Method, device and apparatus for removing road hangers

Abstract

The application discloses a method, device and equipment for removing hanging points in road data, and relates to the technical field of image processing. The method comprises the following steps: determining a first hanging point set based on acquired first road data; wherein the first hanging point set comprises a plurality of hanging points; determining a matching path of the hanging points based on a heuristic search algorithm, wherein the matching path is a path in a path between a road where the hanging points are located and a neighbor point or line of the hanging points, the path has the minimum distance and an included angle with the road where the hanging points are located within a first angle range; and processing the hanging points and / or the matching path according to a spatial position relationship of the hanging points, and removing the hanging points. The scheme of the application solves the problems of long cycle, high cost, low accuracy and poor universality of the existing method for removing hanging points.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus and device for removing road suspension points. Background Technology

[0002] With the development of technology, remote sensing image feature extraction technology has become increasingly mature, and the demand for automatic extraction of remote sensing images is becoming stronger. However, the road features obtained after automatic extraction contain a large number of hanging points, thus requiring efficient hanging point removal methods for post-processing of the extraction results. Currently, commonly used hanging point removal methods include manual removal, automated vector removal through linear region growing, and hanging point processing methods based on a nine-square grid. However, these methods suffer from problems such as long processing time, high cost, low accuracy, and poor universality. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, and equipment for removing road suspension points, thereby solving the problems of long cycle, high cost, low accuracy, and poor universality of existing methods for removing suspension points.

[0004] To achieve the above objectives, embodiments of this application provide a method for removing hanging points from road data, comprising:

[0005] Based on the acquired first road data, a first set of suspension points is determined; wherein, the first set of suspension points includes multiple suspension points;

[0006] Based on a heuristic search algorithm, a matching path for the suspension point is determined, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point, and the angle between the road where the suspension point is located and the road is located is within a first angle range.

[0007] Based on the spatial relationship of the suspension points, the suspension points and / or the matching path are processed to remove the suspension points.

[0008] Optionally, the method further includes:

[0009] Obtain second road data;

[0010] The second road data is processed in a first step to obtain the first road data;

[0011] The first process includes at least one of the following:

[0012] Binarization processing;

[0013] Skeletonization processing;

[0014] Vectorization processing.

[0015] Optionally, based on the acquired first road data, a first set of suspension points is determined, including:

[0016] Obtain the first road node located on only one road line from the first road data;

[0017] Based on the first road node, determine the second set of suspension points;

[0018] Based on the first parameter, the second set of suspension points is processed to determine the first set of suspension points;

[0019] The first parameter includes at least one of the following:

[0020] The first distance from the first road node to the obstacle in the first road data;

[0021] The second distance from the first road node to the blank area in the first road data;

[0022] The third distance from the first road node to the edge contour of the first road data;

[0023] The first length of the road line where the first road node is located.

[0024] Optionally, based on the first parameter, the second set of suspension points is processed to determine the first set of suspension points, including at least one of the following:

[0025] If the first distance is less than the first value and the obstacle is located in the extension direction of the road line where the first road node is located, the first road node is removed from the second set of suspension points.

[0026] If the second distance is less than the second value, the first road node is removed from the second set of suspension points;

[0027] If the third distance is less than the third value, the first road node is removed from the second set of suspension points;

[0028] If the first length is less than the fourth value, and the road line where the first road node is located does not intersect with other road lines in the first road data, the first road node is removed from the second suspension point set.

[0029] Optionally, the matching path for the dangling point is determined based on a heuristic search algorithm, including:

[0030] The suspension point is buffered, and at least one neighboring point and / or at least one neighboring line of the suspension point are obtained;

[0031] Based on a heuristic search algorithm, the shortest distance between the dangling point and each of the neighboring points and the corresponding first path are determined, and / or, the shortest distance between the dangling point and each of the neighboring lines and the corresponding second path are determined;

[0032] The matching path is determined based on the angle between the road line where the suspension point is located and the first path and / or the second path.

[0033] Optionally, determining the shortest distance between the suspending point and each of the neighboring points and the corresponding first path includes:

[0034] Using the suspension point as the first starting point, at least one first reachable point is determined among the eight neighboring points surrounding the first starting point;

[0035] Calculate the estimated value of the path passing through each of the first reachable points;

[0036] Using the first reachable point with the smallest valuation as the second starting point, determine at least one second reachable point among the eight neighboring points around the second starting point, and calculate the valuation of the path through each of the second reachable points;

[0037] The process involves taking the second reachable point with the smallest valuation as the first reachable point, returning to the first reachable point with the smallest valuation as the second starting point, identifying at least one second reachable point among the eight neighboring points around the second starting point, and calculating the valuation of the path through each of the second reachable points, until the neighboring points are added to the path node to obtain the first path and distance between the neighboring points added to the path node and the dangling point.

[0038] Optionally, determining the shortest distance between the suspension point and each of the neighboring lines and the corresponding second path includes:

[0039] Using the suspension point as the third starting point, at least one third reachable point is determined among the eight neighboring points surrounding the third starting point;

[0040] Draw perpendicular lines from each of the third reachable points to each of the neighboring lines, and calculate the distance between each of the third reachable points and each perpendicular foot point, wherein the perpendicular foot is the intersection of the perpendicular line and the neighboring line;

[0041] Based on the distance between each of the third reachable points and the perpendicular foot, obtain the second path and distance from the suspension point to each of the neighboring lines.

[0042] Optionally, if there is an obstacle on the first path or the second path, the angle between the road line where the suspension point is located and the first path or the second path is the angle between the road line where the suspension point is located and the portion of the first path or the second path closest to the suspension point.

[0043] Optionally, based on the spatial relationship of the suspension points, the suspension points and / or the matching path are processed to remove the suspension points, including:

[0044] The type of suspension point is determined based on the spatial relationship of the suspension points;

[0045] Based on the dangling point type, the dangling point and / or the matching path are processed to remove the dangling point.

[0046] Optionally, the suspension point type includes at least one of the following:

[0047] Offset suspension point;

[0048] Point of suspension after decapitation;

[0049] The point of breakage and suspension;

[0050] T-shaped suspension point;

[0051] Highlight the suspension point.

[0052] Optionally, the suspension point type is determined based on the spatial relationship of the suspension points, including at least one of the following:

[0053] If a suspension point does not match a neighboring point and / or a neighboring line, and there is another suspension point in the buffer of the suspension point, and the road lines where the two suspension points are located are parallel and extend in opposite directions, then the two suspension points are determined to be offset suspension points.

[0054] If a road line exists on the first side of the suspension point, the suspension point type is determined to be a dead-end suspension point, wherein the road line where the suspension point is located is located on the second side of the suspension point, and the first side and the second side are arranged opposite to each other;

[0055] A suspension point is defined as a point where the direction vectors of the road lines containing at least two suspension points coincide and the corresponding matching paths coincide.

[0056] If the angle between the extension direction of the road line where the suspension point is located and the matching path is within the second angle range, and there is no road line passing through the first road node in the extension direction of the suspension point, the suspension point is determined to be a T-shaped suspension point, wherein the first road node is the road node at the other end of the road line where the suspension point is located.

[0057] When the angle between the extension direction of the road line where the suspension point is located and the matching path is within the third angle range, and the second road node at the other end of the road line where the suspension point is located is located on the first road line, the suspension point is determined to be a protruding suspension point, wherein the extension direction of the first road line is parallel to the extension direction of the road line where the suspension point is located.

[0058] Optionally, based on the dangling point type, the dangling point and / or the matching path are processed to remove the dangling point, including at least one of the following:

[0059] If the suspension point is an offset suspension point, move the two offset suspension points to the midpoint of the line connecting the two offset suspension points, and adjust the road line where the two offset suspension points are located accordingly.

[0060] If the suspension point is a dead-end suspension point, delete the suspension point and set the intersection of the matching path of the suspension point and the neighboring line of the suspension point as a road node;

[0061] If the suspension point is a broken suspension point, retain the matching path of the suspension point and delete the suspension point;

[0062] If the suspension point is a T-shaped suspension point, delete the suspension point, the matching path corresponding to the suspension point, the road line where the suspension point is located, and the road node at the other end of the road line;

[0063] If the suspension point is a prominent suspension point, delete the suspension point, the matching path corresponding to the suspension point, and the road line where the suspension point is located, while retaining the road node at the other end of the road line.

[0064] This application embodiment also provides an apparatus for removing hanging points from road data, including:

[0065] The first determining module is used to determine a first set of suspension points based on the acquired first road data; wherein the first set of suspension points includes multiple suspension points;

[0066] The second determining module is used to determine the matching path of the suspension point based on a heuristic search algorithm, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point and the path with the road where the suspension point is located, and the angle between the road and the road is located is within a first angle range.

[0067] The processing module is used to process the suspension point and / or the matching path according to the spatial position relationship of the suspension point, and remove the suspension point.

[0068] This application also provides an apparatus for removing drooping points from road data, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method for removing drooping points from road data as described above.

[0069] This application embodiment also provides a readable storage medium storing a program that, when executed by a processor, implements the steps of the method for removing hanging points from road data as described above.

[0070] The above-mentioned technical solution of this application has at least the following beneficial effects:

[0071] The method for removing hanging points from road data according to this application embodiment firstly determines a first set of hanging points based on the acquired first road data; wherein the first set of hanging points includes multiple hanging points; secondly, based on a heuristic search algorithm, a matching path for each hanging point is determined, wherein the matching path is the path with the smallest distance between the road where the hanging point is located and its neighboring points or lines, and the angle between the matching path and the road where the hanging point is located is within a first angle range; thus, the interference of obstacles on distance calculation is eliminated, making the road extraction results more consistent with reality; finally, according to the spatial positional relationship of the hanging points, the hanging points and / or the matching paths are processed to remove the hanging points. In this way, different removal methods are used for different hanging points, improving universality; the technical solution of this application ultimately achieves accurate and rapid removal of hanging points, shortens the production cycle, and reduces costs. Attached Figure Description

[0072] Figure 1 This is a flowchart illustrating a method for removing hanging points from road data according to an embodiment of this application.

[0073] Figure 2A This is a schematic diagram of the offset suspension point according to an embodiment of this application;

[0074] Figure 2B This is a schematic diagram of the severed head suspension point according to an embodiment of this application;

[0075] Figure 2C This is a schematic diagram of the breakage suspension point according to an embodiment of this application;

[0076] Figure 2D This is a schematic diagram of the T-shaped suspension point according to an embodiment of this application;

[0077] Figure 2E This is a schematic diagram of the prominent suspension point in an embodiment of this application;

[0078] Figure 3AThis is a schematic diagram illustrating the offset suspension point processing in an embodiment of this application;

[0079] Figure 3B This is one of the schematic diagrams illustrating the treatment of the severed head suspension point in an embodiment of this application;

[0080] Figure 3C This is the second schematic diagram illustrating the treatment of the severed head suspension point in an embodiment of this application;

[0081] Figure 3D This is one of the schematic diagrams illustrating the treatment of the fractured suspension point in an embodiment of this application;

[0082] Figure 3E This is the second schematic diagram of the treatment of the broken suspension point in the embodiments of this application;

[0083] Figure 3F This is a schematic diagram illustrating the T-shaped suspension point processing in an embodiment of this application;

[0084] Figure 3G This is a schematic diagram illustrating the treatment of the protruding suspension point in an embodiment of this application;

[0085] Figure 4 This is a schematic diagram of the device for removing suspension points from road data according to an embodiment of this application;

[0086] Figure 5 This is a schematic diagram of the structure of a device for removing suspension points from road data according to an embodiment of this application. Detailed Implementation

[0087] 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.

[0088] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0089] The method, apparatus, and equipment for removing hanging points from road data provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0090] like Figure 1 The diagram shown is a flowchart illustrating a method for removing hanging points from road data according to an embodiment of this application. The method includes:

[0091] Step 101: Based on the acquired first road data, determine a first set of suspension points; wherein the first set of suspension points includes multiple suspension points;

[0092] It should be noted that the first road data can be road data obtained based on remote sensing images or remote sensing images with annotation information; among them, remote sensing images refer to films or photographs that record the electromagnetic wave magnitude of various ground features, mainly divided into aerial photographs and satellite photographs.

[0093] Step 102: Based on a heuristic search algorithm, determine the matching path of the suspension point, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point, and the angle between the road where the suspension point is located and the road is located is within a first angle range.

[0094] It should be noted that heuristic search algorithms evaluate each search position in the state space, obtain the best position, and then search from that position until the target is found.

[0095] Step 103: Based on the spatial relationship of the suspension points, process the suspension points and / or the matching path to remove the suspension points.

[0096] The method for removing hanging points from road data according to this application embodiment firstly determines a first set of hanging points based on the acquired first road data; wherein the first set of hanging points includes multiple hanging points; secondly, based on a heuristic search algorithm, a matching path for each hanging point is determined, wherein the matching path is the path with the smallest distance between the road where the hanging point is located and its neighboring points or lines, and the angle between the matching path and the road where the hanging point is located is within a first angle range; thus, the interference of obstacles on distance calculation is eliminated, making the road extraction results more consistent with reality; finally, according to the spatial positional relationship of the hanging points, the hanging points and / or the matching paths are processed to remove the hanging points. In this way, different removal methods are used for different hanging points, improving universality; the technical solution of this application ultimately achieves accurate and rapid removal of hanging points, shortens the production cycle, and reduces costs.

[0097] Furthermore, as an optional implementation, the method also includes:

[0098] Obtain second road data;

[0099] The second road data is processed in a first step to obtain the first road data;

[0100] The first process includes at least one of the following:

[0101] Binarization processing;

[0102] Skeletonization processing;

[0103] Vectorization processing.

[0104] In other words, the first road data is an automatically vectorized set of road points and lines obtained after preprocessing the second road data. The preprocessing process is explained in detail below:

[0105] First, the second road data is binarized, specifically by setting the pixel value of the road in the road extraction result (second road data) to 255 and the pixel value of the background to 0, presenting a clear black and white effect, thereby highlighting the road extraction result.

[0106] Secondly, skeletonization processing is performed, which specifically includes: extracting the central pixel contour of the road and outputting the skeletonized road extraction result;

[0107] Next, vectorization processing is performed, specifically including: vectorizing the extracted road results and marking the direction of the road results to facilitate the next step of operation.

[0108] As an optional implementation, step 101, based on the acquired first road data, determines the first set of suspension points, including:

[0109] (1) Obtain the first road node in the first road data that is located on only one road line;

[0110] (2) Determine the second set of suspension points based on the first road node;

[0111] It should be noted that the second suspension point set includes multiple first road nodes. That is, in the first road data, if any endpoint of a road line is not on any other road line, then that endpoint is a suspension point and is added to the second suspension point set.

[0112] (3) Based on the first parameter, process the second set of suspension points to determine the first set of suspension points;

[0113] The first parameter includes at least one of the following:

[0114] The first distance from the first road node to the obstacle in the first road data;

[0115] The second distance from the first road node to the blank area in the first road data;

[0116] The third distance from the first road node to the edge contour of the first road data;

[0117] The first length of the road line where the first road node is located.

[0118] It should be noted that, considering the influence of obstacles, image edges and blank areas, the first road node obtained may not be a hanging point, that is, the first road node obtained may be a pseudo-hanging point. Therefore, in this optional implementation, the second hanging point set is further processed to remove pseudo-hanging points in order to improve the accuracy of hanging point extraction.

[0119] As a specific implementation, based on the first parameter, the second set of suspension points is processed to determine the first set of suspension points, which includes at least one of the following:

[0120] (1) If the first distance is less than the first value and the obstacle is located in the extension direction of the road line where the first road node is located, the first road node is removed from the second set of suspension points;

[0121] In other words, when determining whether the first road node is a suspended point, the influence of obstacles such as green space, water body, and buildings is considered. The distance from the first road node to the obstacle is calculated. If the obstacle is close to the first road node and is located in the extension direction of the road line where the first road node is located, the first road node is considered to be a normal road node (belonging to a pseudo suspended point), and the first road node is removed from the second suspended point set.

[0122] (2) If the second distance is less than the second value, remove the first road node from the second set of suspension points;

[0123] In other words, when determining whether the first road node is a hanging point, the blank remote sensing image area is considered, the blank area of ​​the data source image is extracted, the distance between the first road node and the blank area of ​​the image is calculated, and if the distance is close, the first road node is considered to be the boundary point of the road line and belongs to the false hanging point, and the first road node is removed from the second hanging point set.

[0124] (3) If the third distance is less than the third value, the first road node is removed from the second set of suspension points;

[0125] In other words, when determining whether the first road node is a hanging point, the influence of the image edge contour is considered, and the distance between the first road node and the image edge contour is calculated. If the distance is close, the first road node is considered to be the boundary point of the road line and belongs to the pseudo hanging point. The point is then removed from the second hanging point set.

[0126] (4) If the first length is less than the fourth value and the road line where the first road node is located does not intersect with other road lines in the first road data, the first road node is removed from the second suspension point set.

[0127] In other words, when determining whether the first road node is a hanging point, the influence of noise factors is considered, and the length of the road line where the first road node is located is calculated. If the length of the road line is shorter than the fourth value (such as 100 meters) and does not intersect with any other road line, then the road line where the first road node is located is considered to be noise in the road extraction result (first road data) and belongs to a false hanging point. The road line and the corresponding first road node are then deleted.

[0128] In this specific implementation, by combining obstacles such as water bodies and green spaces to remove pseudo-hanging points, the processing speed is improved, the goal of quickly and accurately determining the hanging points is achieved, the production cycle is shortened, and the production cost is reduced.

[0129] As an optional implementation, step 102, based on a heuristic search algorithm, determines the matching path for the dangling point, including:

[0130] (1) Buffer the suspension point and obtain at least one neighboring point and / or at least one neighboring line of the suspension point;

[0131] Specifically, this step involves determining the buffer zone of the suspension point with R as the center. All nodes within the buffer zone are called neighboring points, and road lines whose endpoints are not within the buffer zone are called neighboring lines.

[0132] (2) Based on a heuristic search algorithm, determine the distance between the suspending point and each of the neighboring points and the corresponding first path, and / or determine the shortest distance between the suspending point and each of the neighboring lines and the corresponding second path;

[0133] (3) Determine the matching path based on the angle between the road line where the suspension point is located and the first path and / or the second path.

[0134] Here, it should be noted that the specific implementation process of step (3) above can be as follows:

[0135] First, sort the first and second paths in ascending order of distance to obtain the set of shortest paths;

[0136] Secondly, in the set of shortest paths, the path with the shortest distance is selected as the candidate matching path, and its corresponding neighbor points or neighbor lines are selected as candidate neighbor points or candidate neighbor lines.

[0137] Next, with the suspension point as the center, the horizontal axis of the image pixels is used as the x-axis and the vertical axis as the y-axis to generate a Cartesian coordinate system, and calculate the angle between the road line where the suspension point is located and the candidate matching path.

[0138] Finally, if the included angle is within the first angle range, then the neighbor point or neighbor line is considered a matching neighbor point or matching neighbor line. Otherwise, the second shortest path in the shortest path set is selected as a candidate matching path, and the above steps are repeated until the included angle between the candidate matching path and the road line where the hanging point is located is within the first angle range, or the included angle between all paths in the candidate path set and the road line where the hanging point is located is not within the first angle range, that is, the neighbor points or neighbor lines corresponding to all paths in the candidate path set do not meet the requirements.

[0139] It should be noted here that the first angle range is [0°, 10°] or [170°, 180°].

[0140] In this optional implementation, when determining the matching path of the suspension point, not only the matching between points is considered, but also the matching between the suspension point and the road line, which improves the accuracy of suspension point removal.

[0141] As a specific implementation, determining the distance between the suspending point and each of the neighboring points and the corresponding first path includes:

[0142] (1) Taking the suspension point as the first starting point, determine at least one first reachable point among the eight neighboring points around the first starting point;

[0143] This step is as follows: Taking the suspending point as the starting point, check whether the eight neighboring points around it are reachable. If there are obstacle points among the eight neighboring points, the obstacle points are considered unreachable and ignored; if the eight neighboring points are not obstacle points, they are reachable points.

[0144] (2) Calculate the estimated value of the path through each of the first reachable points;

[0145] This step specifically involves calculating the estimated value of the path passing through each of the first reachable points using the formula F = G + H, where F represents the estimated value of the path passing through the first reachable point. The smaller the value of F, the smaller the estimated value of the path passing through that reachable point, and the greater the likelihood that the path passing through that reachable point is the shortest path. The calculations for G and H are shown below:

[0146] G represents the distance from a specific point to the starting point, which is the sum of the distance from the starting point to its parent node and the distance from its parent node to the starting point.

[0147] H represents the estimated distance from the first reachable point to its neighboring points. In this optional implementation, the distance from the reachable point to its neighboring points is calculated directly using Euclidean distance, ignoring any obstacles.

[0148] (3) Take the first reachable point with the smallest valuation as the second starting point, determine at least one second reachable point among the eight neighboring points around the second starting point, and calculate the valuation of the path through each second reachable point;

[0149] (4) The step of taking the second reachable point with the smallest valuation as the first reachable point, returning to the first reachable point with the smallest valuation as the second starting point, determining at least one second reachable point among the eight neighboring points around the second starting point, and calculating the valuation of the path through each second reachable point, until the neighboring point is added to the path node, so as to obtain the first path and distance between the neighboring point added to the path node and the dangling point.

[0150] In other words, the above steps (3) and (4) are as follows: select the one with the smallest F value among all first reachable points as the path node, take this node as the new starting point, repeat steps (2) and (3) until the neighboring points are also added to the path nodes, and finally obtain the shortest path.

[0151] As another specific implementation, determining the shortest distance between the suspension point and each of the neighboring lines and the corresponding second path includes:

[0152] (1) Using the suspension point as the third starting point, determine at least one third reachable point among the eight neighboring points around the third starting point;

[0153] This step is as follows: Taking the suspending point as the starting point, check whether the eight neighboring points around it are reachable. If there are obstacle points among the eight neighboring points, the obstacle points are considered unreachable and ignored; if the eight neighboring points are not obstacle points, they are reachable points.

[0154] (2) Draw perpendicular lines from each of the third reachable points to each of the neighboring lines, and calculate the distance between each of the third reachable points and each perpendicular foot point, wherein the perpendicular foot is the intersection of the perpendicular line and the neighboring line;

[0155] (3) Based on the distance between each of the third reachable points and the perpendicular foot, obtain the second path and distance from the suspension point to each of the neighboring lines.

[0156] The specific implementation process can be as follows: Based on heuristic search, draw a perpendicular line from the reachable point to the road line (neighbor line), take the intersection of the perpendicular line and the road line (neighbor line) as the endpoint, and calculate the Euclidean distance between the two points as the estimated distance from the reachable point to the neighbor line. Repeat the above steps to obtain the shortest path from the dangling point to each neighbor line.

[0157] As an optional implementation, if there is an obstacle on the first path or the second path, the angle between the road line where the suspension point is located and the first path or the second path is the angle between the road line where the suspension point is located and the portion of the first path or the second path closest to the suspension point.

[0158] As an optional implementation, step 103 involves processing the suspension points and / or the matching path based on their spatial relationships to remove the suspension points, including:

[0159] The type of suspension point is determined based on the spatial relationship of the suspension points;

[0160] It should be noted that the spatial relationship of the suspension point can include the spatial relationship between the suspension point and other suspension points or other road lines.

[0161] Based on the dangling point type, the dangling point and / or the matching path are processed to remove the dangling point.

[0162] In this optional implementation, the suspension points are classified into different types based on their spatial positional relationships. This allows for the acquisition of concise and accurate road extraction results. Furthermore, different processing is performed on the suspension points based on their types, achieving the goal of removing suspension points using simple logic. Ultimately, complete and accurate road data is obtained, thus improving the universality of the method for removing suspension points from road data in this application embodiment.

[0163] As a specific implementation method, such as Figures 2A to 2E The suspension point type includes at least one of the following:

[0164] Offset suspension point;

[0165] Point of suspension after decapitation;

[0166] The point of breakage and suspension;

[0167] T-shaped suspension point;

[0168] Highlight the suspension point.

[0169] like Figure 2AAs shown, suspension point d1 is located on road line S1, and suspension point d2 is located on road line S2. That is to say, if the road lines where the two suspension points are located are parallel to each other and extend in opposite directions, then these two suspension points are considered to be offset suspension points.

[0170] like Figure 2B As shown, suspension point d3 is located on road line S3, and the other end of suspension point d3 is on road line S4. That is to say, if the other end of the suspension point is a road line, then the suspension point is considered to be a dead-end suspension point.

[0171] like Figure 2C As shown, suspension point d4 is located on road line S4, and suspension point d5 is located on road line S5. Suspension points d4 and d5 are broken suspension points. That is, among the remaining suspension points that match neighboring points or neighboring lines, the direction vectors of the road line and the matching path are calculated. If the direction vectors coincide or are close to coincide, the suspension point is considered to be a broken suspension point.

[0172] like Figure 2D As shown, suspension point d6 is located on road line S7. Road line S7 and road line S8 are compared with ordinary road node j1, and road line S7 ends at road node j1. Therefore, suspension point d6 is a T-shaped suspension point. That is, if the angle between the extension direction of the road line centered on the suspension point and the matching path is 180° or close to 180°, and the road line is extended in the opposite direction at another node, if there is no road line in the reverse extension direction, then the suspension point is considered to be a "T"-shaped suspension point.

[0173] like Figure 2E As shown, suspension point d7 is located on road line S9. Road line S10 and road line S9 are compared with ordinary road node j2, and road line S9 passes through road node j1 and extends. Then suspension point d7 is a prominent suspension point. That is, if the angle between the extension direction of the road line centered on the suspension point and the matching path is 180° or close to 180°, and there is a road line in the opposite extension direction of another node, then the suspension point is considered to be a prominent suspension point.

[0174] As an optional implementation, the suspension point type is determined based on the spatial relationship of the suspension points, including at least one of the following:

[0175] If a suspension point does not match a neighboring point and / or a neighboring line, and there is another suspension point in the buffer of the suspension point, and the road lines on which the two suspension points are located are parallel and extend in opposite directions, then the two suspension points are determined to be offset suspension points. That is, a buffer processing is performed on suspension points that do not match a neighboring point or a neighboring line. If there is another suspension point in the buffer, and the road lines on which the two suspension points are located are parallel and extend in opposite directions, then the two suspension points are considered to be offset suspension points.

[0176] If a road line exists on the first side of the suspension point, the suspension point type is determined to be a dead-end suspension point, wherein the road line where the suspension point is located is located on the second side of the suspension point, and the first side and the second side are arranged opposite to each other; that is, if the other end of the suspension point is a road line, the suspension point is considered to be a dead-end suspension point.

[0177] A broken suspension point is defined as a suspension point where the direction vectors of the road lines containing at least two suspension points coincide and the corresponding matching paths also coincide. In other words, among the remaining suspension points that match the neighboring point lines, the direction vectors of the road lines and the matching paths are calculated. If the direction vectors coincide or are nearly coincident, the suspension point is considered to be a broken suspension point.

[0178] If the angle between the extension direction of the road line where the suspension point is located and the matching path is within the second angle range, and there is no road line passing through the first road node in the extension direction of the suspension point, the suspension point is determined to be a T-shaped suspension point. The first road node is the road node at the other end of the road line where the suspension point is located. That is, if the angle between the extension direction of the road line centered on the suspension point and the matching path is 180° or close to 180°, and the road line is extended in the opposite direction at another node, if there is no road line in the opposite extension direction, the suspension point is considered to be a "T"-shaped suspension point.

[0179] If the angle between the extension direction of the road line where the suspension point is located and the matching path is within the third angle range, and the second road node at the other end of the road line where the suspension point is located is located on the first road line, then the suspension point is determined to be a protruding suspension point. In this case, the extension direction of the first road line is parallel to the extension direction of the road line where the suspension point is located. That is, if the angle between the extension direction of the road line centered on the suspension point and the matching path is 180° or close to 180°, and there is a road line in the opposite extension direction of the other node, then the suspension point is considered to be a protruding suspension point.

[0180] As an optional implementation, the dangling point and / or the matching path are processed according to the dangling point type to remove the dangling point, including at least one of the following:

[0181] (1) If the suspension point is an offset suspension point, move the two offset suspension points to the midpoint of the line connecting the two offset suspension points, and adjust the road line where the two offset suspension points are located accordingly.

[0182] Specifically, such as Figure 3A As shown, suspension points d1 and d2 on road line S1 and S2 are offset suspension points. The process of processing these two suspension points is as follows: set a line connecting suspension points d1 and d2, move both suspension points d1 and d2 toward the midpoint of the line until the two suspension points coincide at the midpoint d of the line, and adjust road lines S1 and S2 accordingly so that road lines S1 and S2 intersect at the midpoint d.

[0183] (2) If the suspension point is a dead suspension point, delete the suspension point and set the intersection of the matching path of the suspension point and the neighboring line of the suspension point as a road node;

[0184] Specifically, such as Figure 2B As shown, when suspension point d3 on road line S3 is a dead suspension point, the processing procedure for suspension point d3 is as follows: delete suspension point d3, and change the matching path of suspension point d3 ( Figure 3B and 3C The intersection point d of the dashed line portion (in the diagram) and road line S4 is set as the new road node, where, Figure 3B and Figure 3C The difference is that there are obstacles in the matching path. Figure 3C ) and the absence of obstacles ( Figure 3B ).

[0185] (3) If the suspension point is a broken suspension point, retain the matching path of the suspension point and delete the suspension point;

[0186] Specifically, such as Figure 2C As shown, suspension point d4 on road line S4 and suspension point d5 on road line S5 are broken suspension points. The processing procedure for suspension points d4 and d5 is as follows: retain the matching path between road line S4 and road line S5 (either suspension point d4 or suspension point d5). Figure 3D and Figure 3E (The dashed line portion), delete hanging point d4 or hanging point d5, that is, connect road line S4 and road line S5 through a matching path, where, Figure 3D and Figure 3E The difference is that there are obstacles in the matching path. Figure 3E ) and the absence of obstacles ( Figure 3D ).

[0187] (4) If the suspension point is a T-shaped suspension point, delete the suspension point, the matching path corresponding to the suspension point, the road line where the suspension point is located, and the road node at the other end of the road line;

[0188] Specifically, such as Figure 2D As shown, suspension point d6 on road line S7 is a T-shaped suspension point. The processing procedure for suspension point d6 is as follows: the matching path between road line S7 and suspension point d6 is... Figure 3F Delete the dashed part LL in the middle, and delete the intersection of the matching path and the neighbor line S8 (road node j1).

[0189] (5) If the suspension point is a prominent suspension point, delete the suspension point, the matching path corresponding to the suspension point, and the road line where the suspension point is located, and retain the road node at the other end of the road line.

[0190] Specifically, such as Figure 2E As shown, the suspension point d7 located on road line S9 is a prominent suspension point. The processing procedure for suspension point d7 is as follows: delete suspension point d7, and the matching path and road line corresponding to suspension point d7 are... Figure 3G (The dashed part in the text), and retain the road node j2 at the other end of the road line where the suspension point is located.

[0191] The method for removing suspended points from road data in this application has the following advantages: First, it considers the influence of obstacles, noise, image edges, and blank areas to remove false suspended points, thus improving processing speed. Second, it uses a heuristic search algorithm to calculate the shortest paths from suspended points to neighboring points and from suspended points to neighboring lines, and then merges the two to select the shortest distance as the candidate best path. By comparing the road slope and the path slope, the optimal connection path is finally determined. This eliminates the interference of obstacles on distance calculation, making the road extraction results more consistent with reality. Third, it classifies suspended points based on their spatial relationships and processes them differently according to their type. Finally, it obtains complete road data, making the method more universal.

[0192] like Figure 4 As shown in the illustration, this application also provides an apparatus for removing suspension points from road data, comprising:

[0193] The first determining module 401 is used to determine a first set of suspension points based on the acquired first road data; wherein the first set of suspension points includes multiple suspension points;

[0194] The second determining module 402 is used to determine the matching path of the suspension point based on a heuristic search algorithm, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point and the road where the suspension point is located, and the angle between the road and the suspension point is within a first angle range.

[0195] The processing module 403 is used to process the suspension point and / or the matching path according to the spatial position relationship of the suspension point, and remove the suspension point.

[0196] The apparatus for removing hanging points from road data according to this application embodiment firstly determines a first set of hanging points based on the acquired first road data; wherein the first set of hanging points includes multiple hanging points; secondly, a second determining module 402 determines a matching path for the hanging points based on a heuristic search algorithm, wherein the matching path is the path with the smallest distance between the road where the hanging point is located and the neighboring points or lines of the hanging point, and the angle between the matching path and the road where the hanging point is located is within a first angle range; thus, the interference of obstacles on distance calculation is eliminated, making the road extraction results more consistent with reality; finally, a processing module 403 processes the hanging points and / or the matching paths according to the spatial positional relationship of the hanging points to remove the hanging points. In this way, different removal methods are used for different hanging points, improving universality; the technical solution of this application ultimately achieves accurate and rapid removal of hanging points, shortens the production cycle, and reduces costs.

[0197] Optionally, the device further includes:

[0198] The first acquisition module is used to acquire the second road data;

[0199] The second acquisition module is used to perform a first process on the second road data to acquire the first road data;

[0200] The first process includes at least one of the following:

[0201] Binarization processing;

[0202] Skeletonization processing;

[0203] Vectorization processing.

[0204] Optionally, the first determining module 401 includes:

[0205] The first acquisition submodule is used to acquire the first road node in the first road data that is located on only one road line;

[0206] The first determining submodule is used to determine the second set of suspension points based on the first road node;

[0207] The second determining submodule is used to process the second set of suspension points based on the first parameter to determine the first set of suspension points;

[0208] The first parameter includes at least one of the following:

[0209] The first distance from the first road node to the obstacle in the first road data;

[0210] The second distance from the first road node to the blank area in the first road data;

[0211] The third distance from the first road node to the edge contour of the first road data;

[0212] The first length of the road line where the first road node is located.

[0213] Optionally, the second determining submodule is specifically used for at least one of the following:

[0214] If the first distance is less than the first value and the obstacle is located in the extension direction of the road line where the first road node is located, the first road node is removed from the second set of suspension points.

[0215] If the second distance is less than the second value, the first road node is removed from the second set of suspension points;

[0216] If the third distance is less than the third value, the first road node is removed from the second set of suspension points;

[0217] If the first length is less than the fourth value, and the road line where the first road node is located does not intersect with other road lines in the first road data, the first road node is removed from the second suspension point set.

[0218] Optionally, the second determining module 402 includes:

[0219] The second acquisition submodule is used to buffer the suspension point and acquire at least one neighboring point and / or at least one neighboring line of the suspension point;

[0220] The third determination submodule is used to determine the shortest distance between the suspending point and each of the neighboring points and the corresponding first path based on a heuristic search algorithm, and / or to determine the shortest distance between the suspending point and each of the neighboring lines and the corresponding second path.

[0221] The fourth determining submodule is used to determine the matching path based on the angle between the road line where the suspension point is located and the first path and / or the second path.

[0222] Optionally, the third determining submodule includes:

[0223] The first determining unit is used to determine at least one first reachable point among eight neighboring points around the first starting point, taking the suspension point as the first starting point.

[0224] The first calculation unit is used to calculate the estimated value of the path passing through each of the first reachable points;

[0225] The second determining unit is used to take the first reachable point with the smallest estimated value as the second starting point, determine at least one second reachable point among the eight neighboring points around the second starting point, and calculate the estimated value of the path through each of the second reachable points.

[0226] The first acquisition unit is used to take the second reachable point with the smallest valuation as the first reachable point, return to the first reachable point with the smallest valuation as the second starting point, determine at least one second reachable point among the eight neighboring points around the second starting point, and calculate the valuation of the path through each second reachable point, until the neighboring point is added to the path node, so as to obtain the first path and distance between the neighboring point added to the path node and the dangling point.

[0227] Optionally, the third determining submodule includes:

[0228] The third determining unit is used to determine at least one third reachable point among eight neighboring points around the third starting point, taking the suspension point as the third starting point.

[0229] The second calculation unit is used to draw perpendicular lines from each of the third reachable points to each of the neighboring lines, and calculate the distance between each of the third reachable points and each perpendicular foot point, wherein the perpendicular foot is the intersection point of the perpendicular line and the neighboring line;

[0230] The second acquisition unit is used to acquire the second path and distance from the suspension point to each of the neighboring lines based on the distance between each of the third reachable points and the perpendicular foot.

[0231] Optionally, if there is an obstacle on the first path or the second path, the angle between the road line where the suspension point is located and the first path or the second path is the angle between the road line where the suspension point is located and the portion of the first path or the second path closest to the suspension point.

[0232] Optionally, the processing module 403 includes:

[0233] The fifth determining submodule is used to determine the suspension point type of the suspension point based on the spatial positional relationship of the suspension points;

[0234] The processing submodule is used to process the dangling point and / or the matching path according to the dangling point type, and remove the dangling point.

[0235] Optionally, the suspension point type includes at least one of the following:

[0236] Offset suspension point;

[0237] Point of suspension after decapitation;

[0238] The point of breakage and suspension;

[0239] T-shaped suspension point;

[0240] Highlight the suspension point.

[0241] Optionally, the fifth determining submodule is specifically used for at least one of the following:

[0242] If a suspension point does not match a neighboring point and / or a neighboring line, and there is another suspension point in the buffer of the suspension point, and the road lines where the two suspension points are located are parallel and extend in opposite directions, then the two suspension points are determined to be offset suspension points.

[0243] If a road line exists on the first side of the suspension point, the suspension point type is determined to be a dead-end suspension point, wherein the road line where the suspension point is located is located on the second side of the suspension point, and the first side and the second side are arranged opposite to each other;

[0244] A suspension point is defined as a point where the direction vectors of the road lines containing at least two suspension points coincide and the corresponding matching paths coincide.

[0245] If the angle between the extension direction of the road line where the suspension point is located and the matching path is within the second angle range, and there is no road line passing through the first road node in the extension direction of the suspension point, the suspension point is determined to be a T-shaped suspension point, wherein the first road node is the road node at the other end of the road line where the suspension point is located.

[0246] When the angle between the extension direction of the road line where the suspension point is located and the matching path is within the third angle range, and the second road node at the other end of the road line where the suspension point is located is located on the first road line, the suspension point is determined to be a protruding suspension point, wherein the extension direction of the first road line is parallel to the extension direction of the road line where the suspension point is located.

[0247] Optionally, the processing submodule is specifically used for at least one of the following:

[0248] If the suspension point is an offset suspension point, move the two offset suspension points to the midpoint of the line connecting the two offset suspension points, and adjust the road line where the two offset suspension points are located accordingly.

[0249] If the suspension point is a dead-end suspension point, delete the suspension point and set the intersection of the matching path of the suspension point and the neighboring line of the suspension point as a road node;

[0250] If the suspension point is a broken suspension point, retain the matching path of the suspension point and delete the suspension point;

[0251] If the suspension point is a T-shaped suspension point, delete the suspension point, the matching path corresponding to the suspension point, the road line where the suspension point is located, and the road node at the other end of the road line;

[0252] If the suspension point is a prominent suspension point, delete the suspension point, the matching path corresponding to the suspension point, and the road line where the suspension point is located, while retaining the road node at the other end of the road line.

[0253] like Figure 5 As shown, this application embodiment also provides a device for removing hanging points from road data, including: a processor 500, a memory 520, and a program stored in the memory 520 and executable on the processor 500. When the program is executed by the processor, it implements the various processes of the method embodiment for removing hanging points from road data as described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0254] The transceiver 510 is used to receive and send data under the control of the processor 500.

[0255] Among them, Figure 5 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 500 and memory represented by memory 520 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 510 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. For different user equipment, user interface 530 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0256] The processor 500 is responsible for managing the bus architecture and general processing, while the memory 520 can store the data used by the processor 500 when performing operations.

[0257] This application also provides a readable storage medium storing a program. When executed by a processor, this program implements the various processes of the above-described method embodiment for removing hanging points from road data, achieving the same technical effect. To avoid repetition, it will not be described again here. The readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0258] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0259] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles described in this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for removing dangling points from road data, characterized in that, include: Based on the acquired first road data, a first set of suspension points is determined; wherein, the first set of suspension points includes multiple suspension points; Based on a heuristic search algorithm, a matching path for the suspension point is determined, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point, and the angle between the road where the suspension point is located and the road is located is within a first angle range. Based on the spatial relationship of the suspension points, the suspension points and / or the matching path are processed to remove the suspension points; Specifically, processing the suspension points and / or the matching path based on their spatial relationships, and removing the suspension points, includes: The type of suspension point is determined based on the spatial relationship of the suspension points; Based on the type of dangling point, the dangling point and / or the matching path are processed to remove the dangling point; Specifically, processing the dangling point and / or the matching path according to the dangling point type to remove the dangling point includes at least one of the following: If the suspension point is an offset suspension point, move the two offset suspension points to the midpoint of the line connecting the two offset suspension points, and adjust the road line where the two offset suspension points are located accordingly. If the suspension point is a dead-end suspension point, delete the suspension point and set the intersection of the matching path of the suspension point and the neighboring line of the suspension point as a road node; If the suspension point is a broken suspension point, retain the matching path of the suspension point and delete the suspension point; If the suspension point is a T-shaped suspension point, delete the suspension point, the matching path corresponding to the suspension point, the road line where the suspension point is located, and the road node at the other end of the road line; If the suspension point is a prominent suspension point, delete the suspension point, the matching path corresponding to the suspension point, and the road line where the suspension point is located, while retaining the road node at the other end of the road line.

2. The method according to claim 1, characterized in that, The method further includes: Obtain second road data; The second road data is processed in a first step to obtain the first road data; The first process includes at least one of the following: Binarization processing; Skeletonization processing; Vectorization processing.

3. The method according to claim 1, characterized in that, Based on the acquired first road data, a first set of suspension points is determined, including: Obtain the first road node located on only one road line from the first road data; Based on the first road node, determine the second set of suspension points; Based on the first parameter, the second set of suspension points is processed to determine the first set of suspension points; The first parameter includes at least one of the following: The first distance from the first road node to the obstacle in the first road data; The second distance from the first road node to the blank area in the first road data; The third distance from the first road node to the edge contour of the first road data; The first length of the road line where the first road node is located.

4. The method according to claim 3, characterized in that, Based on the first parameter, the second set of suspension points is processed to determine the first set of suspension points, which includes at least one of the following: If the first distance is less than the first value and the obstacle is located in the extension direction of the road line where the first road node is located, the first road node is removed from the second set of suspension points. If the second distance is less than the second value, the first road node is removed from the second set of suspension points; If the third distance is less than the third value, the first road node is removed from the second set of suspension points; If the first length is less than the fourth value, and the road line where the first road node is located does not intersect with other road lines in the first road data, the first road node is removed from the second suspension point set.

5. The method according to claim 1, characterized in that, Based on a heuristic search algorithm, the matching path for the dangling point is determined, including: The suspension point is buffered, and at least one neighboring point and / or at least one neighboring line of the suspension point are obtained; Based on a heuristic search algorithm, the shortest distance between the dangling point and each of the neighboring points and the corresponding first path are determined, and / or, the shortest distance between the dangling point and each of the neighboring lines and the corresponding second path are determined; The matching path is determined based on the angle between the road line where the suspension point is located and the first path and / or the second path.

6. The method according to claim 5, characterized in that, Determining the shortest distance between the suspending point and each of the neighboring points and the corresponding first path includes: Using the suspension point as the first starting point, at least one first reachable point is determined among the eight neighboring points surrounding the first starting point; Calculate the estimated value of the path passing through each of the first reachable points; Using the first reachable point with the smallest valuation as the second starting point, determine at least one second reachable point among the eight neighboring points around the second starting point, and calculate the valuation of the path through each of the second reachable points; The process involves taking the second reachable point with the smallest valuation as the first reachable point, returning to the first reachable point with the smallest valuation as the second starting point, identifying at least one second reachable point among the eight neighboring points around the second starting point, and calculating the valuation of the path through each of the second reachable points, until the neighboring points are added to the path node to obtain the first path and distance between the neighboring points added to the path node and the dangling point.

7. The method according to claim 5, characterized in that, Determining the shortest distance between the suspension point and each of the neighboring lines and the corresponding second path includes: Using the suspension point as the third starting point, at least one third reachable point is determined among the eight neighboring points surrounding the third starting point; Draw perpendicular lines from each of the third reachable points to each of the neighboring lines, and calculate the distance between each of the third reachable points and each perpendicular foot point, wherein the perpendicular foot is the intersection of the perpendicular line and the neighboring line; Based on the distance between each of the third reachable points and the perpendicular foot, obtain the second path and distance from the suspension point to each of the neighboring lines.

8. The method according to claim 5, characterized in that, If there is an obstacle on the first path or the second path, the angle between the road line where the suspension point is located and the first path or the second path is the angle between the road line where the suspension point is located and the portion of the first path or the second path closest to the suspension point.

9. The method according to claim 1, characterized in that, The suspension point type includes at least one of the following: Offset suspension point; Point of suspension after decapitation; The point of breakage and suspension; T-shaped suspension point; Highlight the suspension point.

10. The method according to claim 1, characterized in that, Based on the spatial relationship of the suspension points, the suspension point type is determined, including at least one of the following: If a suspension point does not match a neighboring point and / or a neighboring line, and there is another suspension point in the buffer of the suspension point, and the road lines where the two suspension points are located are parallel and extend in opposite directions, then the two suspension points are determined to be offset suspension points. If a road line exists on the first side of the suspension point, the suspension point type is determined to be a dead-end suspension point, wherein the road line where the suspension point is located is located on the second side of the suspension point, and the first side and the second side are arranged opposite to each other; A suspension point is defined as a point where the direction vectors of the road lines containing at least two suspension points coincide and the corresponding matching paths coincide. If the angle between the extension direction of the road line where the suspension point is located and the matching path is within the second angle range, and there is no road line passing through the first road node in the extension direction of the suspension point, the suspension point is determined to be a T-shaped suspension point, wherein the first road node is the road node at the other end of the road line where the suspension point is located. When the angle between the extension direction of the road line where the suspension point is located and the matching path is within the third angle range, and the second road node at the other end of the road line where the suspension point is located is located on the first road line, the suspension point is determined to be a protruding suspension point, wherein the extension direction of the first road line is parallel to the extension direction of the road line where the suspension point is located.

11. An apparatus for removing suspension points from road data, characterized in that, include: The first determining module is used to determine a first set of suspension points based on the acquired first road data; wherein the first set of suspension points includes multiple suspension points; The second determining module is used to determine the matching path of the suspension point based on a heuristic search algorithm, wherein the matching path is the path with the smallest distance between the road where the suspension point is located and the neighboring points or lines of the suspension point and the path with the road where the suspension point is located, and the angle between the road and the road is located is within a first angle range. The processing module is used to process the suspension points and / or the matching path according to the spatial position relationship of the suspension points, and remove the suspension points; The processing module includes: The fifth determining submodule is used to determine the suspension point type of the suspension point based on the spatial positional relationship of the suspension points; The processing submodule is used to process the dangling point and / or the matching path according to the dangling point type, and remove the dangling point; Specifically, the processing submodule is used for at least one of the following: If the suspension point is an offset suspension point, move the two offset suspension points to the midpoint of the line connecting the two offset suspension points, and adjust the road line where the two offset suspension points are located accordingly. If the suspension point is a dead-end suspension point, delete the suspension point and set the intersection of the matching path of the suspension point and the neighboring line of the suspension point as a road node; If the suspension point is a broken suspension point, retain the matching path of the suspension point and delete the suspension point; If the suspension point is a T-shaped suspension point, delete the suspension point, the matching path corresponding to the suspension point, the road line where the suspension point is located, and the road node at the other end of the road line; If the suspension point is a prominent suspension point, delete the suspension point, the matching path corresponding to the suspension point, and the road line where the suspension point is located, while retaining the road node at the other end of the road line.

12. A device for removing suspension points from road data, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method for removing slack points from road data as claimed in any one of claims 1 to 10.

13. A readable storage medium, characterized in that, The readable storage medium stores a program that, when executed by a processor, implements the steps of the method for removing slack points from road data as described in any one of claims 1 to 10.

Images