A method for quickly extracting strip-shaped local map elements from high-precision maps

Abstract

The present invention relates to a method, system, electronic device and computer-readable storage medium for quickly extracting strip-shaped local map elements from a high-precision map, the method comprising the following steps: according to a preset center line and a preset extraction range, obtaining a preliminary screening rectangular frame containing a preset center line and a margin of a preset extraction range; traversing map elements, retaining map elements whose point coordinates are within the preliminary screening rectangular frame; performing thinning preprocessing on the preset center line; projecting all map elements within the preliminary screening rectangular frame onto the preprocessed center line in turn, and calculating the minimum projection distance value of each map element, retaining map elements whose minimum projection distance value is within the preset extraction range. The present invention takes into account both map extraction effect and computing power consumption, and can effectively ensure that the extraction result is a strip-shaped local map with a preset center line as the axis, and the distances from the map elements at its edges to the center line are evenly distributed, meeting the use requirements of autonomous driving.

Description

Technical Field

[0001] The present invention relates to the field of high-precision maps and autonomous driving, and in particular to a method for quickly extracting strip-shaped local map elements from a high-precision map. Background Art

[0002] High-precision maps are an important part of the autonomous driving system. They can provide road prior information for autonomous driving perception, planning, decision-making, positioning and other modules, and make up for the shortcomings of vehicle-mounted sensors in harsh environments. Autonomous driving systems usually need to extract high-precision map elements within a certain range near the route according to the preset route for use in various modules. The traditional method of extracting local map elements is mainly to use regular shaped areas for filtering, such as rectangles or circles, and directly filter by judging whether the coordinates of the map elements are in the area. For example, an existing approach is to first divide the map to be processed into equal parts, and then judge whether the map points meet the preset conditions through the sub-areas, and then extract them. For example, another existing approach is to solve the problem of redundancy caused by repeated extraction of high-precision map data, and the vector elements in the map are formed into a preset geometric space according to their coordinates, and then judge whether the pre-added new elements are in the geometric space, thereby avoiding the problem of repeated addition. The above method is mainly applicable to the case where the center line of the area to be extracted is itself a relatively regular shape, so that the distance from the edge of the constructed rectangular area to the extracted object is uniform. However, if the center line of the extracted area itself has a large curvature, such as in scenes with continuous curves or sharp bends, the center line to be extracted is a circular arc with curvature. If a regular rectangular area is still used for extraction, then the distance from the map elements at the edge of the area to the specified center line must be uneven.

[0003] If the above-mentioned regular area screening method is not adopted, without considering the amount of calculation, for example, directly screening by calculating the distance from all map feature points to the center line can also obtain relatively ideal extraction results. However, when there are many map feature points in the area and there are also many discrete points that constitute the center line, this method will cause a lot of computing power consumption and cannot be applied to real-time autonomous driving systems. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a method for quickly extracting strip-shaped local map elements from a high-precision map, thereby solving the problems of uneven distance from the edge of the extraction area to the specified center line and large computing power consumption in the prior art.

[0005] According to a first aspect of the present invention, there is provided a method for quickly extracting strip-shaped local map elements from a high-precision map, comprising the following steps:

[0006] S1, according to the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the remainder being the preset extraction range is obtained;

[0007] S2, traverse the map elements and retain the map elements whose point coordinates are within the initial screening rectangular box;

[0008] S3, performing thinning preprocessing on the preset center line;

[0009] S4, projecting all map elements within the initial screening rectangular frame onto the preprocessed center line in sequence, calculating the minimum projection distance value of each map element, and retaining the map elements whose minimum projection distance value is within the preset extraction range.

[0010] Optionally, step S1 includes:

[0011] Traverse the horizontal and vertical coordinates of the discrete points on the preset center line, calculate the maximum horizontal coordinate xmax, the minimum horizontal coordinate xmin, the maximum vertical coordinate ymax, and the minimum vertical coordinate ymin of the preset center line, and set the preset extraction range to set_range. According to the following formula, the four corner point coordinate extreme values ​​are calculated, and the four corner point coordinate extreme values ​​form a preliminary screening rectangular frame:

[0012] x_min_rect=xmin-set_range,

[0013] x_max_rect=xmax+set_range,

[0014] y_min_rect=ymin-set_range,

[0015] y_max_rect=ymax+set_range.

[0016] Optionally, in step S2, traversing the map elements and retaining the map elements whose point coordinates are within the initial screening rectangular frame includes:

[0017] S201, obtaining the point coordinates (x, y) of a single map element in the high-precision map. If the point coordinates (x, y) are determined to satisfy both x_min_rect≤x≤x_max_rect and y_min_rect≤y≤y_max_rect, it means that the point is within the initial screening rectangular frame, and the map element corresponding to the point coordinates (x, y) is retained;

[0018] S202, traverse all map elements in the high-precision map.

[0019] Optionally, in step S3, the thinning preprocessing of the preset center line includes:

[0020] The preset center line is thinned and compressed using a thinning algorithm to obtain multiple key nodes of the preset center line, and the key nodes are retained.

[0021] Optionally, step S3 includes:

[0022] S301, connecting the first and last points of the trajectory points of the preset center line with a straight line to obtain a first trajectory segment, calculating the distances from all remaining points to the first trajectory segment, and finding the maximum distance among them; if it is determined that the maximum distance exceeds a specified error range, selecting the point as a reserved point, and dividing the first trajectory segment into two with the point as the boundary;

[0023] S302, repeating step S301 for the two newly generated trajectories until the maximum distance is within a specified error range;

[0024] S303, taking the n reserved points obtained in step S301 and step S302 as key nodes of the preset center line, wherein n is a natural number greater than 1; retaining n of the key nodes, connecting lines of adjacent key nodes to form a second trajectory segment, and forming a new center line by connecting n-1 second trajectory segments.

[0025] Optionally, step S4 includes:

[0026] S401, vertically projecting a single map element in the primary screening rectangular frame onto n-1 second trajectory segments in turn to obtain a projection distance dist_project of the map element onto the n-1 second trajectory segments, calculating a minimum value from the n-1 projection distances dist_project, the minimum value being the minimum projection distance min_dist_project from the map element to the new center line; if the minimum projection distance min_dist_project is determined to be within a preset extraction range, extracting the map element;

[0027] S402, traverse all map elements in the initial screening rectangular frame, and extract all map elements in the initial screening rectangular frame whose minimum projection distance min_dist_project to the new center line is within a preset extraction range.

[0028] Optionally, in step S401, the vertical projection of the single map element in the primary screening rectangular frame to n-1 second trajectory segments in sequence to obtain the projection distance dist_project of the map element to the n-1 second trajectory segments includes:

[0029] Project each map element in the initial screening rectangle vertically onto n-1 second trajectory segments in turn. If the projection point falls on the second trajectory segment, the projection distance dist_project is the distance from the map element to the projection point. If the projection point falls on the extension line of the second trajectory segment, the projection distance dist_project is the minimum value of the distances from the map element to the two endpoints of the second trajectory segment.

[0030] The map element is used to traverse n-1 second trajectory segments in sequence to obtain projection distances dist_project of the map element for the n-1 second trajectory segments respectively.

[0031] According to a second aspect of the present invention, there is provided a system for quickly extracting strip-shaped local map elements from a high-precision map, comprising:

[0032] A preset module, used to obtain a preliminary screening rectangular frame including a preset center line and a preset extraction range according to a preset center line and a preset extraction range;

[0033] A preliminary screening module is used to traverse map elements and retain map elements whose point coordinates are within the preliminary screening rectangular box;

[0034] A preprocessing module, used for performing thinning preprocessing on the preset center line;

[0035] The precise screening module is used to project all map elements within the initial screening rectangular box onto the preprocessed center line in sequence, calculate the minimum projection distance value of each map element, and retain the map elements whose minimum projection distance value is within the preset extraction range.

[0036] According to a third aspect of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the processor is used to implement the steps of the above-mentioned method for rapidly extracting strip-shaped local map elements from a high-precision map when executing a computer management program stored in the memory.

[0037] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the above-mentioned method for quickly extracting strip-shaped local map elements from a high-precision map are implemented.

[0038] The present invention proposes a method, system, electronic device and storage medium for quickly extracting strip-shaped local map elements from a high-precision map. First, a preliminary screening rectangular frame is constructed by the coordinate extreme values ​​of a preset route / track (also referred to as a preset center line) for initial map element screening; then a thinning algorithm is used to perform track thinning and compression on the preset center line, and only key nodes are retained to further reduce the calculation amount of subsequent precise screening; finally, the map element points after the preliminary screening are projected onto the thinned center line one by one, and the final screening result is obtained by judging whether the minimum projection distance is within the preset extraction range.

[0039] The method proposed in the patent of this invention can take into account both the map extraction effect and computing power consumption. It filters the map elements through the rectangular frame and filters the non-key points of the center line through the thinning algorithm. These two steps effectively reduce the calculation amount of the final precise screening. At the same time, the calculation method of the projection distance from the map point to the trajectory line is used in the precise screening, which can effectively ensure that the extraction result is a strip-shaped local map with the preset center line as the axis, and the distance from the map elements on the edge to the center line is evenly distributed. This method can be used for real-time map extraction, display and use in autonomous driving, accurately filter out unnecessary map information, and meet the use requirements of autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flow chart of a method for quickly extracting strip-shaped local map elements from a high-precision map provided by the present invention;

[0041] Figure 2 A schematic diagram of a typical method for constructing a rectangular frame for initial screening of map points according to the present invention;

[0042] Figure 3 This is a schematic diagram of a typical map point initial screening method of the present invention;

[0043] Figure 4 This is a typical schematic diagram of using the Douglas-Peucker algorithm to thin out the trajectory line in the present invention;

[0044] Figure 5 A schematic diagram of a typical method for calculating the minimum distance from a map point to a trajectory segment of the present invention;

[0045] Figure 6 This is a typical extraction effect diagram of the present invention;

[0046] Figure 7 A system structure diagram for quickly extracting strip-shaped local map elements from a high-precision map provided by the present invention;

[0047] Figure 8 A schematic diagram of the structure of an electronic device provided by the present invention;

[0048] Fig. 9 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0049] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0050] Figure 1 A flowchart of a method for quickly extracting strip-shaped local map elements from a high-precision map provided by the present invention is as follows: Figure 1 As shown, the method includes:

[0051] S1, according to the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the remainder being the preset extraction range is obtained;

[0052] S2, traverse the map elements and retain the map elements whose point coordinates are within the initial screening rectangular box;

[0053] S3, performing thinning preprocessing on the preset center line;

[0054] S4, projecting all map elements within the initial screening rectangular frame onto the preprocessed center line in sequence, calculating the minimum projection distance value of each map element, and retaining the map elements whose minimum projection distance value is within the preset extraction range.

[0055] It can be understood that, based on the defects in the background technology, the embodiment of the present invention proposes a method for quickly extracting strip-shaped local map elements from a high-precision map. In this method, a preliminary screening rectangular frame is first constructed by the coordinate extreme values ​​of the preset route / track (also referred to as the preset center line) and the preset extraction range for initial map element screening; then the preset center line is subjected to track thinning and compression using a thinning algorithm, and only key nodes are retained to further reduce the amount of calculation for subsequent precise screening, saving the computing power consumption for subsequent precise screening; finally, the map element points after the preliminary screening are projected one by one on the thinned center line, and the final screening result is obtained by judging whether the minimum projection distance is within the preset extraction range. This method can take into account both the map extraction effect and the computing power consumption at the same time, and filter the map elements through the rectangular frame preliminary screening, and filter the non-key points of the center line through the thinning algorithm. These two steps effectively reduce the amount of calculation for the final precise screening. At the same time, the calculation method of the projection distance from the map point to the track line is used in the precise screening, which can effectively ensure that the extraction result is a strip-shaped local map with the preset center line as the axis, and the distance from the map elements at its edge to the center line is evenly distributed. This method can be used for real-time map extraction, display and use in autonomous driving, accurately filtering out unnecessary map information, and meeting the needs of autonomous driving.

[0056] In a possible embodiment, in step S1, Figure 2The figure is a typical schematic diagram of a method for constructing a rectangular frame for initial screening of map points. 201 is a discrete point used to describe the center line. The horizontal coordinates and vertical coordinates of the discrete points of the preset center line are traversed to obtain the maximum horizontal coordinate value xmax, the minimum horizontal coordinate value xmin, the maximum vertical coordinate value ymax, and the minimum vertical coordinate value ymin. The center line rectangular envelope frame formed by these coordinates is shown in 202.

[0057] Assume that the preset extraction range is set_range, which is determined by the actual needs of the user, and the typical value is 100-200m. In order to ensure that the initial screening results do not miss the map elements near the endpoints of the trajectory line, the centerline rectangular envelope 202 is further expanded by the distance of set_range, that is, the horizontal spacing 204 and the vertical spacing 205 in the figure are both equal to set_range, and the initial screening rectangular frame 203 is obtained, and the extreme values ​​of the coordinates of its four corner points are:

[0058] x_min_rect=xmin-set_range, x_max_rec=xmax+set_range,

[0059] y_min_rect=ymin-set_range, y_max_rect=ymax+set_range.

[0060] It can be understood that in step S1, based on the coordinate extreme value of the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the margin of the preset extraction range is obtained, preparing for the subsequent preliminary screening of map elements.

[0061] In a possible implementation manner, in step S2, traversing the map elements and retaining the map elements whose point coordinates are within the initial screening rectangular frame includes:

[0062] S201, obtaining the point coordinates (x, y) of a single map element in the high-precision map. If the point coordinates (x, y) are determined to satisfy both x_min_rect≤x≤x_max_rect and y_min_rect≤y≤y_max_rect, it means that the point is within the initial screening rectangular frame, and the map element corresponding to the point coordinates (x, y) is retained;

[0063] S202, traverse all map elements in the high-precision map and repeat step S201 for initial screening.

[0064] It can be understood that all high-precision map elements are traversed, and preliminary screening is completed by judging whether their point coordinates are within the initial screening rectangular frame, and only the map elements within the rectangular frame are retained for subsequent screening. The purpose of this step is to reduce the number of map elements that are subsequently accurately screened.

[0065] Figure 3 It is a typical schematic diagram of a map point initial screening method, wherein 301 is a preliminary screening rectangular frame, the first map point 302, the second map point 303, and the third map point 304 fall on the corner point, the edge line, and the frame of the preliminary screening rectangular frame 301 respectively, and are all valid points and are thus retained, while the fourth map point 305 is eliminated because its ordinate is higher than the rectangular frame y_max_rect.

[0066] Optionally, in step S3, the thinning preprocessing of the preset center line includes:

[0067] The preset center line is thinned and compressed using a thinning algorithm to obtain multiple key nodes of the preset center line, and the key nodes are retained.

[0068] It is understandable that the purpose of this step is to reduce the number of trajectory points of the center line during subsequent precise screening to save computing power consumption.

[0069] In order to ensure that the thinned trajectory does not produce obvious deformation compared with the original trajectory, that is, the projection error of the thinned trajectory to the original trajectory is within the specified threshold dilute_threshold, the classic Douglas-Peucker thinning algorithm is usually chosen. The larger the thinning error threshold, the fewer points will be retained after thinning, and the subsequent screening calculation amount will be smaller, but the corresponding thinning trajectory will be more deformed. Therefore, it is usually set according to actual needs and experience, and its typical value range is 1 to 10m.

[0070] In a possible implementation manner, step S3 includes:

[0071] S301, connecting the first and last points of the trajectory points of the preset center line with a straight line to obtain a first trajectory segment, calculating the distances from all remaining points to the first trajectory segment, and finding the maximum distance among them; if it is determined that the maximum distance exceeds a specified error range, selecting the point as a reserved point, and dividing the first trajectory segment into two with the point as the boundary;

[0072] S302, repeating step S301 for the two newly generated trajectories until the maximum distance is within a specified error range;

[0073] S303, taking the n reserved points obtained in step S301 and step S302 as key nodes of the preset center line, wherein n is a natural number greater than 1; retaining n of the key nodes, connecting lines of adjacent key nodes to form a second trajectory segment, and forming a new center line by connecting n-1 second trajectory segments.

[0074] More specifically, Figure 4 This is a typical schematic diagram of using the Douglas-Peucker algorithm to thin out the trajectory. Figure 4In the upper part, 401 and 402 are the first and last points of the original center line (i.e., the preset center line), and 403 is the connecting line of the first and last points (i.e., corresponding to the first trajectory segment mentioned above). All remaining points except the first and last points are vertically projected on the connecting line 403 to obtain the projection distance of each point, as shown in 404. The point corresponding to the maximum projection distance is found, as shown in 405. If the maximum projection distance is higher than the preset thinning error threshold, point 405 is recorded as a reserved point, and the original trajectory is divided into two with the maximum projection distance point 405 as the dividing point, that is, the first split trajectory line 406 is composed of the original center line first point 401, the maximum projection distance point 405 and the middle point between the two, and the second split trajectory line 407 is composed of the original center line last point 402, the maximum projection distance point 405 and the middle point between the two. A new trajectory line head and tail endpoint connecting line is constructed again, and the above process of "calculating the projection distance of the remaining points - judging whether the maximum projection distance is higher than the thinning error threshold - recording the maximum distance projection point as the reserved point - continuing to split with this point as the dividing point" is repeated again until the maximum projection distance of the split trajectory is less than the thinning error threshold, then the thinning process ends, and all recorded points plus the head and tail endpoints of the original trajectory are the thinning reserved points 408. Figure 4 The adjacent reserved points 408 are connected to obtain n-1 second trajectory line segments, and all the reserved points 408 are connected in sequence to obtain a new center line composed of the second trajectory line segments after thinning and compression.

[0075] In a possible implementation manner, step S4 includes:

[0076] S401, vertically projecting a single map element in the primary screening rectangular frame onto n-1 second trajectory segments in turn to obtain a projection distance dist_project of the map element onto the n-1 second trajectory segments, calculating a minimum value from the n-1 projection distances dist_project, the minimum value being the minimum projection distance min_dist_project from the map element to the new center line; if the minimum projection distance min_dist_project is determined to be within a preset extraction range, extracting the map element;

[0077] S402, traverse all map elements in the initial screening rectangular frame, and extract all map elements in the initial screening rectangular frame whose minimum projection distance min_dist_project to the new center line is within a preset extraction range.

[0078] Optionally, in step S401, the vertical projection of the single map element in the primary screening rectangular frame to n-1 second trajectory segments in sequence to obtain the projection distance dist_project of the map element to the n-1 second trajectory segments includes:

[0079] Project each map element in the initial screening rectangle vertically onto n-1 second trajectory segments in turn. If the projection point falls on the second trajectory segment, the projection distance dist_project is the distance from the map element to the projection point. If the projection point falls on the extension line of the second trajectory segment, the projection distance dist_project is the minimum value of the distances from the map element to the two endpoints of the second trajectory segment.

[0080] The map element is used to traverse n-1 second trajectory segments in sequence to obtain projection distances dist_project of the map element for the n-1 second trajectory segments respectively.

[0081] It can be understood that in step S4, the map elements after the initial screening are projected onto the new center line after thinning and compression to obtain the map elements to be extracted. The calculation method of the projection distance used for screening in this step can ensure that the distance from all map element points to the center line after screening is within the specified range, that is, the strip area is extracted.

[0082] For a more detailed description, please refer to Figure 5 .like Figure 5 The figure shows a typical schematic diagram of a method for calculating the minimum distance from a map point to a trajectory segment. Figure 5 As shown in the upper part of , 501 is the reserved point of the center line after thinning and compression, the point numbers are 1 to n, and there are n-1 segments of line segments composed of adjacent points (i.e., the above-mentioned second trajectory segments). The map feature point 502 after the initial screening is vertically projected on the n-1 second trajectory segments in turn, and the projection distance between the map feature point 502 and each second trajectory segment is calculated. In the figure, the line segment 503 composed of point _i-1 and point _i, and the line segment 511 composed of point _i and point _i+1 correspond to two typical projection situations, namely, the projection point falls on the line segment and outside the line segment.

[0083] like Figure 5 As shown in the lower part of , the projection point 504 of the map feature point 502 on the line segment 503 falls on the line segment 503, so its projection distance is the distance 505 from the map feature point 502 to the projection point 504. The projection point 512 of the map point 502 on the line segment 511 falls on the extension line of the line segment 511, so the projection distance of the point 502 on the line segment 511 should be the minimum value of the distance between the same point _i and the point _i+1, which is the projection distance 513 in the figure.

[0084] The projection distances of the map feature point 502 to the n-1 second trajectory segments are calculated in the above manner, and the minimum value is obtained, which represents the shortest distance from the map feature point to the new center line. If the distance is less than the preset extraction range set_range, the map point is retained. In addition, since the original trajectory (i.e., the preset center line) is also thinned in step 2, due to the existence of thinning error, the actual extraction range here should be added with the thinning error threshold, i.e., set_range+dilute_threshold.

[0085] Then we need to complete the extraction of strip-shaped local map features. Figure 6 The figure shows a typical extraction effect diagram, where 601 is the original centerline trajectory point, 602 is the retained point after thinning in step 2, and since step 3 is to accurately screen according to the projection distance from the map point to the centerline thinning point, the local map boundary 603 obtained after screening is actually a parallel line of the new centerline after thinning, and the maximum value 604 of the new centerline is the preset extraction range, thus forming Figure 6 The strip map area shown in .

[0086] Figure 7 A system structure diagram for quickly extracting strip-shaped local map elements from a high-precision map provided by an embodiment of the present invention, such as Figure 7 As shown, a system for quickly extracting strip-shaped local map elements from a high-precision map includes a preset module 701, a primary screening module 702, a preprocessing module 703 and a precise screening module 704, wherein:

[0087] A preset module 701 is used to obtain a preliminary screening rectangular frame including a preset center line and a residual of a preset extraction range according to a preset center line and a preset extraction range;

[0088] A preliminary screening module 702, for traversing map elements and retaining map elements whose point coordinates are within the preliminary screening rectangular frame;

[0089] A preprocessing module 703 is used to perform thinning preprocessing on the preset center line;

[0090] The precise screening module 704 is used to project all map elements in the initial screening rectangular frame onto the preprocessed center line in sequence, calculate the minimum projection distance value of each map element, and retain the map elements whose minimum projection distance value is within the preset extraction range.

[0091] It can be understood that the system for quickly extracting strip-shaped local map elements from a high-precision map provided by the present invention corresponds to the method for quickly extracting strip-shaped local map elements from a high-precision map provided by the aforementioned embodiments. The relevant technical features of the system can refer to the relevant technical features of the method for quickly extracting strip-shaped local map elements from a high-precision map, which will not be repeated here.

[0092] See also Figure 8 , Figure 8 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 8 As shown, an embodiment of the present invention provides an electronic device 8, including a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and executable on the processor 802. When the processor 802 executes the computer program 803, the following steps are implemented:

[0093] According to the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the remainder being the preset extraction range is obtained;

[0094] Traverse the map elements and retain the map elements whose point coordinates are within the initial screening rectangular box;

[0095] Perform thinning preprocessing on the preset center line;

[0096] All map elements within the initial screening rectangular frame are projected onto the preprocessed center line in turn, and the minimum projection distance value of each map element is calculated, and the map elements whose minimum projection distance value is within the preset extraction range are retained.

[0097] See also Fig. 9 , Fig. 9 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Fig. 9 As shown, this embodiment provides a computer-readable storage medium 9, on which a computer program 901 is stored. When the computer program 901 is executed by a processor, the following steps are implemented:

[0098] According to the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the remainder being the preset extraction range is obtained;

[0099] Traverse the map elements and retain the map elements whose point coordinates are within the initial screening rectangular box;

[0100] Perform thinning preprocessing on the preset center line;

[0101] All map elements within the initial screening rectangular frame are projected onto the preprocessed center line in turn, and the minimum projection distance value of each map element is calculated, and the map elements whose minimum projection distance value is within the preset extraction range are retained.

[0102] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0107] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0108] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for quickly extracting strip-shaped local map elements from a high-precision map, characterized in that: The following steps are involved: S1, according to the preset center line and the preset extraction range, a preliminary screening rectangular frame including the preset center line and the remainder being the preset extraction range is obtained; S2, traverse the map elements and retain the map elements whose point coordinates are within the initial screening rectangular box; S3, performing thinning preprocessing on the preset center line; S4, projecting all map elements within the initial screening rectangular frame onto the preprocessed center line in sequence, calculating the minimum projection distance value of each map element, and retaining the map elements whose minimum projection distance value is within the preset extraction range.

2. According to claim 1, a method for quickly extracting strip-shaped local map elements from a high-precision map is characterized in that: Step S1 includes: Traverse the horizontal and vertical coordinates of the discrete points on the preset center line, calculate the maximum horizontal coordinate xmax, the minimum horizontal coordinate xmin, the maximum vertical coordinate ymax, and the minimum vertical coordinate ymin of the preset center line, and set the preset extraction range to set_range. According to the following formula, the four corner point coordinate extreme values ​​are calculated, and the four corner point coordinate extreme values ​​form a preliminary screening rectangular frame: x_min_rect=xmin-set_range, x_max_rect=xmax+set_range, y_min_rect=ymin-set_range, y_max_rect=ymax+set_range.

3. A method for quickly extracting strip-shaped local map elements from a high-precision map according to claim 1 or 2, characterized in that: In step S2, the traversal of map elements and the retention of map elements whose point coordinates are within the initial screening rectangular frame include: S201, obtaining the point coordinates (x, y) of a single map element in the high-precision map. If the point coordinates (x, y) are determined to satisfy both x_min_rect≤x≤x_max_rect and y_min_rect≤y≤y_max_rect, it means that the point is within the initial screening rectangular frame, and the map element corresponding to the point coordinates (x, y) is retained; S202, traverse all map elements in the high-precision map and repeat step S201 for initial screening.

4. According to claim 3, a method for quickly extracting strip-shaped local map elements from a high-precision map is characterized in that: In step S3, the thinning preprocessing of the preset center line includes: The preset center line is thinned and compressed using a thinning algorithm to obtain multiple key nodes of the preset center line, and the key nodes are retained.

5. According to claim 3, a method for quickly extracting strip-shaped local map elements from a high-precision map is characterized in that: Step S3 includes: S301, connecting the first and last points of the trajectory points of the preset center line with a straight line to obtain a first trajectory segment, calculating the distances from all remaining points to the first trajectory segment, and finding the maximum distance among them; if it is determined that the maximum distance exceeds a specified error range, selecting the point as a reserved point, and dividing the first trajectory segment into two with the point as the boundary; S302, repeating step S301 for the two newly generated trajectories until the maximum distance is within a specified error range; S303, taking the n reserved points obtained in step S301 and step S302 as key nodes of the preset center line, wherein n is a natural number greater than 1; retaining n of the key nodes, connecting lines of adjacent key nodes to form a second trajectory segment, and forming a new center line by connecting n-1 second trajectory segments.

6. According to claim 5, a method for quickly extracting strip-shaped local map elements from a high-precision map is characterized in that: Step S4 includes: S401, vertically projecting a single map element in the primary screening rectangular frame onto n-1 second trajectory segments in turn to obtain a projection distance dist_project of the map element onto the n-1 second trajectory segments, calculating a minimum value from the n-1 projection distances dist_project, the minimum value being the minimum projection distance min_dist_project from the map element to the new center line; if the minimum projection distance min_dist_project is determined to be within a preset extraction range, extracting the map element; S402, traverse all map elements in the initial screening rectangular frame, and extract all map elements in the initial screening rectangular frame whose minimum projection distance min_dist_project to the new center line is within a preset extraction range.

7. A method for rapidly extracting strip-shaped local map elements from a high-precision map according to claim 6, characterized in that: In step S401, the vertical projection of the single map element in the primary screening rectangular frame to the n-1 second trajectory segments in turn to obtain the projection distance dist_project of the map element to the n-1 second trajectory segments includes: Project each map element in the initial screening rectangle vertically onto n-1 second trajectory segments in turn. If the projection point falls on the second trajectory segment, the projection distance dist_project is the distance from the map element to the projection point. If the projection point falls on the extension line of the second trajectory segment, the projection distance dist_project is the minimum value of the distances from the map element to the two endpoints of the second trajectory segment. The map element is used to traverse n-1 second trajectory segments in sequence to obtain projection distances dist_project of the map element for the n-1 second trajectory segments respectively.

8. A system for rapidly extracting strip-shaped local map elements from a high-precision map, characterized in that: include: A preset module, used to obtain a preliminary screening rectangular frame including a preset center line and a preset extraction range according to a preset center line and a preset extraction range; A preliminary screening module is used to traverse map elements and retain map elements whose point coordinates are within the preliminary screening rectangular box; A preprocessing module, used for performing thinning preprocessing on the preset center line; The precise screening module is used to project all map elements within the initial screening rectangular box onto the preprocessed center line in sequence, calculate the minimum projection distance value of each map element, and retain the map elements whose minimum projection distance value is within the preset extraction range.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of a method for quickly extracting strip-shaped local map elements from a high-precision map as described in any one of claims 1 to 7 when executing a computer management program stored in the memory.

10. A computer-readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by a processor, the steps of a method for quickly extracting strip-shaped local map elements from a high-precision map as described in any one of claims 1 to 7 are implemented.

Images