CN112964264B - Road edge detection method, device, high-precision map, vehicle and storage medium - Google Patents
Road edge detection method, device, high-precision map, vehicle and storage medium Download PDFInfo
- Publication number
- CN112964264B CN112964264B CN202110176657.3A CN202110176657A CN112964264B CN 112964264 B CN112964264 B CN 112964264B CN 202110176657 A CN202110176657 A CN 202110176657A CN 112964264 B CN112964264 B CN 112964264B
- Authority
- CN
- China
- Prior art keywords
- road
- point
- point cloud
- points
- road edge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000003708 edge detection Methods 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 65
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000005520 cutting process Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004387 environmental modeling Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The present disclosure provides a road edge detection method, apparatus, high-precision map, vehicle, and storage medium, the road edge detection method including: dividing the obtained point cloud map to obtain a plurality of point cloud subgraphs; extracting a road edge seed point of each point cloud subgraph based on each point cloud subgraph; detecting road edge points by using a normal vector and a region growing clustering method based on each seed point; and splicing the detected road edge points to obtain a road boundary line. The method and the device can improve the detection precision of the road edge.
Description
Technical Field
The present disclosure relates to the field of vehicle navigation technology and autopilot technology, and in particular, to a road edge detection method, apparatus, high-precision map, vehicle, and storage medium.
Background
Traditional navigation maps cannot meet the need of automatic driving due to insufficient precision. High-definition maps are becoming industry consensus as a necessary ring in unmanned operation, and have advantages such as high accuracy and multiple dimensions. The high-definition map can provide more prospective information indication and information redundancy for the driving system, and realize matching and positioning of the automobile, so that the driving system can sense a larger range of traffic situation, and the safety of automatic driving is ensured.
Among the high-definition maps, the point cloud map is favored by the industry of automatic driving because of the advantages of being not influenced by environmental illumination, being accurate in environmental modeling and the like. The part of decision making and planning is a ring of road semantic map construction, and information such as each lane, road boundary and the like needs to be detected, so that unmanned vehicles are assisted to make decisions and run on correct roads.
However, in the prior art, the method for detecting the road edge (such as the vision-based method) is easily blocked by the vehicle, resulting in errors in the detected road edge.
Disclosure of Invention
Because the methods used in the prior art to detect road edges (such as vision-based methods) are subject to vehicle occlusion, errors in the detected road edges are caused. Accordingly, embodiments of the present disclosure provide at least a road edge detection method, apparatus, high-precision map, vehicle, and computer-readable storage medium to improve the detection precision of road edges.
In a first aspect, an embodiment of the present disclosure provides a road edge detection method, including:
dividing the obtained point cloud map to obtain a plurality of point cloud subgraphs;
Extracting a road edge seed point of each point cloud subgraph based on each point cloud subgraph;
detecting road edge points by using a normal vector and a region growing clustering method based on each road edge seed point;
and splicing the detected road edge points to obtain a road boundary line.
In the embodiment of the disclosure, the point cloud map is segmented into a plurality of point cloud subgraphs, the road edge seed points of each point cloud subgraph are extracted, then the road edge points are detected by using a normal vector and an area growth clustering method based on each seed point, and finally the edge points detected by each point cloud subgraph are spliced to obtain the road boundary line, so that complete road edge point cloud can be obtained, and the accuracy and the robustness of road edge detection are improved.
In a possible implementation manner, the extracting, based on each point cloud sub-graph, a road edge seed point of each point cloud sub-graph includes:
searching a first seed point in a search area formed by two adjacent search directions; the searching direction is the direction of outward radiation by taking the center point of the point cloud subgraph as a starting point.
And extracting the first seed points as road edge seed points of each point cloud subgraph.
In the embodiment of the disclosure, the center point of each point cloud sub-graph is used as a basis, and the radial directions are used for searching in the directions away from the center point, so that a large number of widely distributed road edge seed points can be obtained.
In a possible implementation manner, the searching the first seed point in the search area formed by two adjacent search directions includes:
and searching the first seed point according to a search interval in the search area.
In one possible implementation manner, the first seed point is a point in a search interval with a larger average value of the heights of the point clouds in two adjacent search intervals.
In a possible implementation manner, the method for detecting the road edge point by using the normal vector and the region growing cluster based on each seed point includes:
and detecting the road edge points by using a normal vector of the ground and a normal vector of points with a distance smaller than a preset distance between each seed point based on each seed point and using a region growing clustering method.
In the embodiment of the disclosure, the area growth clustering is performed by the normal vector of the ground and the normal vector of the point with the distance smaller than the preset distance from each seed point, so that the detection precision of the road edge point can be ensured, and other points (such as the point parallel to the ground on the road edge) outside the road edge are prevented from being detected.
In a possible implementation manner, the detecting the road edge point by using a normal vector of the ground and a normal vector of a point with a distance between each seed point being smaller than a preset distance according to the first aspect in a region growing clustering method based on each seed point includes:
calculating normal vectors of points with the distance between the normal vectors and each seed point being smaller than a preset distance, and adding the points with the corresponding normal vectors being perpendicular to the normal vectors on the ground into a clustering result;
respectively calculating normal vectors of points with the distance between each point and the clustering result being smaller than the preset distance, and adding points with the normal vector corresponding to each point being perpendicular to the normal vector of the ground into the clustering result until no new points are added into the clustering result;
and determining the points in the clustering result as the road edge points.
In a possible implementation manner, the determining the point in the cluster as the road edge point includes:
judging the height of the point cloud in each clustering result, and eliminating abnormal clustering results with the height of the point cloud being greater than the reference height;
and determining the points in other clustering results except the abnormal clustering result as the road edge points.
In the embodiment of the disclosure, by judging the height of the point cloud in each clustering result, abnormal clustering results with the height of the point cloud being greater than the reference height can be removed, further, point clouds such as static vehicles and dynamic vehicles can be removed, false detection can be avoided, and further, the detection precision and the robustness of the road edge can be further improved.
In a possible implementation manner, the splicing the edge points detected by each point cloud sub-graph to obtain the road boundary line includes:
splicing each point cloud sub-graph to obtain the road edge point cloud of the point cloud map;
and connecting the road edge point clouds to obtain the road boundary line.
In a possible implementation manner, the connecting the road edge point cloud to obtain the road boundary line includes:
selecting a road edge point close to the center of the road according to the extending track of the road, connecting the road edge point to form a road line, and removing the road edge point deviating from the straight line part in the road line;
the broken road is connected along the extending direction of the road along the line, thereby forming the road boundary line.
In the embodiment of the disclosure, the part of the road edge point cloud broken due to the shielding of the vehicle can be connected to form the finished road boundary line, and in the splicing process, the road edge points deviating from the straight line part in the road line are removed, so that the finally obtained road boundary line is accurate.
In a possible implementation manner, the splitting the acquired point cloud map to obtain a plurality of point cloud subgraphs includes:
dividing the obtained point cloud map about the road along a preset direction to obtain a plurality of point cloud subgraphs; the included angle between the preset direction and the specific direction is smaller than the preset included angle; the specific direction is perpendicular to the extending direction of the road.
In the embodiment of the disclosure, the point cloud map is segmented according to the method, so that the subsequent extraction of seed points and the detection of road edge points are facilitated.
In a possible implementation manner of the first aspect, before the segmenting the obtained point cloud map about the road along the preset direction, the method further includes:
determining a plurality of mutually parallel pre-cutting lines according to the placement mode of the point cloud map;
Determining the intersection point of each cutting line and two edges of the road, and determining the center point of a line segment formed by the intersection point according to the intersection point;
and determining the extending direction formed by connecting lines of a plurality of the center points as the extending direction of the road.
In a second aspect, an embodiment of the present disclosure provides a road edge detection apparatus, including:
the segmentation module is used for segmenting the acquired point cloud map to acquire a plurality of point cloud subgraphs;
the extraction module is used for extracting the road edge seed points of each point cloud subgraph based on each point cloud subgraph;
the detection module is used for detecting road edge points based on each seed point by using a normal vector and a region growing clustering method;
and the splicing module is used for splicing the edge points of each detected point cloud subgraph to obtain a road boundary line.
According to a second aspect, in one possible implementation manner, the extracting module is specifically configured to:
based on the central point of each point cloud sub-graph, searching in a plurality of radial directions to a direction away from the central point, and further extracting the road edge seed point of each point cloud sub-graph.
According to a second aspect, in one possible implementation manner, the extracting module is specifically configured to:
and in each searching direction, searching in a direction away from the central point by taking the central point of each point cloud subgraph as a basis and using a preset step length and a preset angle.
According to a second aspect, in a possible implementation manner, in each search direction, a plurality of search intervals are formed by the preset step size and the preset angle, and the areas of the plurality of search intervals gradually increase along a direction away from the center point; the extraction module is specifically used for:
and when the absolute value of the difference value of the height mean values of the point clouds of the two adjacent search intervals is larger than the first threshold value and smaller than the second threshold value, extracting the points in the search interval with the larger height mean value as the seed points.
According to a second aspect, in one possible implementation manner, the detection module is specifically configured to:
and detecting the road edge points by using a normal vector of the ground and a normal vector of points with a distance smaller than a preset distance between each seed point based on each seed point and using a region growing clustering method.
According to a second aspect, in one possible implementation manner, the detection module is specifically configured to:
Calculating normal vectors of points with the distance between the normal vectors and each seed point being smaller than a preset distance, and adding the points with the corresponding normal vectors being perpendicular to the normal vectors on the ground into a clustering result;
respectively calculating normal vectors of points with the distance between each point in the clustering result being smaller than the preset distance, and adding the corresponding normal vector and the point perpendicular to the ground normal vector into the clustering result until no new point is added into the clustering result;
and determining the points in the clustering result as the road edge points.
According to a second aspect, in one possible implementation manner, the detection module is specifically configured to:
judging the height of the point cloud in each clustering result, and eliminating abnormal clustering results with the height of the point cloud being greater than the reference height;
and determining the points in other clustering results except the abnormal clustering result as the road edge points.
According to a second aspect, in one possible implementation manner, the splicing module is specifically configured to:
splicing each point cloud sub-graph to obtain the road edge point cloud of the point cloud map;
and connecting the road edge point clouds to obtain the road boundary line.
According to a second aspect, in one possible implementation manner, the splicing module is specifically configured to:
Selecting a road edge point close to the center of the road according to the extending track of the road, connecting the road edge point to form a road line, and removing the road edge point deviating from the straight line part in the road line;
the broken road is connected along the extending direction of the road along the line, thereby forming the road boundary line.
According to a second aspect, in one possible implementation manner, the segmentation module is specifically configured to:
dividing the obtained point cloud map about the road along a preset direction to obtain a plurality of point cloud subgraphs; the included angle between the preset direction and the specific direction is smaller than the preset included angle; the specific direction is perpendicular to the extending direction of the road.
According to a second aspect, in one possible implementation manner, the segmentation module is specifically configured to:
determining a plurality of mutually parallel pre-cutting lines according to the placement mode of the point cloud map;
determining the intersection point of each cutting line and two edges of the road, and determining the center point of a line segment formed by the intersection point according to the intersection point;
determining an extending direction formed by connecting lines of the plurality of center points as the extending direction of the road
In a third aspect, embodiments of the present disclosure provide a high-precision map comprising a plurality of roads, each road comprising a road boundary line, the road boundary line being obtained by the method of the first aspect and any of the possible implementations of the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a vehicle comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication over the bus when the vehicle is running, the machine-readable instructions when executed by the processor performing the steps of the road edge detection method as described in the first aspect.
In a fifth aspect, embodiments of the present disclosure provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the road edge detection method according to the first aspect.
According to the method and the related device, the point cloud map is divided into a plurality of point cloud subgraphs, the road edge seed points of each point cloud subgraph are extracted, the road edge points are detected by using a normal vector and an area growth clustering method based on each seed point, and finally the edge points detected by each point cloud subgraph are spliced to obtain the road boundary line, so that complete road edge point cloud can be obtained, and the accuracy and the robustness of road edge detection are improved.
The foregoing objects, features and advantages of the disclosure will be more readily apparent from the following detailed description of the preferred embodiments taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the embodiments are briefly described below, which are incorporated in and constitute a part of the specification, these drawings showing embodiments consistent with the present disclosure and together with the description serve to illustrate the technical solutions of the present disclosure. It is to be understood that the following drawings illustrate only certain embodiments of the present disclosure and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may admit to other equally relevant drawings without inventive effort.
FIG. 1 illustrates a flow chart of a method of road edge detection provided by an embodiment of the present disclosure;
FIG. 2 illustrates a segmentation schematic of a point cloud map for roads according to an embodiment of the present disclosure;
FIG. 3 illustrates a perspective view of a navigational mapping vehicle provided by an embodiment of the present disclosure;
FIG. 4 illustrates a search schematic of a first seed point on a search area provided by an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of searching a road edge seed point in a plurality of search areas in a point cloud subgraph according to an embodiment of the present disclosure;
FIG. 6 illustrates a flowchart of a method for obtaining a point cloud map provided by an embodiment of the present disclosure;
FIG. 7 illustrates a flow chart of a method of detecting road edge points provided by an embodiment of the present disclosure;
FIG. 8 shows a schematic diagram of a clustering process based on seed points provided by an embodiment of the present disclosure;
FIG. 9 shows a flowchart of a method for stitching road boundary lines according to a curbside point cloud, provided by an embodiment of the present disclosure;
fig. 10 is a schematic structural diagram of a road edge detection device according to an embodiment of the disclosure;
fig. 11 shows a schematic structural view of a vehicle provided in an embodiment of the present disclosure.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. The components of the embodiments of the present disclosure, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure, as claimed, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be made by those skilled in the art based on the embodiments of this disclosure without making any inventive effort, are intended to be within the scope of this disclosure.
In recent years, with the great increase in the number of automobiles, many cities face increasingly serious road traffic problems, and unmanned driving has received more and more attention. The unmanned vehicle mainly comprises three parts of environment perception, path planning and decision control, wherein the environment perception is the basis of the path planning and the decision control, and the road environment detection is an important link in an environment perception system, so that the road environment detection plays a vital role in the overall performance of the unmanned vehicle.
According to research, the traditional navigation map cannot meet the requirement of automatic driving due to insufficient precision. High-definition maps are becoming industry consensus as a necessary ring in unmanned operation, and have advantages such as high accuracy and multiple dimensions. The high-definition map can provide more prospective information indication for the driving system, and realize matching and positioning of the automobile, so that the driving system can sense a larger range of traffic situation, and the safety of automatic driving is ensured.
Among the high-definition maps, the point cloud map is favored by the industry of automatic driving because of the advantages of being not influenced by environmental illumination, being accurate in environmental modeling and the like. The essential part of decision making and planning is the semantic map construction of the road, and the information of each lane, road boundary and the like needs to be detected to assist the unmanned vehicle to make decisions and drive on the correct road.
However, in the prior art, the method for detecting the edge of the road (such as the vision-based method) is easily blocked by the vehicle, so that the detected edge of the road has errors. Therefore, how to improve the detection accuracy of the road edge to ensure the safety of vehicle driving is a technical problem to be solved by the present disclosure.
Based on the above study, the present disclosure provides a road edge detection method, which segments an obtained point cloud map to obtain a plurality of point cloud subgraphs; extracting the road edge seed points of each point cloud subgraph; detecting road edge points by using a normal vector and a region growing clustering method based on each seed point; and splicing the edge points detected by each point cloud subgraph to obtain a road boundary line. The road edge detection method can improve the detection precision and the robustness of the road edge.
The present invention is directed to a method for manufacturing a semiconductor device, and a semiconductor device manufactured by the method.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The term "and/or" is used herein to describe only one relationship, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
In order to facilitate understanding of embodiments of the present application, a detailed description of aspects of the present application will be provided below in conjunction with specific embodiments. Referring to fig. 1, a flowchart of a road edge detection method according to an embodiment of the disclosure includes the following steps S101 to S104:
s101, segmenting the obtained point cloud map to obtain a plurality of point cloud subgraphs.
For example, referring to fig. 2, the acquired point cloud map about the road is segmented along a preset direction x3 to obtain a plurality of point cloud subgraphs. That is, the point cloud map may be split multiple times along a preset direction, so that multiple point cloud subgraphs may be obtained. Wherein the plurality may be two, three, five or more, and is not limited herein. The included angle θ between the preset direction x3 and the specific direction x2 is smaller than the preset included angle, and the specific direction x2 is perpendicular to the extending direction x1 of the road.
It will be appreciated that since the direction of extension of the road may not be a straight line, the specific direction x2 is perpendicular to the direction of extension x1 of the road, and that the specific direction x2 is perpendicular to the direction of extension of some small portion of the direction of extension of the road (which small portion may be considered approximately a straight line). When the included angle θ is larger and larger, the preset direction is closer to the extending direction x1 of the road, which is unfavorable for the segmentation of the map, so that the included angle θ needs to be smaller than the preset included angle, so that the segmented point cloud subgraph is favorable for the subsequent extraction of the road seed points.
In some embodiments, referring to fig. 2, before cutting the point cloud map, a plurality of pre-cut lines L may be determined according to a placement manner of the point cloud map. For example, if the point cloud map is placed horizontally, then the cut is made vertically; and if the point cloud map is placed vertically, transversely cutting. Wherein the plurality of pre-cut lines may be a set of pre-cut lines that are parallel to each other.
Then, determining intersection points D1 and D2 of each cutting line L and two edges of the road, and determining a center point DC of a line segment formed by the intersection points according to the intersection points; an extending direction formed by connecting lines of the plurality of center points DC is determined as an extending direction of the road.
Referring to fig. 3, a side view of a vehicle 100 for acquiring a point cloud map according to an embodiment of the present disclosure is shown. Wherein the vehicle 100 is a navigational map vehicle. That is, when the vehicle 100 is traveling on the road, a point cloud map related to the surrounding environment may be acquired.
Illustratively, the vehicle 100 includes an image acquisition unit 10, a global satellite navigation (GNSS) unit 20, a point cloud data acquisition unit 30, a vehicle wheel speed meter unit 40, and a multi-sensor data time synchronization unit 50.
The image acquisition unit 10 is used for acquiring a plurality of images related to the surrounding environment. For example, the image pickup unit 10 may include a plurality of monocular cameras, which may be disposed outside the vehicle 100 (e.g., in front of the upper surface of the vehicle).
The GNSS unit 20 is configured to provide positioning data of the vehicle 100. For example, the GNSS unit 20 may be a dual antenna GNSS signal receiving module that may be mounted in the middle of the upper surface of the vehicle 100.
The point cloud data acquisition unit 30 is configured to acquire a point cloud map related to the surrounding environment. For example, the point cloud data acquisition unit 30 may comprise a lidar (e.g., a tilted multi-line lidar). Lidar is used to transmit a first laser beam to the surrounding environment and to receive a second laser beam reflected by objects in the environment (e.g., buildings, traffic lights, traffic signs, vehicles, pedestrians, roadway partitions, roads, etc.).
The vehicle wheel speed meter unit 40 for providing wheel speed data may be installed near the wheels, for example, near the rear wheels.
The multi-sensor data time synchronization unit 50 is coupled to the image acquisition unit 10, the GNSS unit 20, the point cloud data acquisition unit 30, and the vehicle wheel speed meter unit 40, and is configured to synchronize data acquired by the image acquisition unit 10, the GNSS unit 20, the point cloud data acquisition unit 30, and the vehicle wheel speed meter unit 40, and may be disposed on a side of the vehicle 100.
It will be appreciated that the vehicle 100 also includes a processor (not shown in fig. 2) that may be electrically connected to the various units described above and that performs a corresponding method, such as a road edge detection method in embodiments of the present disclosure, based on the data obtained by the various units described above.
S102, extracting the road edge seed points of each point cloud subgraph based on each point cloud subgraph.
For example, a first seed point may be searched in a search area composed of two adjacent search directions, and the first seed point may be extracted as a road edge seed point of each of the point cloud subgraphs. The searching direction is the direction of outward radiation by taking the center point of the point cloud subgraph as a starting point.
It will be appreciated that since the road edge will be higher than the road, when searching on each search area, a location with a significant change in height is found, it can be determined to be the road edge. Therefore, in order to distinguish the road heights in each search area, the search areas need to be divided into sections along the search direction, and then a position with a higher height needs to be found.
Referring to fig. 4, a first seed point may be searched in a search area formed of two adjacent search directions L1 and L2. In this embodiment, the included angle a between the adjacent search directions L1 and L2 is smaller than the preset angle. Specifically, the first seed point may be searched for in the search area formed of L1 and L2 according to the search interval k. The search interval k is an area formed in the search area according to a preset step length s in the direction away from the center point C. In this way, a plurality of search intervals k1 to kn may be formed in the search direction within the search area, and the areas of the plurality of search intervals (fan-shaped intervals in fig. 4) gradually increase in a direction away from the center point C. Therefore, when the height average value of the point clouds of two adjacent search intervals k changes, the interval with higher height average value can be determined as the road edge seed point.
In this embodiment, the preset step s is 0.1m and the preset angle a is 1 °. It can be appreciated that too small a step increases the amount of computation and is susceptible to noise; if the step length is too large, the average height is not distinguished obviously (the differentiation is not obvious), and the road edge is not easy to find, so the preset step length and the preset angle can be set specifically according to the actual situation, and the method is not limited.
It should be noted that, in general, the road edge is about 10cm higher than the road surface, and if the difference of the height differences is too large, it is indicated that the search area can be an obstacle or a stationary vehicle, so in this embodiment, the absolute value of the difference of the height average value is limited to be smaller than the second threshold value, so that the extraction accuracy of the seed point can be ensured. For example, the first threshold may be 0.05m and the second threshold may be 0.2m. Of course, in other embodiments, the first threshold value and the second threshold value may also be other values, which are not limited herein.
Thus, in the embodiment of the disclosure, the first seed point is a point in a search interval with a larger average value of the heights of the point clouds in two adjacent search intervals, and the absolute value of the difference between the average values of the heights of the point clouds in the two adjacent search intervals is greater than a first threshold and less than a second threshold.
Referring to fig. 5, in order to improve the search coverage of the road edge seed point, the road edge seed point d may be searched radially outwards based on the center point C of the single point cloud sub-image T, and the search areas y1 to yn in a plurality of different directions may be searched in a direction away from the center point C, that is, based on the center point C of the point cloud sub-image T. In the present embodiment, the search is performed in the directions away from the center point C by using 8 search areas in different directions, but it is to be understood that the search may be performed in more or less search areas in other embodiments, and the present invention is not limited thereto.
S103, detecting the road edge points based on each road edge seed point by using a normal vector and a region growing clustering method.
For example, a clustering result can be obtained by using a normal vector and a region growing clustering method based on each seed point, and the points in the clustering result are taken as the road edge points.
And S104, splicing the detected road edge points to obtain a road boundary line.
And splicing the edge points determined by each point cloud subgraph to obtain a complete road boundary line.
In the embodiment of the disclosure, the acquired point cloud map is segmented to obtain a plurality of point cloud subgraphs, then the road edge seed points of each point cloud subgraph are extracted, then the road edge points are determined by a method of normal vector and growth area clustering based on each seed point, so that complete road edge point clouds can be obtained, and then the road edge point clouds of each point cloud subgraph are spliced to obtain complete road boundary lines, so that the accuracy and the robustness of road edge detection are improved.
The above-described S101 to S104 will be described in detail with reference to specific embodiments.
As shown in fig. 6, when the point cloud map is acquired in S101, the point cloud map includes the following S1011 to S1012:
S1011, acquiring a point cloud data frame and corresponding pose data thereof; the point cloud data frame is synchronized with the time stamp of the corresponding pose data.
Illustratively, the point cloud data frame may be acquired by the point cloud data acquisition unit 30 in fig. 3, the pose data may be acquired by the GNSS unit 20 in fig. 3, and the time stamp may be acquired by the multi-sensor data time synchronization unit 50 in fig. 3. Wherein the pose data includes position coordinate data and pose data.
And S1012, splicing the point cloud data frames together according to the pose data to obtain a point cloud map.
Because the time stamps of the pose data and the point cloud data frames are synchronous, the data frames at different time points are spliced according to the pose data (positioning information), and a point cloud map with higher precision can be obtained.
For S103 described above, when detecting a road edge point using a method of normal vector and region growing cluster based on each of the seed points, as shown in fig. 7, the following S1031 to S1033 are included:
s1031, calculating normal vectors of points with the distance between each seed point being smaller than a preset distance, and adding points with the corresponding normal vectors being perpendicular to the normal vectors of the ground into the clustering result.
Referring to fig. 8, for each seed point q, a normal vector to a point from which it is less than a preset distance (distance between q and p 1) is calculated, and points of normal phasors perpendicular to the ground are added to the cluster.
S1032, respectively calculating normal vectors of points with the distance between each point in the clustering result being smaller than the preset distance, and adding the corresponding normal vector and the points perpendicular to the ground normal vector into the clustering result until no new point is added into the clustering result.
For example, for each point in the clustering result, searching outwards by a preset distance (distance between p1 and p 2), and adding all points in the preset distance, wherein the normal phasors are perpendicular to the normal vector of the ground, into the clusters. Step S1032 is repeated until no new points join the cluster. That is, all the regions that can be connected are traversed step by step with a fixed search radius.
And S1033, determining the points in the clustering result as the road edge points.
For example, for each cluster, verifying the height of the point cloud, and eliminating the cluster result with the height higher than the reference height, for example, the point cloud of a static vehicle, a dynamic vehicle and the like can be eliminated. The reference height can be set to be 1m, so that the occurrence of the condition of error detection can be effectively avoided. Thus, in some embodiments, step S1033 may include the sub-steps of:
a) Judging the height of the point cloud in each clustering result, and eliminating abnormal clustering results with the height of the point cloud being greater than the reference height;
b) And determining the points in other clustering results except the abnormal clustering result as the road edge points.
For S104 described above, when the edge points detected by each of the point cloud subgraphs are spliced to obtain the road boundary line, as shown in fig. 9, the following S1041 to S1043 are included:
s1041, splicing each point cloud sub-graph to obtain the road edge point cloud of the point cloud map.
By way of example, the detection results of all the point cloud subgraphs are spliced to obtain a complete road edge point cloud, and then the road edge point cloud is connected to obtain a road boundary line. However, in some cases, due to some parameter settings, such as vehicle shielding, some disconnection phenomenon may exist in the extracted road edge point cloud, so in some embodiments, in order to further improve the accuracy of the road boundary line, a subsequent step needs to be performed.
S1042, selecting a road edge point close to the center of the road to be connected along the road according to the extending track of the road, and eliminating the road edge point deviating from the straight line part along the road.
For example, a road edge point near the center of the road may be selected to connect along the road according to the travel track (i.e., the road extension track) of the vehicle 100 in fig. 3, and the road edge point deviated from the straight line portion in the road may be removed. For example, the angle between the current road edge point and the straight line part in the line can be calculated, when the angle deviation exceeds 15 degrees, the current road edge point is determined to be an error point, and therefore the current road edge point needs to be removed.
And S1043, connecting the broken road along the extending direction of the road, and further forming the road boundary line.
Illustratively, connecting the broken road edges along the extending direction of the road results in a final road boundary line.
It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.
Based on the same technical concept, the embodiment of the disclosure further provides a road edge detection device corresponding to the road edge detection method, and since the principle of solving the problem by the device in the embodiment of the disclosure is similar to that of the road edge detection method in the embodiment of the disclosure, the implementation of the device can refer to the implementation of the method, and the repetition is omitted.
Referring to fig. 10, a schematic diagram of a road edge detection apparatus 500 according to an embodiment of the disclosure is provided, where the road edge detection apparatus includes:
the segmentation module 501 is configured to segment the obtained point cloud map to obtain a plurality of point cloud subgraphs;
an extracting module 502, configured to extract a road edge seed point of each point cloud sub-graph based on each point cloud sub-graph;
a detection module 503, configured to detect a road edge point based on each of the seed points by using a normal vector and a method of region growing clustering;
and the splicing module 504 is configured to splice the detected road edge points to obtain a road boundary line.
In one possible implementation, the extracting module 502 is specifically configured to:
searching a first seed point in a search area formed by two adjacent search directions; the searching direction is the direction of outward radiation by taking the central point of the point cloud subgraph as a starting point;
and extracting the first seed points as road edge seed points of each point cloud subgraph.
In one possible implementation, the extracting module 502 is specifically configured to:
and searching the first seed point according to a search interval in the search area. The search interval is an area formed in the search area according to a preset step length in the direction away from the center point.
In one possible implementation manner, the first seed point is a point in a search interval with a larger average value of the heights of the point clouds in two adjacent search intervals. Specifically, an absolute value of a difference between the height average values of the point clouds of the two adjacent search intervals is greater than a first threshold value and less than a second threshold value.
In one possible implementation, the detection module 503 is specifically configured to:
and detecting the road edge points by using a normal vector of the ground and a normal vector of points with a distance smaller than a preset distance between each seed point based on each seed point and using a region growing clustering method.
In one possible implementation, the detection module 503 is specifically configured to:
calculating normal vectors of points with the distance between the normal vectors and each seed point being smaller than a preset distance, and adding the points with the corresponding normal vectors being perpendicular to the normal vectors on the ground into a clustering result;
respectively calculating normal vectors of points with the distance between each point in the clustering result being smaller than the preset distance, and adding the corresponding normal vector and the point perpendicular to the ground normal vector into the clustering result until no new point is added into the clustering result;
and determining the points in the clustering result as the road edge points.
In one possible implementation, the detection module 503 is specifically configured to:
judging the height of the point cloud in each clustering result, and eliminating abnormal clustering results with the height of the point cloud being greater than the reference height;
and determining the points in other clustering results excluding the abnormal clustering result as the road edge points.
In one possible implementation, the stitching module 504 is specifically configured to:
splicing each point cloud sub-graph to obtain the road edge point cloud of the point cloud map;
and connecting the road edge point clouds to obtain the road boundary line.
In one possible implementation, the stitching module 504 is specifically configured to:
selecting a road edge point close to the center of the road according to the extending track of the road, connecting the road edge point to form a road line, and removing the road edge point deviating from the straight line part in the road line;
the broken road is connected along the extending direction of the road along the line, thereby forming the road boundary line.
In one possible implementation, the segmentation module 501 is specifically configured to:
dividing the obtained point cloud map about the road along a preset direction to obtain a plurality of point cloud subgraphs; the included angle between the preset direction and the specific direction is smaller than the preset included angle; the specific direction is perpendicular to the extending direction of the road.
The process flow of each module in the apparatus and the interaction flow between the modules may be described with reference to the related descriptions in the above method embodiments, which are not described in detail herein.
In an embodiment of the present disclosure, there is further provided a high-precision map including a plurality of roads, each road including a road boundary line obtained by the road edge detection method in any one of possible implementations.
Based on the same technical concept, the embodiment of the disclosure also provides a vehicle. Referring to fig. 11, a schematic structural diagram of a vehicle 700 according to an embodiment of the present disclosure includes a processor 701, a memory 702, and a bus 703. The memory 702 is configured to store execution instructions, including a memory 7021 and an external memory 7022; the memory 7021 is also referred to as an internal memory, and is used for temporarily storing operation data in the processor 701 and data exchanged with an external memory 7022 such as a hard disk, and the processor 701 exchanges data with the external memory 7022 via the memory 7021.
In the embodiment of the present application, the memory 702 is specifically configured to store application program codes for executing the solution of the present application, and the processor 701 controls the execution. That is, when the vehicle 700 is running, communication between the processor 701 and the memory 702 is through the bus 703, such that the processor 701 executes the application code stored in the memory 702, thereby performing the method in any of the foregoing embodiments.
The processor 701 may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The Memory 702 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the vehicle 700. In other embodiments of the present application, vehicle 700 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the road edge detection method in the method embodiments described above. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.
The computer program product of the road edge detection method provided in the embodiments of the present disclosure includes a computer readable storage medium storing program codes, where the instructions included in the program codes may be used to execute the steps of the road edge detection method in the above method embodiments, and specifically, reference may be made to the above method embodiments, which are not described herein.
The disclosed embodiments also provide a computer program which, when executed by a processor, implements any of the methods of the previous embodiments. The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or a part of the technical solution, or in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present disclosure, and are not intended to limit the scope of the disclosure, but the present disclosure is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, it is not limited to the disclosure: any person skilled in the art, within the technical scope of the disclosure of the present disclosure, may modify or easily conceive changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features thereof; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (15)
1. A method of road edge detection, comprising:
dividing the obtained point cloud map to obtain a plurality of point cloud subgraphs;
extracting a road edge seed point of each point cloud subgraph based on each point cloud subgraph;
detecting road edge points by using a normal vector and a region growing clustering method based on each road edge seed point;
and splicing the detected road edge points to obtain a road boundary line.
2. The method of claim 1, wherein the extracting the road edge seed points of each of the point cloud subgraphs based on each of the point cloud subgraphs comprises:
searching a first seed point in a search area formed by two adjacent search directions; the searching direction is the direction of outward radiation by taking the central point of the point cloud subgraph as a starting point;
and extracting the first seed points as road edge seed points of each point cloud subgraph.
3. The method of claim 2, wherein searching for the first seed point in a search area comprised of two adjacent search directions comprises:
and searching the first seed point according to a search interval in the search area.
4. A method according to claim 3, wherein the first seed point is a point in a search interval in which the mean value of the height of the point cloud is large, in two adjacent search intervals.
5. The method of any one of claims 1-4, wherein detecting road edge points using normal vector and region growing clustering based on each of the road edge seed points comprises:
and detecting the road edge points by using a normal vector of the ground and a normal vector of points with a distance smaller than a preset distance between each seed point based on each seed point and using a region growing clustering method.
6. The method of claim 5, wherein the detecting the road edge points in a region growing cluster method using a normal vector of the ground and a normal vector of points having a distance from each of the seed points less than a preset distance based on each of the seed points comprises:
calculating normal vectors of points with the distance between the normal vectors and each seed point being smaller than a preset distance, and adding points with the normal vector corresponding to each point being perpendicular to the normal vector of the ground into a clustering result;
respectively calculating normal vectors of points with the distance between each point in the clustering result being smaller than the preset distance, and adding the corresponding normal vector and the point perpendicular to the ground normal vector into the clustering result until no new point is added into the clustering result;
And determining the points in the clustering result as the road edge points.
7. The method of claim 6, wherein the determining the point in the cluster as the road edge point comprises:
judging the height of the point cloud in each clustering result, and eliminating abnormal clustering results with the height of the point cloud being greater than the reference height;
and determining the points in other clustering results excluding the abnormal clustering result as the road edge points.
8. The method according to any one of claims 1-4, wherein said stitching the detected road edge points to obtain a road boundary line comprises:
splicing each point cloud sub-graph to obtain the road edge point cloud of the point cloud map;
and connecting the road edge point clouds to obtain the road boundary line.
9. The method of claim 8, wherein the connecting the road edge point cloud to obtain the road boundary line comprises:
selecting a road edge point close to the center of the road according to the extending track of the road, connecting the road edge point to form a road line, and removing the road edge point deviating from the straight line part in the road line;
The broken road is connected along the extending direction of the road along the line, thereby forming the road boundary line.
10. The method according to any one of claims 1-4, wherein the segmenting the obtained point cloud map to obtain a plurality of point cloud subgraphs includes:
dividing the obtained point cloud map about the road along a preset direction to obtain a plurality of point cloud subgraphs; the included angle between the preset direction and the specific direction is smaller than the preset included angle; the specific direction is perpendicular to the extending direction of the road.
11. The method according to claim 10, wherein before the segmenting the obtained point cloud map about the road along the preset direction, further comprises:
determining a plurality of pre-cutting lines according to the placement mode of the point cloud map;
determining the intersection point of each cutting line and two edges of the road, and determining the center point of a line segment formed by the intersection point according to the intersection point;
and determining the extending direction formed by connecting lines of a plurality of the center points as the extending direction of the road.
12. A road edge detection apparatus, comprising:
the segmentation module is used for segmenting the acquired point cloud map to acquire a plurality of point cloud subgraphs;
The extraction module is used for extracting the road edge seed points of each point cloud subgraph;
the detection module is used for detecting road edge points based on each seed point by using a normal vector and a region growing clustering method;
and the splicing module is used for splicing the edge points detected by each point cloud subgraph to obtain a road boundary line.
13. A high precision map comprising a plurality of roads, each road comprising a road boundary line, said road boundary line being obtained by the method of any of claims 1-11.
14. A vehicle, characterized by comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor in communication with said memory via the bus when the vehicle is in motion, said machine readable instructions when executed by said processor performing the steps of the road edge detection method according to any one of claims 1-11.
15. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the road edge detection method according to any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110176657.3A CN112964264B (en) | 2021-02-07 | 2021-02-07 | Road edge detection method, device, high-precision map, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110176657.3A CN112964264B (en) | 2021-02-07 | 2021-02-07 | Road edge detection method, device, high-precision map, vehicle and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112964264A CN112964264A (en) | 2021-06-15 |
| CN112964264B true CN112964264B (en) | 2024-03-26 |
Family
ID=76284426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110176657.3A Active CN112964264B (en) | 2021-02-07 | 2021-02-07 | Road edge detection method, device, high-precision map, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112964264B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806464A (en) * | 2021-09-18 | 2021-12-17 | 北京京东乾石科技有限公司 | Road tooth determining method, device, equipment and storage medium |
| CN115248447B (en) * | 2021-09-29 | 2023-06-02 | 上海仙途智能科技有限公司 | Laser point cloud-based path edge identification method and system |
| CN114049327B (en) * | 2021-11-16 | 2022-05-20 | 中国测绘科学研究院 | Improved large-range road center line block extraction algorithm |
| CN115248448B (en) * | 2022-09-22 | 2022-12-16 | 毫末智行科技有限公司 | Laser radar-based road edge detection method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260699A (en) * | 2015-09-10 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | Lane line data processing method and lane line data processing device |
| CN110569704A (en) * | 2019-05-11 | 2019-12-13 | 北京工业大学 | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| KR20200065590A (en) * | 2018-11-30 | 2020-06-09 | 웨이즈원 주식회사 | Method and apparatus for detecting lane center point for accurate road map |
| CN111551958A (en) * | 2020-04-28 | 2020-08-18 | 北京踏歌智行科技有限公司 | Mining area unmanned high-precision map manufacturing method |
| CN111771206A (en) * | 2019-01-30 | 2020-10-13 | 百度时代网络技术（北京）有限公司 | Map zoning system for autonomous vehicles |
| CN112013831A (en) * | 2020-09-09 | 2020-12-01 | 北京易控智驾科技有限公司 | Map boundary automatic extraction method and device based on terrain analysis |
| CN112036274A (en) * | 2020-08-19 | 2020-12-04 | 江苏智能网联汽车创新中心有限公司 | Driving region detection method and device, electronic equipment and storage medium |
-
2021
- 2021-02-07 CN CN202110176657.3A patent/CN112964264B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260699A (en) * | 2015-09-10 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | Lane line data processing method and lane line data processing device |
| KR20200065590A (en) * | 2018-11-30 | 2020-06-09 | 웨이즈원 주식회사 | Method and apparatus for detecting lane center point for accurate road map |
| CN111771206A (en) * | 2019-01-30 | 2020-10-13 | 百度时代网络技术（北京）有限公司 | Map zoning system for autonomous vehicles |
| CN110569704A (en) * | 2019-05-11 | 2019-12-13 | 北京工业大学 | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| CN111551958A (en) * | 2020-04-28 | 2020-08-18 | 北京踏歌智行科技有限公司 | Mining area unmanned high-precision map manufacturing method |
| CN112036274A (en) * | 2020-08-19 | 2020-12-04 | 江苏智能网联汽车创新中心有限公司 | Driving region detection method and device, electronic equipment and storage medium |
| CN112013831A (en) * | 2020-09-09 | 2020-12-01 | 北京易控智驾科技有限公司 | Map boundary automatic extraction method and device based on terrain analysis |
Non-Patent Citations (2)
| Title |
|---|
| 基于三维激光雷达的道路边界提取和障碍物检测算法;王灿;孔斌;杨静;王智灵;祝辉;;模式识别与人工智能(第04期);第353-362页 * |
| 基于双多线激光雷达的低矮道边检测;石庭敏等;计算机与数字工程;第45卷(第12期);第2368-2372页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112964264A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112964264B (en) | Road edge detection method, device, high-precision map, vehicle and storage medium | |
| US11781870B2 (en) | Crowd sourcing data for autonomous vehicle navigation | |
| CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
| US20200333159A1 (en) | Method and apparatus for displaying virtual route | |
| CN105667518B (en) | The method and device of lane detection | |
| US10074270B2 (en) | Clustering observations of objects along roads for navigation-related operations | |
| KR102083909B1 (en) | Automatic extraction method for lane data information for autonomous driving vehicles based on point cloud map | |
| KR102558055B1 (en) | Suboptimal estimation method | |
| CN108303103B (en) | Method and device for determining target lane | |
| US11619516B2 (en) | Method for detecting map error information, apparatus, device, vehicle and storage medium | |
| US11294392B2 (en) | Method and apparatus for determining road line | |
| WO2018133851A1 (en) | Point cloud data processing method and apparatus, and computer storage medium | |
| CN110749329B (en) | Lane level topology construction method and device based on structured road | |
| CN111537994B (en) | Unmanned mine card obstacle detection method | |
| JP2015148601A (en) | System and method for mapping, localization and pose correction | |
| US10302754B1 (en) | Object recognition device | |
| Ravi et al. | Lane width estimation in work zones using LiDAR-based mobile mapping systems | |
| CN112325896A (en) | Navigation method, navigation device, intelligent driving equipment and storage medium | |
| CN115205803A (en) | Automatic driving environment sensing method, medium and vehicle | |
| WO2018002932A1 (en) | Lane level accuracy using vision of roadway lights and particle filter | |
| CN112068155B (en) | Partition obstacle detection method based on multiple multi-line laser radars | |
| Meis et al. | A new method for robust far-distance road course estimation in advanced driver assistance systems | |
| US20210365721A1 (en) | Systems and methods for creating a parking map | |
| EP4024330B1 (en) | Object recognition method and object recognition device | |
| KR102255924B1 (en) | Vehicle and method for detecting lane |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |