CN110906940A - Lane sideline aggregation method based on track direction - Google Patents
Lane sideline aggregation method based on track direction Download PDFInfo
- Publication number
- CN110906940A CN110906940A CN201911026989.2A CN201911026989A CN110906940A CN 110906940 A CN110906940 A CN 110906940A CN 201911026989 A CN201911026989 A CN 201911026989A CN 110906940 A CN110906940 A CN 110906940A
- Authority
- CN
- China
- Prior art keywords
- track
- points
- point
- line
- clustering
- 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.)
- Granted
Links
Images
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 invention relates to a lane line aggregation method based on a track direction, which comprises the following steps: generating a buffer area of the track segment according to a set width by taking the track segment between two adjacent track points as a center; combining the buffers of all the track segments to generate a buffer list, judging whether track points are reserved or abandoned in the buffer list according to whether the track points are in the buffer list, and generating a reference track according to all the reserved track points; and extending the track points in the reference track to two sides to generate scanning line segments, clustering the intersection points of the same scanning line segment and the original lane line to generate each clustering point, classifying each clustering point, and fitting into a line to obtain the aggregation result of the lane line. The tracks in the characteristic directions are extracted from a large number of tracks, so that a large number of original tracks can be prevented from participating in calculation, and the calculation efficiency is improved; and introducing the intersection point of the track scanning line and the lane sideline as a new clustering element, so that the finally generated lane shape, particularly the lane shapes of the miscellaneous line and the curve, conforms to the actual situation.
Description
Technical Field
The invention relates to the field of high-precision map generation, in particular to a lane sideline aggregation method based on a track direction.
Background
The high-precision electronic map information at least takes a lane entity as an abstract object and can describe the relationship between each data element taking a lane as a main body, and at present, in order to generate lane boundary data in a high-precision map, a large amount of lane boundary vector data uploaded from a vehicle end needs to be aggregated.
In the prior art, a method for aggregating lane sideline vector data is commonly used for aggregating line segments, but the method has poor effect on processing mixed lines and curves, and the aggregated lane line has large direction change and is not in accordance with the actual lane line shape.
Disclosure of Invention
The invention provides a method and a system for converging lane lines based on a track direction, aiming at the technical problems in the prior art, and solving the problem that the lane lines conforming to the actual shape are difficult to obtain for miscellaneous lines and curves in the prior art.
The technical scheme for solving the technical problems is as follows: a lane line aggregation method based on track direction comprises the following steps:
step 1, taking a track segment between two adjacent track points as a center, and generating a buffer area of each track segment according to a set width;
step 2, combining the buffers of the track segments to generate a buffer list, traversing all the track points, judging whether to reserve or discard the track points according to whether the track points are in the buffer list, and generating a reference track according to each reserved track point;
and 3, extending the track points in the reference track to two sides to generate scanning line segments, clustering the intersection points of the same scanning line segments and the original lane lines to generate all clustering points, classifying all the clustering points, and fitting the clustering points into a line to obtain the aggregation result of the lane lines.
The invention has the beneficial effects that: on the basis of the original lane sideline data input, the input of the trajectory line data is added, and the lane line aggregation is assisted in the trajectory direction, so that the interference in other directions is eliminated; the tracks of the characteristic directions are extracted from a large number of tracks to represent the directions of other tracks, and the finally extracted tracks are used for reference of road directions, so that a large number of original tracks can be prevented from participating in calculation, and the calculation efficiency is improved; the intersection point of a track scanning line and a lane side line is introduced as a new clustering element, the transverse distance of the scanning line is used as a characteristic, and the clustering generation of the lane line shape is realized along the track direction, so that the finally generated lane shape, particularly the lane shape of a mixed line and a curve, conforms to the actual situation.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, before the step 1 of generating the buffer area of the trajectory segment, the method further includes: performing area division on the input original lane lines and tracks;
and respectively carrying out lane line aggregation on each divided area according to the method in the step 1 to the step 3, and then combining lane lines of each divided area.
Further, the process of performing region division includes:
dividing by taking longitude and latitude as a unit, and numbering each divided area;
for any track point, when the track point and the adjacent track point are in the same divided region, reserving the serial number of the divided region where the track point is located; when the track points and any adjacent track points are not in the same divided region, reserving the serial numbers of the divided regions where the track points are located and adjacent to the track points;
for any original lane line, when the original lane line is in one divided region, the serial number of the divided region where the original lane line is located is reserved; and when the original lane line crosses the region, reserving the serial numbers of the divided regions where the original lane line is positioned.
Further, the process of merging the lane lines of the respective divided regions includes: and traversing the starting point and the end point of the lane line of each divided area boundary, and connecting the two lane lines together when finding points with similar distance and angle from the starting point and the end point of the lane line adjacent to the divided area.
Further, the buffer area of the track line segment generated in step 1 is a quadrangle which takes the track line segment as a central line, has a set width and has a length equal to that of the track line segment.
Further, the process of traversing all the trace points in step 2 includes:
and traversing the trace points according to the time sequence, discarding the trace points if the trace points are in the buffer area list, and adding the buffer area of the trace line segment consisting of the trace points and the previous trace points into the buffer area list if the trace points are not in the buffer area list.
Further, whether any of the track points is in the buffer list is judged to include: traversing the buffer area list, and judging whether the track point is in the range of any buffer area and whether the direction of the track point is consistent with that of the buffer area; the direction of the track point is the direction from the previous track point of the track point to the track line segment of the track point; the direction of the buffer area is consistent with the direction of the track.
Further, judging whether the track point is in the range of any buffer area comprises the following steps: making rays in any direction perpendicular to the track direction from the track points, and if the number of intersection points of the rays and the buffer area is an odd number, judging that the track points are in the buffer area; and if the intersection point number of the ray and the buffer area is an even number, judging that the track point is outside the buffer area.
Further, the process of generating each cluster point in step 3 includes: and judging whether the number of the intersection points of the scanning line segments and the original lane lines exceeds a set number, if so, clustering the intersection points by adopting a MeanShift clustering method, and if not, clustering the intersection points by using a DBSCAN clustering method.
Further, the process of classifying each cluster point in step 3 includes:
and classifying the clustering points with transverse distance variation smaller than a set distance threshold into one class along the direction of the reference track, wherein the transverse distance is the distance between the clustering points and the starting points of the scanning line segments.
The beneficial effect of adopting the further scheme is that:
the method comprises the steps of performing region division on input original lane lines and tracks, respectively aggregating the lane lines according to each divided region, combining the lane lines of each divided region, limiting calculation in each divided region, reducing calculation amount and memory use, facilitating parallel calculation of each region and improving performance.
By judging the number of the intersection points of the scanning line segments and the original lane lines and selecting different clustering methods according to the set number, the performance and the accuracy can be considered.
Drawings
Fig. 1 is a flowchart of a lane line aggregation method based on a track direction according to the present invention;
FIG. 2 is a flowchart of an embodiment of a lane line aggregation method based on track direction according to the present invention;
FIG. 3 is a schematic diagram of partitioned traces according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a buffer list according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an intersection point and a cluster point provided in an embodiment of the present invention;
FIG. 6 is a schematic diagram of generating a fit line according to an embodiment of the present invention;
FIG. 7 is a diagram illustrating the effect of removing the parasitic wires according to the embodiment of the present invention;
fig. 8 is a diagram illustrating an effect of generating a miscellaneous curve according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a flowchart of a lane line aggregation method based on a track direction according to the present invention is shown in fig. 1, and the method includes:
step 1, taking a track segment between two adjacent track points as a center, and generating a buffer area of each track segment according to a set width.
The track is composed of a plurality of time-continuous track points, every two continuous track points can be connected into line segments, and the track can be regarded as a collection of the line segments.
And 2, combining the buffers of each track segment to generate a buffer list, traversing all track points, judging whether to reserve or discard the track points according to whether the track points are in the buffer list, and generating a reference track according to each reserved track point.
The buffers formed by the track line segments are combined together to form a buffer list.
And 3, extending the track points in the reference track to two sides to generate scanning line segments, clustering the intersection points of the same scanning line segment and the original lane line to generate each clustering point, classifying each clustering point, and fitting into a line to obtain the aggregation result of the lane line.
According to the lane line aggregation method based on the track direction, provided by the invention, on the basis of the original lane sideline data input, the input of the track line data is increased, the lane line aggregation is assisted by the track direction, and the interference in other directions is eliminated; the tracks of the characteristic directions are extracted from a large number of tracks to represent the directions of other tracks, and the finally extracted tracks are used for reference of road directions, so that a large number of original tracks can be prevented from participating in calculation, and the calculation efficiency is improved; the intersection point of a track scanning line and a lane side line is introduced as a new clustering element, the transverse distance of the scanning line is used as a characteristic, and the clustering generation of the lane line shape is realized along the track direction, so that the finally generated lane shape, particularly the lane shape of a mixed line and a curve, conforms to the actual situation.
Example 1
Embodiment 1 provided by the present invention is an embodiment of a lane line aggregation method based on a track direction provided by the present invention, and as shown in fig. 2, is a flowchart of an embodiment of a lane line aggregation method based on a track direction provided by the present invention, and as can be seen from fig. 2, in this embodiment, before generating a buffer area of a track line segment, the method further includes: and carrying out region division on the input original lane lines and tracks, respectively aggregating the lane lines according to each divided region, and then combining the lane lines of each divided region.
Specifically, the process of dividing the region includes: and dividing the areas by taking longitude and latitude as a unit, and numbering each divided area.
For any track point, when the track point and the adjacent track point are in the same divided area, the serial number of the divided area where the track point is located is reserved; and when the track point and any adjacent track point are not in the same divided region, reserving the serial numbers of the track point and the adjacent divided region. For any original lane line, when the original lane line is in a divided area, the serial number of the divided area where the original lane line is located is reserved; when the original lane line crosses the region, the serial numbers of each divided region where the original lane line is located are reserved. The connection of multiple divided areas is convenient to be made at last.
Specifically, when dividing by taking longitude and latitude as a unit, dividing 180 degrees into halves for 13 times to obtain the range of a single divided area, namely the longitude and latitude range of the single divided range is 180 degrees/2130.02197265625. In the middle region of China with a latitude of 30 degrees, the actual width of the region is 2108 meters. According to the mode of dividing the region, the whole world can be divided into 213*214And each of the fixed regions may be combined into a region number based on the longitude-direction number and the latitude-direction number.
The process of merging the lane lines of each divided area includes: and traversing the starting point and the end point of the lane line of each divided area boundary, and connecting the two lane lines together when finding points with similar distance and angle from the starting point and the end point of the lane line of the adjacent divided areas.
As shown in fig. 3, which is a schematic diagram of a partitioned track according to an embodiment of the present invention, after region partitioning, calculation may be limited to a region, so as to reduce the calculation amount and memory usage, facilitate parallel calculation of each region, and improve performance.
After the area division is carried out, the process of carrying out lane line aggregation on any divided area comprises the following steps:
step 1, generating a buffer area of each track segment according to a set width by taking the track segment between two adjacent track points as a reference.
Specifically, the buffer area of the generated track line segment is a quadrangle which takes the track line segment as a central line, has a set width and has the same length as the track line segment.
The attributes of the buffer area of the track line segment comprise the positions of four vertexes of the quadrangle and the direction of the buffer area, and the direction of the buffer area is consistent with the direction of the track.
And 2, combining the buffers of each track segment to generate a buffer list, traversing all track points, selectively reserving or discarding the track points according to whether the track points are in the buffer list, and generating a reference track according to each reserved track point.
Specifically, as shown in fig. 4, which is a schematic diagram of a buffer list provided in the embodiment of the present invention, the process of traversing all trace points in step 2 includes: and traversing the track points according to the time sequence, discarding the track points if the track points are in the buffer area list, and adding the buffer area of the track line segment consisting of the track points and the previous track points into the buffer area list if the track points are not in the buffer area list.
Judging whether any track point is included in the buffer area list or not: and traversing the buffer area list, and judging whether the track point is in any buffer area range and whether the direction of the track point is consistent with that of the buffer area. And the direction of the track point is the direction from the previous track point of the track point to the track line segment of the track point.
Trace points that are close in location but different in direction are also considered not to be in the buffer list.
Specifically, a horizontal cross point number discrimination method can be adopted to judge whether the track point is in the range of the polygon buffer area: making rays in any direction perpendicular to the track direction from the track point, and if the number of intersection points of the rays and the polygonal buffer area is an odd number, judging that the track point is in the polygonal buffer area; and if the number of the intersection points of the rays and the polygonal buffer area is even, judging that the track point is outside the polygonal buffer area.
In the execution process of the step 2, the traversed track points are discarded if the traversed track points are in the buffer area list, the finally reserved track points are the track points for generating the buffer area list, the reserved track points form a reference track, a large number of original tracks can be prevented from participating in calculation, and the calculation efficiency is improved.
And 3, extending the track points in the reference track to two sides to generate scanning line segments, clustering the intersection points of the same scanning line segment and the original lane line to generate each clustering point, classifying each clustering point, and fitting into a line to obtain the aggregation result of the lane line.
Specifically, the direction in which the track point extends to both sides may be a direction perpendicular to the track direction, and the extending distance may be 20 m.
Fig. 5 is a schematic diagram of intersection points and cluster points provided by the embodiment of the present invention, in fig. 5, a dark color in the middle is a track point, dense small points on both sides are intersection points of a scan line segment and an original lane line, and a larger point in the middle of the intersection points is a cluster point generated by clustering the intersection points of the same scan line segment and the original lane line.
The process of generating each cluster point in step 3 includes:
and judging whether the number of the intersection points of the scanning line segments and the original lane lines exceeds the set number, if so, clustering the intersection points by adopting a MeanShift clustering method, and if not, clustering the intersection points by using a DBSCAN clustering method.
The radius (eps) of the parameter core point of the DBSCAN clustering method and the bandwidth (bandwidth) of the parameter of the MeanShift clustering method can be set to be the shortest distance that two lane lines can distinguish.
The DBSCAN clustering method and the MeanShift clustering method are both density-based clustering methods, and when the MeanShift method is used for clustering large data volume, the performance and the memory performance are superior to those of the DBSCAN, so that different clustering methods are selected by judging the sizes of the intersection point number and the set number, the performance and the accuracy can be considered, and the set number can be 1000.
The method for classifying each clustering point in the step 3 comprises the following steps: and classifying cluster points with transverse distance variation smaller than a set distance threshold into one class along the direction of the reference track, wherein the transverse distance is the distance between the cluster points and the starting points of the scanning line segments. The method specifically comprises the following steps: and collecting clustering points with the transverse distance smaller than a distance threshold along the track direction, and classifying the clustering points into the same class.
And points with close transverse distance and plane distance are classified as the same type, when the transverse distance exceeds a distance threshold value, the points are classified as a new type, and after the classification is finished, the points of the same type are fitted into a line, namely, the lane line result in the area.
Fig. 6 is a schematic diagram of generating a fit line according to an embodiment of the present invention, in fig. 6, a track point of a middle dark-color point, lane line cluster points of light-color points on two sides, marked numbers are transverse distances of the cluster points, and lines passing through the similar cluster points are fit lines, that is, a result of aggregating lane line boundaries in a divided region.
And after the process of lane line aggregation of each divided area is finished, combining the lane lines of each divided area to finish the generation of the lane lines of all the areas.
As shown in fig. 7 and 8, which are respectively a mixed line removing effect diagram and a curve generating effect diagram provided by the embodiment of the present invention, a light line in fig. 7 is an original lane line, a dark line is a lane line generated by using the lane line aggregation method provided by the embodiment of the present invention, a light line in fig. 8 is an original lane line, and a dark line is a lane line generated by using the lane line aggregation method provided by the embodiment of the present invention, it can be seen from fig. 7 and 8 that the lane line aggregation method based on the track direction provided by the embodiment of the present invention has a good effect in an actual use process, and can make a finally generated curve shape, particularly, lane shapes of the mixed line and the lane conform to an actual situation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A lane line aggregation method based on track direction is characterized by comprising the following steps:
step 1, taking a track segment between two adjacent track points as a center, and generating a buffer area of each track segment according to a set width;
step 2, combining the buffers of the track segments to generate a buffer list, traversing all the track points, judging whether to reserve or discard the track points according to whether the track points are in the buffer list, and generating a reference track according to each reserved track point;
and 3, extending the track points in the reference track to two sides to generate scanning line segments, clustering the intersection points of the same scanning line segments and the original lane lines to generate all clustering points, classifying all the clustering points, and fitting the clustering points into a line to obtain the aggregation result of the lane lines.
2. The method of claim 1, wherein the step 1 of generating the buffer of trajectory line segments further comprises: performing area division on the input original lane lines and tracks;
and respectively carrying out lane line aggregation on each divided area according to the method in the step 1 to the step 3, and then combining lane lines of each divided area.
3. The method of claim 2, wherein the process of performing region partitioning comprises:
dividing by taking longitude and latitude as a unit, and numbering each divided area;
for any track point, when the track point and the adjacent track point are in the same divided region, reserving the serial number of the divided region where the track point is located; when the track points and any adjacent track points are not in the same divided region, reserving the serial numbers of the divided regions where the track points are located and adjacent to the track points;
for any original lane line, when the original lane line is in one divided region, the serial number of the divided region where the original lane line is located is reserved; and when the original lane line crosses the region, reserving the serial numbers of the divided regions where the original lane line is positioned.
4. The method of claim 2, wherein the process of merging the lane lines of each of the divided regions comprises: and traversing the starting point and the end point of the lane line of each divided area boundary, and connecting the two lane lines together when finding points with similar distance and angle from the starting point and the end point of the lane line adjacent to the divided area.
5. The method according to claim 1, wherein the buffer area of the track line segment generated in step 1 is a quadrilateral with the track line segment as a center line, a set width and a length equal to that of the track line segment.
6. The method of claim 1, wherein traversing all of the trace points in step 2 comprises:
and traversing the trace points according to the time sequence, discarding the trace points if the trace points are in the buffer area list, and adding the buffer area of the trace line segment consisting of the trace points and the previous trace points into the buffer area list if the trace points are not in the buffer area list.
7. The method of claim 1 or 6, wherein determining whether any of the trace points are in the buffer list comprises: traversing the buffer area list, and judging whether the track point is in the range of any buffer area and whether the direction of the track point is consistent with that of the buffer area; the direction of the track point is the direction from the previous track point of the track point to the track line segment of the track point; the direction of the buffer area is consistent with the direction of the track.
8. The method of claim 7, wherein determining whether the trace points are within any of the buffer areas comprises: making rays in any direction perpendicular to the track direction from the track points, and if the number of intersection points of the rays and the buffer area is an odd number, judging that the track points are in the buffer area; and if the intersection point number of the ray and the buffer area is an even number, judging that the track point is outside the buffer area.
9. The method according to claim 1, wherein the step 3 of generating each cluster point comprises: and judging whether the number of the intersection points of the scanning line segments and the original lane lines exceeds a set number, if so, clustering the intersection points by adopting a MeanShift clustering method, and if not, clustering the intersection points by using a DBSCAN clustering method.
10. The method according to claim 1, wherein the step 3 of classifying each cluster point comprises:
and classifying the clustering points with transverse distance variation smaller than a set distance threshold into one class along the direction of the reference track, wherein the transverse distance is the distance between the clustering points and the starting points of the scanning line segments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911026989.2A CN110906940B (en) | 2019-10-26 | 2019-10-26 | Lane sideline aggregation method based on track direction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911026989.2A CN110906940B (en) | 2019-10-26 | 2019-10-26 | Lane sideline aggregation method based on track direction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110906940A true CN110906940A (en) | 2020-03-24 |
| CN110906940B CN110906940B (en) | 2021-05-18 |
Family
ID=69815876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911026989.2A Active CN110906940B (en) | 2019-10-26 | 2019-10-26 | Lane sideline aggregation method based on track direction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110906940B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287778A (en) * | 2020-10-16 | 2021-01-29 | 苏州万店掌网络科技有限公司 | People flow analysis method and medium based on directional aggregation |
| CN112433203A (en) * | 2020-10-29 | 2021-03-02 | 同济大学 | Lane alignment detection method based on millimeter wave radar data |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
| CN113465615A (en) * | 2021-06-23 | 2021-10-01 | 智道网联科技(北京)有限公司 | Lane line generation method and related device |
| CN114049327A (en) * | 2021-11-16 | 2022-02-15 | 中国测绘科学研究院 | Improved large-range road center line block extraction algorithm |
| WO2022188775A1 (en) * | 2021-03-11 | 2022-09-15 | 奇瑞汽车股份有限公司 | Road network file generation method and apparatus, and device, readable storage medium and vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488485A (en) * | 2015-12-07 | 2016-04-13 | 北京航空航天大学 | Lane line automatic extraction method based on vehicle trajectory |
| DE102015000399A1 (en) * | 2015-01-13 | 2016-07-28 | Audi Ag | Mapping of lanes using vehicle fleet data |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
| CN110287904A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of lane line extracting method, device and storage medium based on crowdsourcing data |
-
2019
- 2019-10-26 CN CN201911026989.2A patent/CN110906940B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102015000399A1 (en) * | 2015-01-13 | 2016-07-28 | Audi Ag | Mapping of lanes using vehicle fleet data |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN105488485A (en) * | 2015-12-07 | 2016-04-13 | 北京航空航天大学 | Lane line automatic extraction method based on vehicle trajectory |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
| CN110287904A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of lane line extracting method, device and storage medium based on crowdsourcing data |
Non-Patent Citations (2)
| Title |
|---|
| LULIANG TANG .ET AL: "Lane-Level Road Information Mining from Vehicle GPS Trajectories Based on Naïve Bayesian Classification", 《ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION》 * |
| MELO .ET AL: "Detection and Classification of Highway Lanes Using Vehicle Motion Trajectories", 《TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287778A (en) * | 2020-10-16 | 2021-01-29 | 苏州万店掌网络科技有限公司 | People flow analysis method and medium based on directional aggregation |
| CN112287778B (en) * | 2020-10-16 | 2021-07-27 | 苏州万店掌网络科技有限公司 | People flow analysis method and medium based on directional aggregation |
| CN112433203A (en) * | 2020-10-29 | 2021-03-02 | 同济大学 | Lane alignment detection method based on millimeter wave radar data |
| WO2022089194A1 (en) * | 2020-10-29 | 2022-05-05 | 同济大学 | Millimeter-wave radar data-based lane line detection method |
| CN112433203B (en) * | 2020-10-29 | 2023-06-20 | 同济大学 | Lane linearity detection method based on millimeter wave radar data |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
| WO2022188775A1 (en) * | 2021-03-11 | 2022-09-15 | 奇瑞汽车股份有限公司 | Road network file generation method and apparatus, and device, readable storage medium and vehicle |
| CN113465615A (en) * | 2021-06-23 | 2021-10-01 | 智道网联科技(北京)有限公司 | Lane line generation method and related device |
| CN113465615B (en) * | 2021-06-23 | 2021-11-09 | 智道网联科技(北京)有限公司 | Lane line generation method and related device |
| CN114049327A (en) * | 2021-11-16 | 2022-02-15 | 中国测绘科学研究院 | Improved large-range road center line block extraction algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110906940B (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110906940B (en) | Lane sideline aggregation method based on track direction | |
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| CN105528588B (en) | A kind of Lane detection method and device | |
| CN106840176B (en) | GPS time-space data increment road network real-time updating and track matching system | |
| CN106323301B (en) | Method and device for acquiring road information | |
| CN108898672A (en) | A kind of semi-automatic cloud method making three-dimensional high-definition mileage chart lane line | |
| CN108986493A (en) | Traffic lights transit time distribution method and its device | |
| Uduwaragoda et al. | Generating lane level road data from vehicle trajectories using kernel density estimation | |
| CN102622370B (en) | Method and device for acquisition of route description and electronic map server | |
| CN105893703B (en) | A kind of urban road network's major trunk roads choosing method based on polygon | |
| CN111858810B (en) | Modeling elevation point screening method for road DEM construction | |
| CN104751733B (en) | The region method for drafting and device of map, path distance sorting technique and system | |
| CN113553482B (en) | Stay point identification and trip chain construction system, algorithm, equipment and storage medium | |
| CN108469263B (en) | Method and system for shape point optimization based on curvature | |
| CN112749242B (en) | Road network topology reconstruction method based on shared bicycle GPS data | |
| CN116543310B (en) | Road line extraction method based on Voronoi diagram and kernel density | |
| CN114332291A (en) | Oblique photography model building outer contour rule extraction method | |
| CN111209805B (en) | Rapid fusion optimization method for multi-channel segment data of lane line crowdsourcing data | |
| CN110913345B (en) | Section passenger flow calculation method based on mobile phone signaling data | |
| CN116071722A (en) | Lane geometric information extraction method, system, equipment and medium based on road section track | |
| CN113903173A (en) | Vehicle track feature extraction method based on directed graph structure and LSTM | |
| CN116051841A (en) | Roadside ground object multistage clustering segmentation algorithm based on vehicle-mounted LiDAR point cloud | |
| CN116310442A (en) | Track point identification method, track point identification device and map making method | |
| CN115631476A (en) | Lane data processing method, system, electronic device and storage medium | |
| CN111696115A (en) | Zebra line corner extraction method and system based on point cloud scanning line |
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 |