, and following the ordered sequence of path points, calculate the distance Δd between adjacent path points. i A segment-by-segment accumulation process is performed. The cumulative path distance corresponding to the starting node is set to zero, and the distance between adjacent path points in the first segment is used as the cumulative path distance value for the second path point. Subsequently, the distances of each subsequent segment are added to the cumulative distance of the previous node, thus obtaining the cumulative path distance of each path point in the sequence relative to the stop line position. In one specific implementation, the cumulative path distance D of the k-th path point... k It can be represented as:

[0072]

[0073] Where, Δd i Indicates adjacent path points p i With p i+1 The physical distance between them.

[0074] like Figure 2 As shown, the path points on the path reference curve are p1, p2, p3, p4, p5, and p6, respectively. Path point p1 is located at the stop line and is the starting node for calculating the cumulative path distance. First, the distance between adjacent path points is calculated; for example, the distance dis between path points p1 and p2 is calculated. 12 The distance between path points p2 and p3 is dis 23 The distance between path points p3 and p4 is dis34 The distance between path points p4 and p5 is dis 45 And the distance dis between path points p5 and p6 56 .

[0075] Subsequently, taking path point p1 as the starting reference point, its cumulative path distance is set to zero, and the distance dis is... 12 As the cumulative path distance from path point p2 to the stop line, dis 12 with dis 23 The accumulated value is used as the cumulative path distance from path point p2 to the stop line, and the distances between subsequent adjacent path points are accumulated segment by segment to obtain the cumulative path distances corresponding to path points p4, p5, and p6 respectively.

[0076] Starting from the point where the stop lines intersect, traverse all path points along the lane centerline in a direction away from the stop lines. During this process, for each path point p... i Each is constructed as a data vector containing geometric spatial information and distance metric information, represented as follows:

[0077]

[0078] Among them, spatial coordinates represents the three-dimensional geometric position of the i-th path point in the spatial coordinate system; represents the physical distance between two adjacent path points in the ordered sequence (i.e., the (i-1)-th point and the i-th point); represents the cumulative path distance of the i-th path point.

[0079] Through steps S204-S206, the path points on the path reference curve are sequentially arranged and their distances are accumulated segment by segment. This ensures that each path point on the path reference curve uses the stop line position as a unified distance starting point, and the corresponding cumulative path distance is obtained along the lane travel direction. This allows the obtained cumulative path distance to accurately represent the actual physical distance traveled by the vehicle along the lane centerline to the stop line. Therefore, the distance calculation result between the target and the stop line no longer relies on the approximation of the straight-line geometric distance between the two points, but is accumulated based on the actual travel path. This significantly reduces distance measurement errors in scenarios such as curves, ramps, and complex intersections, improving the reliability and applicability of the distance calculation results in vehicle-road cooperative signal control and decision-making applications.

[0080] Step S3: Construct a distance mapping configuration table to establish the mapping relationship between path points and their corresponding cumulative path distances. After calculating the cumulative path distances for each path point on the path reference curve, a distance mapping configuration table is constructed to establish the mapping relationship between path points and their cumulative path distances. This enables quick querying of the distance from any target location within the space to the stop line. The distance mapping configuration table is used to associate spatial locations within the area of ​​interest with the cumulative path distances on the corresponding lane paths. This allows for direct retrieval of the distance from the target to the stop line via indexing after obtaining target location information, without the need for real-time path searching and distance accumulation calculations.

[0081] In an optional embodiment, step S3 specifically includes:

[0082] Step S301: Determine the set of pixel coordinates covered by each lane area within the region of interest. Based on the lane boundary information described in the map data, and combined with the boundary range of the region of interest in the spatial coordinate system, the region of interest is projected and transformed to the bird's-eye view coordinate system, and the pixel area range corresponding to each lane area in the bird's-eye view is identified. The pixel area corresponding to each lane area is traversed, and all pixel coordinate points within that pixel area are extracted, thus forming the set of pixel coordinates corresponding to each lane area.

[0083] In an optional embodiment, step S301 specifically includes:

[0084] Step S3011: Extract the lane physical boundary information of each lane area in the spatial coordinate system from the map data.

[0085] The physical boundary information of each lane region in the spatial coordinate system is extracted from map data to describe the geometric extent of each lane in the real road environment. Lane physical boundary information may include the left and right boundary lines of the lane or the polygonal outline enclosing the lane region. It is typically composed of a series of physical location coordinate points arranged in spatial order, each of which can be represented in two-dimensional or three-dimensional coordinate form as (x,y) or (x,y,z). The lane physical boundary can be formed by sequentially connecting adjacent boundary nodes to create a closed or semi-closed polygonal region, used to fully characterize the lateral width and longitudinal extension direction of a single lane in the spatial coordinate system. Through the geometric definition of lane physical boundary information, the spatial positional relationship of different lane regions within the region of interest can be clearly distinguished, providing the basic geometric input for subsequent projection mapping of lane regions onto the bird's-eye view coordinate system to form pixel region ranges.

[0086] Step S3012: Obtain the boundary parameters of the region of interest in the spatial coordinate system and the pixel resolution parameters used to characterize the number of pixels per unit spatial distance.

[0087] Obtain the boundary parameters of the region of interest in the spatial coordinate system, including the minimum boundary value in the lateral direction. With maximum boundary value and the minimum boundary value in the longitudinal direction. With maximum boundary value The `pixel2dist` parameter is used to define the coverage area of ​​the region of interest in the spatial coordinate system. Simultaneously, it acquires the pixel resolution parameter `pixel2dist`, which represents the number of pixels corresponding to a unit spatial distance in the bird's-eye view coordinate system. This establishes a proportional mapping between the spatial coordinates and the pixel coordinates of the bird's-eye view, indicating the number of pixels corresponding to each meter of physical distance in the bird's-eye view. For example, when `pixel2dist` is set to 10, it means that 1 meter of physical length in the spatial coordinate system corresponds to 10 pixel units in the bird's-eye view; when `pixel2dist` is set to 5, it means that each meter of physical distance corresponds to 5 pixel units. By adjusting the value of the `pixel2dist` parameter, the spatial discretization accuracy of the bird's-eye view can be flexibly controlled. When the value of `pixel2dist` is larger, the number of pixels corresponding to a unit physical distance increases, making the representation of lane boundaries and lane centerlines more refined in pixel space, which is beneficial to improving the accuracy of the subsequent distance mapping configuration table. When the value of `pixel2dist` is smaller, it can effectively reduce the size of the pixel data, thereby reducing the storage overhead and computational load of the distance mapping configuration table. In practical applications, the value of pixel2dist can be set according to the spatial range of the region of interest, system storage resources, and computing power to achieve a balance between distance mapping accuracy and system resource consumption.

[0088] Step S3013: Based on the minimum lateral boundary value of the boundary parameters, calculate the lateral offset of the lane physical boundary information relative to the starting boundary of the region of interest, and perform proportional mapping transformation and rounding on the lateral offset according to the pixel resolution parameters to obtain the pixel lateral boundary range of the lane area in the bird's-eye view coordinate system.

[0089] Step S3014: Based on the minimum longitudinal boundary value of the boundary parameters, calculate the longitudinal offset of the lane physical boundary information relative to the starting boundary of the region of interest, and perform proportional mapping transformation and rounding on the longitudinal offset according to the pixel resolution parameters. At the same time, combine the height parameters of the bird's-eye view corresponding to the region of interest to perform mirror offset, and obtain the pixel longitudinal boundary range of the lane area in the bird's-eye view coordinate system.

[0090] Based on the boundary parameters and pixel resolution parameters obtained in step S3012, coordinate mapping transformation is performed on the physical boundary information of the lane area in the spatial coordinate system, and it is projected onto the bird's-eye view coordinate system to determine the pixel boundary range corresponding to each lane area.

[0091] In the horizontal direction, the minimum horizontal boundary value of the region of interest in the spatial coordinate system is used. As the initial reference boundary, the lateral offset of each spatial coordinate point in the lane physical boundary relative to the initial boundary is calculated. The pixel horizontal coordinates are obtained by combining the pixel resolution parameter `pixel2dist` with scaling transformation and rounding down. In the vertical direction, the minimum vertical boundary value of the region of interest in the spatial coordinate system is used. As the initial reference boundary, the longitudinal offset of each spatial coordinate point in the lane physical boundary relative to the initial boundary is calculated. The pixel resolution parameter `pixel2dist` is then used for scaling and rounding down. Since the spatial coordinate system and the bird's-eye view coordinate system have opposite coordinate directions in the vertical direction, the vertical pixel coordinates are further mirrored using the corresponding height parameter from the bird's-eye view to obtain the corresponding vertical pixel coordinates. The horizontal and vertical pixel coordinates can be calculated using the following formulas:

[0092]

[0093] )

[0094] in, () represents the two-dimensional coordinates of the lane's physical boundary point in the spatial coordinate system; , These represent the minimum boundary values ​​of the region of interest in the horizontal and vertical directions in the spatial coordinate system, respectively, and are used as the starting reference boundary during the bird's-eye view projection transformation; floor(·) represents the floor function; These represent the horizontal and vertical pixel coordinates of the lane area in the bird's-eye view coordinate system, respectively, used to determine the horizontal and vertical pixel boundaries of the lane area in the bird's-eye view; height represents the vertical height of the region of interest in the bird's-eye view coordinate system.

[0095] The height of the bird's-eye view coordinate system in the vertical direction is determined based on the vertical span of the region of interest in the spatial coordinate system. The specific calculation method is as follows:

[0096]

[0097] in, , This represents the maximum and minimum boundary values ​​of the region of interest in the longitudinal direction of the spatial coordinate system; ceil(·) represents the rounding up function.

[0098] Through the aforementioned horizontal and vertical mapping transformations, the geometric positions of the lane physical boundaries in the spatial coordinate system are projected onto the bird's-eye view coordinate system, forming corresponding pixel boundary ranges to define the pixel coverage area of ​​each lane region in the bird's-eye view. For example... Figure 3 As shown, after scaling and mirror offset processing, the geometric structure of the multi-lane road within the region of interest is projected onto the bird's-eye view coordinate system, forming a corresponding pixelated spatial representation. The light blue curve represents the centerline path of each lane, the colored lines represent the physical boundary of each lane area, and the blue arrows indicate the direction of travel. Each lane area forms a clear pixel boundary coverage region in the bird's-eye view.

[0099] Step S3015: For each lane area, determine the pixel area defined by the horizontal boundary range and the vertical boundary range of the pixel, and traverse and extract the pixel coordinates within the pixel area to form a set of pixel coordinates covered by each lane area.

[0100] After obtaining the pixel lateral boundary range and pixel vertical boundary range of each lane area in the bird's-eye view coordinate system through steps S3013 and S3014 respectively, the corresponding pixel area is determined based on the aforementioned pixel boundary range. Specifically, for each lane area, the minimum and maximum horizontal coordinates in the pixel lateral boundary range are used as the start and end values ​​for lateral traversal, and the minimum and maximum vertical coordinates in the pixel vertical boundary range are used as the start and end values ​​for vertical traversal, thus constructing the corresponding pixel coverage area in the bird's-eye view coordinate system.

[0101] According to the preset traversal rules, all pixel positions within the pixel coverage area are scanned point by point, and the coordinates of each pixel within the pixel area are extracted sequentially. The extracted pixel coordinates are then uniformly stored in the pixel coordinate set of the corresponding lane area. Through the above traversal method, each lane area can form a pixel coordinate set that completely covers its physical space, used to represent all discrete spatial positions of the lane area in the bird's-eye view coordinate system. In practical applications, the above traversal process can be implemented using a double-loop method, that is, scanning column by column within the horizontal pixel range, and simultaneously scanning row by row within each column within the vertical pixel range, thereby efficiently extracting the pixel coordinates of all pixels within the pixel area.

[0102] Through steps S3011-S3015, the physical boundary areas of each lane described in continuous spatial coordinates in the high-precision map are accurately mapped and transformed to discrete pixel space in the bird's-eye view coordinate system. Based on the pixel boundary range, each lane area is fully discretized, forming a set of pixel coordinates corresponding to each lane area. This processing method achieves precise scale alignment between the physical road space and the pixel index space, ensuring that any spatial location within the lane area can find a unique corresponding pixel representation in the bird's-eye view. By performing pixel-level discrete coverage of the lane areas, the integrity and continuity of the lane space range during the mapping process are guaranteed. It also provides a unified data infrastructure for establishing a rapid mapping relationship between pixel coordinates and cumulative path distances, allowing the target to be directly located to the corresponding lane path distance from any position using pixel indexing, thus avoiding the computational overhead of traditional path-by-path search and real-time geometric calculation.

[0103] Step S302: Convert each pixel coordinate in the pixel coordinate set into physical position coordinates in the same coordinate system as the path reference curve.

[0104] After projecting the lane areas from the spatial coordinate system to the bird's-eye view coordinate system, each lane area is discretized as a regular indexed region composed of a large number of pixel coordinates. This indexed region facilitates efficient traversal and mapping relationship construction. However, pixel coordinates are only used for index representation and do not inherently possess the meaning of actual physical distance, while the path reference curve and its corresponding cumulative path distance are constructed based on the spatial coordinate system. To achieve the geometric correspondence between pixel positions and path reference curves, a reverse mapping process is performed on each pixel coordinate, converting the pixel coordinates into corresponding physical position coordinates, so that each discrete pixel position is re-corresponding to a specific physical position in the spatial coordinate system.

[0105] like Figure 4 As shown, the shaded area represents the target lane region in the current example. This region, in the bird's-eye view coordinate system, consists of a large number of discrete pixels, used to cover the geometric extent of the lane in pixel space. A point-by-point traversal is performed on the set of pixel coordinates within this lane region. For any pixel coordinate... By combining the boundary parameters of the region of interest in the spatial coordinate system and the pixel resolution parameters, the region is converted into its corresponding physical location coordinates according to a preset inverse coordinate transformation relationship. The calculation method for physical location coordinates can be expressed as follows:

[0106]

[0107]

[0108] in, This indicates the pixel coordinates of the lane area in the bird's-eye view coordinate system; pixel2dist indicates the number of pixels per unit physical distance. , These represent the minimum boundary values ​​of the region of interest in the horizontal and vertical directions in the spatial coordinate system, respectively; height represents the vertical height of the region of interest in the bird's-eye view coordinate system. This indicates the actual physical location of the corresponding pixel in the spatial coordinate system.

[0109] Through the aforementioned inverse transformation process, the discrete pixels originally located in the bird's-eye view pixel space are remapped back to their specific physical locations in the spatial coordinate system, thus placing each pixel location in the same coordinate system as the path reference curve. Based on this unified coordinate foundation, in subsequent steps, the nearest path point can be accurately matched on the path reference curve of the corresponding lane using the physical location coordinates as input, and the cumulative path distance corresponding to that pixel location can be obtained, achieving precise mapping of the distance from any position in the lane to the stop line.

[0110] Step S303: Based on the physical location coordinates, match the nearest path point on the corresponding path reference curve, and associate the cumulative path distance corresponding to the matched nearest path point with the pixel coordinates.

[0111] In this embodiment, after completing the inverse transformation from pixel coordinates to physical location coordinates, the obtained physical location coordinates are used as the matching benchmark to perform the nearest path point matching operation on the path reference curve of the corresponding lane. Specifically, for multiple consecutive path points on the path reference curve, the spatial distance between each path point and the current physical location coordinates is calculated, and the path point with the smallest spatial distance is selected as the target matching path point. Since the path reference curve has formed a high-density distributed sequence of path points through continuous interpolation, the path reference curve can accurately approximate the actual driving trajectory of the lane. Therefore, the target matching path point can be approximately regarded as the projection position of the physical location coordinates on the lane driving path. Subsequently, the pre-calculated cumulative path distance of the target matching path point is read, and a correspondence is established between the cumulative path distance and the current pixel coordinates, thereby realizing the mapping association between the pixel spatial position and the driving distance along the lane path. Through the above processing, each pixel coordinate point obtains a corresponding real driving distance attribute, which is used to construct a distance mapping configuration table and support quick query of the distance from any target position within the lane area to the stop line.

[0112] In one optional embodiment, to reduce the computational overhead of nearest path point matching, instead of calculating the distance to each path point on the path reference curve one by one, a set of candidate path points is first determined based on physical location coordinates. Then, the spatial distance is calculated among the candidate path point sets, and the one with the smallest distance is selected as the target matching path point. The set of candidate path points can be obtained in any of the following ways: searching for path points in adjacent grids based on the spatial grid cells where the physical location coordinates are located; or selecting path points within a preset window range near the previous matching index based on the driving direction sequence of the path point sequence; or performing a nearest neighbor search on the path reference curve through a pre-constructed spatial index structure to obtain a preset number of nearest neighbor path points. By performing distance calculation only on the set of candidate path points, the computational load can be reduced while ensuring matching accuracy.

[0113] Step S304: Use a preset index function to generate a unique index key value for the pixel coordinates, and store the index key value and the corresponding cumulative path distance to build a distance mapping configuration table.

[0114] The construction of the distance mapping configuration table can be completed in the offline preprocessing stage to achieve digital calibration of each lane area within the region of interest. This offline calibration process aims to establish the correspondence between the spatial location of pixels within the lane area and the actual driving distance. By performing full coverage processing on the pixel locations of each lane within the region of interest, each pixel coordinate is assigned a corresponding cumulative path distance attribute, thereby forming a layer of digital distance field distribution representing the driving distance in the bird's-eye view coordinate system.

[0115] In an optional embodiment, step S304 specifically includes:

[0116] Step S3041: Determine the length range in the horizontal direction based on the minimum and maximum horizontal boundary values ​​of the boundary parameters, and determine the length range in the vertical direction based on the minimum and maximum vertical boundary values ​​of the boundary parameters.

[0117] Step S3042: Compare the length range values ​​in the vertical direction with those in the horizontal direction;

[0118] Step S3043: When the length range value in the vertical direction is greater than the length range value in the horizontal direction, multiply the pixel horizontal coordinate in the pixel coordinates with the height of the bird's-eye view corresponding to the region of interest, and add the product result to the pixel vertical coordinate in the pixel coordinates to generate an index key value;

[0119] Step S3044: When the length range value in the vertical direction is less than or equal to the length range value in the horizontal direction, multiply the vertical coordinate of the pixel in the pixel coordinates with the width of the bird's-eye view corresponding to the region of interest, and add the product result to the horizontal coordinate of the pixel in the pixel coordinates to generate an index key value;

[0120] Step S3045: Use the generated index key value as the key and the corresponding cumulative path distance as the value to construct a key-value pair and store it in the distance mapping configuration table.

[0121] Specifically, the pixel size range of the bird's-eye view in the horizontal and vertical directions is determined. Based on the boundary parameters of the region of interest in the spatial coordinate system, the minimum boundary value in the horizontal direction is obtained. With maximum boundary value ,according to and Determine the range of length values ​​in the horizontal direction ( ); and obtain the minimum boundary value in the longitudinal direction. With maximum boundary value ,according to and Determine the range of length values ​​in the vertical direction .

[0122] By combining the pixel resolution parameter `pixel2dist`, the aforementioned physical length range is mapped to the corresponding pixel width and pixel height in the bird's-eye view coordinate system, which are used to characterize the overall size of the region of interest in the bird's-eye view. The horizontal pixel width of the bird's-eye view can be determined as follows:

[0123]

[0124] Here, ceil(·) represents the floor function; pixel2dist represents the number of pixels per unit physical distance.

[0125] Similarly, the vertical pixel height of the bird's-eye view can be obtained, which is used to represent the pixel size range of the region of interest in the vertical direction. The specific calculation method is as follows:

[0126]

[0127] For the range of length values ​​in the horizontal direction ( ) and the length range in the vertical direction The comparison is used to determine the expansion direction to be used when generating subsequent index key values. When Greater than ( When ), choose the vertical direction as the main unfolding direction; when Less than or equal to ( When selecting the horizontal direction, the index generation method is chosen based on the size ratio of the region of interest. The expansion method for converting two-dimensional pixel coordinates into one-dimensional indexes is dynamically selected, ensuring that all pixel positions are compactly and uniquely numbered. This guarantees the continuity and uniqueness of the index mapping space in bird's-eye views at different size ratios.

[0128] When the judgment Greater than ( When this condition is met, it indicates that the region of interest has a larger pixel span in the vertical direction. In this case, the vertical expansion method is preferred for generating index key values. The pixel horizontal coordinate in the current pixel coordinate is then used. Multiply by the bird's-eye view height parameter, and then multiply the product by the pixel ordinate. The sum is used to generate the corresponding index key value haxiIndice, whose indexing function is:

[0129]

[0130] When the judgment Less than or equal to ( When the region of interest (ROI) spans at least as many pixels horizontally as vertically, a horizontal expansion method is preferred for generating index key values. The ordinate of the current pixel coordinates is then used to... Multiply by the width parameter of the bird's-eye view, and then multiply the product with the pixel x-coordinate. The sum is used to generate the corresponding index key value haxiIndice, whose indexing function is:

[0131]

[0132] This unfolding method allows two-dimensional pixel coordinates to be continuously mapped into a one-dimensional index space in the vertical or horizontal dimensions, thereby ensuring that different pixel positions correspond to different index key values.

[0133] The generated index key is used as a unique identifier, and the cumulative path distance corresponding to the current pixel coordinate is stored as the corresponding value, forming a one-to-one mapping relationship between the index key and the cumulative path distance. By traversing the set of pixel coordinates of each lane area within the region of interest, the above mapping relationship is generated and stored one by one, thereby constructing a distance mapping configuration table covering the entire bird's-eye view. The distance mapping configuration table can be implemented using a hash table, array, or key-value database structure, with its index key as a direct addressing subscript and the corresponding cumulative path distance as the stored data, thus achieving distance lookup with constant time complexity.

[0134] Through steps S301-S304, a digital mapping system from pixel spatial location to cumulative driving distance along the lane path is established within the region of interest, significantly improving ranging performance and real-time response efficiency in large-scale traffic scenarios. Simultaneously, based on physical coordinate restoration and a nearest neighbor matching mechanism using a high-density interpolation point sequence, it ensures that each pixel within the region of interest can obtain a driving distance attribute that precisely corresponds to its spatial location and strictly extends along the lane path. This effectively eliminates the ranging bias caused by neglecting road curvature in traditional algorithms on curved or irregularly shaped intersections. Through these processes, the path search, geometric projection, and distance integration calculation processes, which originally needed to be executed in real-time during online operation, are moved to the offline calibration stage. This allows the system to quickly obtain the actual driving distance from the target location to the stop line simply by querying the index during operation, and in the online stage, it only needs to query the index to quickly obtain the actual driving distance from the target location to the stop line. The computational complexity is reduced from high-order geometric operations to constant-time table lookup indexes, greatly reducing the processor load.

[0135] Step S4: Obtain the target's location information and generate a corresponding index key value based on the location information. Query the corresponding cumulative path distance in the distance mapping configuration table using the index key value to determine the distance between the target and the corresponding stop line.

[0136] In this embodiment, step S4 is used to quickly obtain the distance from the target position to the stop line during the online operation phase of the system, and its specific implementation process is as follows.

[0137] First, the target's current location information is acquired through onboard sensors, a positioning module, or a perception algorithm. This location information may include the target's two-dimensional or three-dimensional physical coordinates in a spatial coordinate system, representing the target's actual spatial location within the region of interest.

[0138] Subsequently, based on the coordinate mapping relationship established in steps S301 to S303, the obtained target physical location coordinates are subjected to coordinate projection transformation processing consistent with the offline calibration stage, mapping the target's physical location to the bird's-eye view coordinate system to obtain the target's corresponding pixel coordinates. This mapping process preferably uses the same boundary parameters and pixel resolution parameters as when constructing the pixel coordinate set to ensure coordinate consistency between the online query stage and the offline construction stage.

[0139] After obtaining the pixel coordinates corresponding to the target, an indexing function is used to process the pixel coordinates, generating a unique index key value that corresponds one-to-one with each pixel coordinate. For example, based on the length range of the region of interest in the horizontal and vertical directions, an appropriate index calculation method can be selected to combine the pixel's horizontal and vertical coordinates into a single integer index key value, thereby ensuring that each pixel position corresponds to a unique key value identifier.

[0140] Next, using the generated index key value as the query keyword, a lookup operation is performed in the pre-built distance mapping configuration table to directly obtain the cumulative path distance stored corresponding to the index key value, thereby determining the actual travel distance from the target's current location to the stop line along the corresponding lane path.

[0141] By constructing a distance mapping configuration table, a one-to-one correspondence between spatial location and driving distance is pre-established in the pixel space of the bird's-eye view. This eliminates the need for complex calculations such as path search, nearest path point matching, or distance accumulation during online operation. Once the pixel coordinates corresponding to the target are obtained, only an index key value needs to be generated using an index function and a single table lookup operation is required to directly obtain the cumulative path distance from the target location to the stop line. This significantly improves distance query efficiency and reduces real-time computational load. Because the distance mapping configuration table uses a direct addressing storage method based on unique index key values, the cumulative path distance corresponding to the target location can be obtained in a single query operation. The query time does not increase with the increase of lane length, path point density, or number of lanes, making it suitable for the high-frequency real-time access requirements of distance information in vehicle-road cooperative scenarios.

[0142] In summary, the lane-path-based stop-line distance determination method provided in this application constructs a path reference curve by performing continuous processing on the lane paths within the region of interest. This transforms the originally discrete map information into a mathematical model capable of accurately simulating vehicle trajectories. Based on this model, the cumulative distance along the path is calculated. This fundamentally solves the ranging deviation caused by traditional Euclidean distance in curved or complex intersection scenarios, ensuring the authenticity and accuracy of distance feedback. Furthermore, by pre-constructing a distance mapping configuration table that stores the cumulative distance mapping relationship between path points and corresponding stop lines, the complex spatial geometric calculation and curve integration process is transferred to the offline preprocessing stage. This allows for result retrieval in online real-time applications using only simple index keys, significantly reducing online computational complexity while maintaining distance calculation accuracy. This achieves high real-time response efficiency while ensuring high-precision ranging, thus providing more reliable and efficient distance parameter support for auxiliary decision-making such as traffic signal timing optimization in vehicle-road cooperative scenarios.

[0143] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this application.

[0144] Furthermore, some embodiments of this application also provide an electronic device. The electronic device can be various forms of digital computer, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, etc. The electronic device can also be various forms of mobile devices, such as cellular phones, smartphones, wearable devices, and other similar computing devices.

[0145] The electronic device includes: one or more processors; and a memory storing computer program instructions, which, when executed, cause the processor to perform a lane path-based stop line distance determination method as provided in any one or more of the above embodiments. Figure 5 An exemplary structural diagram of the electronic device is disclosed. The electronic device includes one or more processors 1101, a memory 1102, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations. The components, their connections and relationships, and their functions shown herein are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0146] The electronic device may further include an input device 1103 and an output device 1104. The processor 1101, memory 1102, input device 1103, and output device 1104 may be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0147] Input device 1103 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 1104 may include a display device, auxiliary lighting device (e.g., LED), and haptic feedback device (e.g., vibration motor). The display device may include, but is not limited to, a liquid crystal display, a light-emitting diode display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0148] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device (e.g., a cathode ray tube or LCD monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback); and input from the user can be received in any form (e.g., voice input or tactile input).

[0149] In this embodiment, a computer-readable medium stores a computer program / instructions that, when executed by a processor, implement a lane path-based stop line distance determination method provided in any one or more of the above embodiments. This computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into that device. The aforementioned computer-readable medium carries one or more computer-readable instructions.

[0150] The memory 1102 can serve as a non-transitory computer-readable storage medium, used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 1102, thereby implementing the program instructions / modules corresponding to the methods provided in any one or more of the embodiments described above in this application.

[0151] The memory 1102 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 1102 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1102 may optionally include memory remotely located relative to the processor 1101, and these remote memories can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0152] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0153] Computer-readable media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory, static random access memory, dynamic random access memory, other types of random access memory, read-only memory, electrically erasable programmable read-only memory, flash memory or other memory technologies, read-only optical discs, digital versatile optical discs or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0154] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0155] In the above embodiments, all or part of the implementation can be achieved through software, hardware, firmware, or any combination thereof. For example, it can be implemented using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the above steps or functions. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. In addition, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0156] The computer program product provided in this application includes one or more computer programs / instructions. When executed by a processor, these computer programs / instructions generate, in whole or in part, the processes or functions described in this application. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0157] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0158] The scope of this application is defined by the appended claims rather than the foregoing description, and is therefore intended to encompass all variations falling within the meaning and scope of equivalents of the claims. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Terms such as "first," "second," etc., are used only to distinguish descriptions and do not indicate any particular order, nor should they be construed as indicating or implying relative importance.

[0159] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily made by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A method for determining stop line distance based on lane path, characterized in that, include: Determine the region of interest, which includes multiple lane regions, and each lane region corresponds to a lane path; For each lane path, a continuous processing is performed to generate a path reference curve constructed from multiple consecutively arranged path points. The cumulative path distance from each path reference curve to the corresponding stop line is calculated, starting from the intersection of each path reference curve and the corresponding stop line. Construct a distance mapping configuration table that maps the path points to the cumulative distances of the corresponding paths; Obtain the target's location information and generate a corresponding index key value based on the location information. Use the index key value to query the corresponding cumulative path distance in the distance mapping configuration table to determine the distance between the target and the corresponding stop line.

2. The method for determining stop line distance based on lane path according to claim 1, characterized in that, The step of performing continuous processing on each lane path to generate a path reference curve constructed from a plurality of continuously arranged path points includes: Obtain multiple original centerline nodes on the lane centerline corresponding to the lane path; The original centerline nodes are interpolated based on the spacing between adjacent original centerline nodes, and multiple interpolation nodes are generated between the adjacent original centerline nodes. The interpolation nodes and the original centerline nodes are arranged in order of lane travel direction to form a continuous sequence of path points, thereby constructing the path reference curve.

3. The method for determining stop line distance based on lane path according to claim 2, characterized in that, The step of interpolating the original centerline nodes based on the spacing between adjacent original centerline nodes to generate multiple interpolated nodes between the adjacent original centerline nodes includes: The interpolation point resolution is determined based on the curvature characteristics of the lane centerline. Calculate the physical distance between adjacent original centerline nodes on the lane centerline; Based on the interpolation point resolution and the physical distance, determine the number of interpolation nodes to be generated between the adjacent original centerline nodes; The interpolation step size is determined based on the number of interpolation nodes and the projection difference of adjacent original centerline nodes in the coordinate axis direction. Based on the interpolation step size, the interpolation nodes are generated between the adjacent original centerline nodes.

4. The method for determining stop line distance based on lane path according to claim 1, characterized in that, The step of calculating the cumulative path distance from each path point on the path reference curve to the corresponding stop line, starting from the intersection of each path reference curve and the corresponding stop line, includes: Arrange the path points on the path reference curve in the direction away from the stop line to obtain an ordered sequence of path points with the starting point as the first node; Calculate the distance between two adjacent path points in the ordered path point sequence; Based on the distance between two adjacent path points, the distances of each path point in the ordered path point sequence are accumulated sequentially to obtain the path length of each path point relative to the starting point, which is used as the cumulative path distance.

5. The method for determining stop line distance based on lane path according to claim 1, characterized in that, The step of constructing a distance mapping configuration table that maps the path points to the corresponding cumulative path distances includes: Determine the set of pixel coordinates covered by each lane region within the region of interest; Each pixel coordinate in the pixel coordinate set is converted into a physical location coordinate in the same coordinate system as the path reference curve; Based on the physical location coordinates, the nearest path point corresponding to it is matched on the corresponding path reference curve, and the cumulative path distance corresponding to the matched nearest path point is associated with the pixel coordinates; A preset index function is used to generate a unique index key value for the pixel coordinates, and the index key value and the corresponding cumulative path distance are stored to construct the distance mapping configuration table.

6. The method for determining stop line distance based on lane path according to claim 5, characterized in that, The step of determining the set of pixel coordinates covered by each lane region within the region of interest includes: Extract the physical boundary information of each lane area in the spatial coordinate system from the map data; Obtain the boundary parameters of the region of interest in the spatial coordinate system and the pixel resolution parameters used to characterize the number of pixels per unit spatial distance; Based on the minimum lateral boundary value of the boundary parameters, the lateral offset of the lane physical boundary information relative to the starting boundary of the region of interest is calculated, and the lateral offset is proportionally mapped and rounded according to the pixel resolution parameters to obtain the pixel lateral boundary range of the lane area in the bird's-eye view coordinate system. Based on the minimum longitudinal boundary value of the boundary parameters, the longitudinal offset of the lane physical boundary information relative to the starting boundary of the region of interest is calculated. The longitudinal offset is then proportionally mapped and rounded according to the pixel resolution parameters. Simultaneously, a mirror offset is performed in conjunction with the height parameters of the bird's-eye view corresponding to the region of interest to obtain the pixel longitudinal boundary range of the lane area in the bird's-eye view coordinate system. For each lane region, a pixel region defined by the horizontal boundary range and the vertical boundary range of the pixel is determined, and the pixel coordinates within the pixel region are extracted by traversing the region to form a set of pixel coordinates covered by each lane region.

7. The method for determining stop line distance based on lane path according to claim 6, characterized in that, The step of generating a unique index key value for the pixel coordinates using a preset index function, and storing the index key value and the corresponding cumulative path distance to construct the distance mapping configuration table includes: The horizontal length range is determined based on the horizontal minimum boundary value and the horizontal maximum boundary value of the boundary parameters, and the vertical length range is determined based on the vertical minimum boundary value and the vertical maximum boundary value of the boundary parameters. Compare the length range values ​​in the vertical direction with the length range values ​​in the horizontal direction. When the length range value in the vertical direction is greater than the length range value in the horizontal direction, the horizontal coordinate of the pixel in the pixel coordinates is multiplied by the height of the bird's-eye view corresponding to the region of interest, and the product result is added to the vertical coordinate of the pixel in the pixel coordinates to generate the index key value; When the length range value in the vertical direction is less than or equal to the length range value in the horizontal direction, the vertical coordinate of the pixel in the pixel coordinates is multiplied by the width of the bird's-eye view corresponding to the region of interest, and the product result is added to the horizontal coordinate of the pixel in the pixel coordinates to generate the index key value; The generated index key value is used as the key, and the corresponding cumulative path distance is used as the value to construct a key-value pair and store it in the distance mapping configuration table.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; and a memory storing computer program instructions that, when executed, cause the processors to perform the lane path-based stop line distance determination method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program and / or instructions stored thereon, characterized in that, When the computer program and / or instructions are executed by the processor, they implement the lane path-based stop line distance determination method as described in any one of claims 1-7.

10. A computer program product comprising a computer program and / or instructions, characterized in that, When the computer program and / or instructions are executed by the processor, they implement the lane path-based stop line distance determination method as described in any one of claims 1-7.

Images