CN110458083A - A kind of lane line vectorization method, device and storage medium - Google Patents
A kind of lane line vectorization method, device and storage medium Download PDFInfo
- Publication number
- CN110458083A CN110458083A CN201910719035.3A CN201910719035A CN110458083A CN 110458083 A CN110458083 A CN 110458083A CN 201910719035 A CN201910719035 A CN 201910719035A CN 110458083 A CN110458083 A CN 110458083A
- Authority
- CN
- China
- Prior art keywords
- lane line
- point cloud
- edge
- lane
- central axes
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Abstract
The present invention relates to a kind of lane line vectorization method, device and storage mediums, belong to electronic map field.This method comprises: obtaining original lane line point cloud；After being fitted lane line central axes based on least square method, according to the statistical information of original lane line point cloud to lane line central axes distance, the lane line point cloud in lane line edge extent is extracted；The profile point for detecting the lane line point cloud in lane line edge extent is fitted the lane line edge line of vector quantization according to profile point.Vector quantization lane line edge definition can be ensured with this solution, while simplifying and calculating, as a result accurately and reliably.
Description
Technical field
The present invention relates to electronic map field more particularly to a kind of lane line vectorization methods, device and storage medium.
Background technique
High-precision map of navigation electronic is vehicle in unmanned middle important references information, it can be provided precisely for vehicle
Positioning and decision-making foundation.And the edge definition of lane line is also one of core index in high-precision map of navigation electronic, often
It is required that lane position is accurate to Centimeter Level.Realize that lane line point cloud data is bonded with vector quantization edge line, for accurately determining vehicle
Road line position plays a significant role.
For the Automatic Vector of lane line point cloud, lane is directly extracted from point cloud data currently, having frequently with method
Line point cloud carries out vector quantization, and the left and right lane edge line precision that this method obtains is not high, is easy to appear same lane line width not
One；Another kind obtains lane line edge pixel, edge line of the then inverse mapping to lane line point cloud, the method based on semantic segmentation
Need largely to mark sample, process is complicated and computationally intensive.
So, it is necessary to it proposes a kind of can both ensure lane line edge definition, while the simple lane line of calculating process
Vectorization method.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of lane line vectorization method, device and storage medium, Ke Yizhun
Really now the vector quantization at lane line edge, guarantee vector quantization lane line are bonded with lane line point cloud.
In the embodiment of the present invention in a first aspect, providing a kind of lane line vectorization method, comprising:
Obtain original lane line point cloud；
After being fitted lane line central axes based on least square method, according to original lane line point cloud to the lane line central axes
The statistical information of distance extracts the lane line point cloud in lane line edge extent；
The profile point for detecting the lane line point cloud in lane line edge extent is fitted the vehicle of vector quantization according to the profile point
Diatom edge line.
In the second aspect of the embodiment of the present invention, a kind of lane line vectoring arrangement is provided, comprising:
Module is obtained, for obtaining original lane line point cloud；
Extraction module, after based on least square method fitting lane line central axes, according to original lane line point cloud to institute
The statistical information of lane line central axes distance is stated, the lane line point cloud in lane line edge extent is extracted；
Fitting module, for detecting the profile point of the lane line point cloud in lane line edge extent, according to the profile point
It is fitted the lane line edge line of vector quantization.
In the third aspect of the embodiment of the present invention, a kind of device is provided, including memory, processor and be stored in institute
The computer program that can be run in memory and in the processor is stated, the processor is realized when executing the computer program
Such as the step of first aspect the method for the embodiment of the present invention.
In the fourth aspect of the embodiment of the present invention, a kind of computer readable storage medium is provided, it is described computer-readable
Storage medium is stored with computer program, and first aspect of the embodiment of the present invention is realized when the computer program is executed by processor
The step of the method for offer.
5th aspect of the embodiment of the present invention, provides a kind of computer program product, the computer program product packet
Computer program is included, realizes that first aspect of the embodiment of the present invention mentions when the computer program is executed by one or more processors
The step of the method for confession.
In the embodiment of the present invention, it is fitted the central axes of lane line by least square method, then counts institute in initial point cloud
Central axes range distribution is a little arrived, according to distribution characteristics, extracts the point within the scope of edge lane line.Finally, with lane line edge
Point is profile point, is fitted the edge line of lane line, obtains the lane line of vector quantization.The program is simple and easy, relative to traditional root
Marginal point cloud position is obtained according to edge pixel inverse mapping, calculation amount is less, and directly calculates original point cloud, avoids counting
According to loss of significance in conversion, ensure that the calculating at lane line edge is accurate.Wherein, the statistics letter based on cloud all the points to longitudinal axis
Breath can eliminate the influence of individual rim point, realize that practical lane line point cloud is bonded with the complete of vector quantization edge line.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of lane line vectorization method provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic illustration of lane line vectorization method provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of lane line vectoring arrangement provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides a kind of lane line vectorization method, device and storage mediums, for accurately determining vehicle
Diatom edge ensures the precision of lane line vector quantization.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Embodiment one:
Referring to Fig. 1, the flow diagram of lane line vectorization method provided in an embodiment of the present invention, comprising:
S101, original lane line point cloud is obtained；
The original lane line point cloud is the lane line point cloud data extracted from original point cloud data, can generally be passed through
Specific algorithm, such as clustering, connectivity analysis etc. obtains lane line point cloud or direct labor selectes lane line point cloud, leads to
The original lane line point cloud for crossing above method acquisition is generally less accurate.
S102, based on least square method fitting lane line central axes after, according to original lane line point cloud to the lane line
The statistical information of central axes distance extracts the lane line point cloud in lane line edge extent；
For original lane line point cloud, progress lane line point cloud can be segmented and accurately extracted.General lane line can be divided into
Straight line and curve can be indicated with the broken line of segmentation for the lane line of curve driving or calibration curve equation indicate.
All the points in a certain section of lane line original lane line point cloud based on division, are fitted all the points by least square method
Central axes.Wherein, the central axes can be indicated by linear equation in planar two dimensional coordinate system or curvilinear equation.
The distance for counting all the points to central axes in the one section of lane line point cloud currently divided is searched according to statistical information
Marginal point in lane line point cloud, and using all the points in edge point range as the lane line point cloud after essence extraction.Wherein, institute
Stating statistical information is distributed intelligence of all the points away from central axes.
Specifically, the frequency distribution based on all the points in the original lane line point cloud to lane line central axes distance
Histogram calculates the standard variance of point cloud distribution；
When the standard variance be less than preset value, extract edge lane line within the scope of lane line point cloud.
Further, when the standard variance be greater than preset value, then constantly remove in the original lane line with the vehicle
The corresponding point of diatom central axes maximum distance, until the standard variance is less than preset value.
Illustratively, the distance that all the points arrive central axes at plane coordinate system (i.e. in xy coordinate plane) is calculated, is with 1cm
Distance, forms each point cloud histogram frequency distribution diagram in section, and stochastic variable X indicates distribution law, calculates the mark of stochastic variable X
Quasi- variance, when variance yields is less than threshold value T, then meeting a cloud essence to extract the maximum distance for requiring, and putting is the one of lane line width
Half.If variance yields is greater than threshold value T, after needing to repeat to reject the corresponding point of maximum distance, standard variance is calculated again, until side
Difference is less than threshold value T.
S103, detection lane line edge extent in lane line point cloud profile point, according to the profile point be fitted vector
The lane line edge line of change.
The profile point is the corresponding point of lane line marginal position, is obtained a little after essence is extracted in original car diatom point cloud
Cloud data are the point cloud in edge extent.In general, by pre-defined algorithm test point cloud data acquisition profile, the predetermined calculation
Method can be Alpha Shapes algorithm.
Specifically, the profile point of the lane line point cloud within the scope of edge lane line is detected by Alpha Shapes algorithm,
Lane lines left and right edges are distinguished, lane lines left and right edges are fitted.
Lane line has one fixed width, and corresponding along lane line direction, there are both sides of the edge, respectively left edge and the right side
Edge.By Alpha Shapes algorithm, the point cloud distribution of lane line central axes two sides is detected, both sides of the edge profile point is extracted.
Optionally, according to the linear equation of the lane line central axes, the equation of lane lines left and right edges line is established respectively,
According to the equation of the lane lines left and right edges line, lane lines left and right edges are fitted.
Illustratively, it is assumed that equation are as follows: Ax+By+C=0；It may further assume that left and right edges equation is respectively
Ax+By+Cl=0 and Ax+By+Cr=0, wherein exist And
Fig. 2 is the schematic illustration of lane line vector quantization provided in an embodiment of the present invention, in conjunction with Fig. 2 to lane line vector quantization
Process is described in detail, as shown in Figure 2: 20 being lane line, 202 is any point in lane line point cloud, 201 is lane line axis
Line, according to fig. 2 in original lane line point cloud, be fitted to obtain lane line central axes 201 by least square method, then according to a cloud
Middle all the points obtain histogram frequency distribution diagram, in the standard variance for seeking histogram, judgment criteria to the distance of central axes 201
Whether it is less than preset threshold, when being less than threshold value, then using current point cloud as the lane line point cloud after purification, otherwise constantly rejects outer
It encloses apart from farthest point, until standard deviation square value is less than threshold value, the lane line point cloud that available essence is extracted.
Then, in detection circumference point, it is assumed that 202 be the point of lane line outermost, then point 202 is arrived central axes 201
Point in distance range is used as the point in the lane line point cloud in edge extent, the point composition lane line point cloud in edge extent.
Method provided in this embodiment is based on lane line central axes, calculates initial point cloud all the points distribution characteristics, Jin Erti
The point cloud in edge extent is taken, vector quantization lane line simple and quick can be obtained, guarantees that lane line edge and actual point cloud are accurate
Fitting promotes lane line point Yun Jingdu.
Embodiment two:
Fig. 3 is the structural schematic diagram of lane line vectoring arrangement provided by Embodiment 2 of the present invention, comprising:
Module 310 is obtained, for obtaining original lane line point cloud；
Extraction module 320 is arrived after based on least square method fitting lane line central axes according to original lane line point cloud
The statistical information of lane line central axes distance extracts the lane line point cloud in lane line edge extent；
Optionally, the extraction module 320 includes:
Computing unit, for the frequency based on all the points in the original lane line point cloud to lane line central axes distance
Rate distribution histogram calculates the standard variance of point cloud distribution；
Extraction unit extracts the lane line point within the scope of edge lane line for being less than preset value when the standard variance
Cloud.
Optionally, the extraction unit further include:
Removal unit, for when the standard variance be greater than preset value, then constantly remove in the original lane line with institute
The corresponding point of lane line central axes maximum distance is stated, until the standard variance is less than preset value.
Fitting module 330, for detecting the profile point of the lane line point cloud in lane line edge extent, according to the profile
The lane line edge line of point fitting vector quantization.
Optionally, the profile point of the lane line point cloud within the scope of edge lane line is detected by Alpha Shapes algorithm,
Lane lines left and right edges are distinguished, lane lines left and right edges are fitted.
Optionally, according to the linear equation of the lane line central axes, the equation of lane lines left and right edges line is established respectively,
According to the equation of the lane lines left and right edges line, lane lines left and right edges are fitted.
It should be noted that the left and right edges line is the two sides along lane line direction or lane line central axes direction
Edge line, can be straight line or curve, again without limitation.
Device through this embodiment both can simplify lane line vector quantization process, reduce calculation amount, meanwhile, guarantee vehicle
Diatom edge definition, realization are bonded with actual point cloud.
Those of ordinary skill in the art will appreciate that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, the program can be stored in a computer readable storage medium,
When being executed, including step S101 to S103, the storage medium includes such as to the program: ROM/RAM, magnetic disk, CD.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of lane line vectorization method characterized by comprising
Obtain original lane line point cloud；
After being fitted lane line central axes based on least square method, according to original lane line point cloud to lane line central axes distance
Statistical information, extract lane line edge extent in lane line point cloud；
The profile point for detecting the lane line point cloud in lane line edge extent is fitted the lane line of vector quantization according to the profile point
Edge line.
2. the method according to claim 1, wherein it is described according to original lane line point cloud into the lane line
The statistical information of axial line distance extracts the lane line point cloud in lane line edge extent specifically:
Based on the histogram frequency distribution diagram of all the points in the original lane line point cloud to lane line central axes distance, calculate
The standard variance of point cloud distribution；
When the standard variance be less than preset value, extract edge lane line within the scope of lane line point cloud.
3. according to the method described in claim 2, it is characterized in that, described when the standard variance is less than preset value, extraction side
Lane line point cloud within the scope of edge lane line further include:
When the standard variance is greater than preset value, then constantly remove maximum with the lane line central axes in the original lane line
Apart from corresponding point, until the standard variance is less than preset value.
4. the method according to claim 1, wherein the lane line point cloud in the detection lane line edge extent
Profile point, according to the profile point be fitted vector quantization lane line edge line further include:
The profile point of the lane line point cloud within the scope of edge lane line is detected by Alpha Shapes algorithm, and it is left to distinguish lane line
Right hand edge is fitted lane lines left and right edges.
5. the method according to claim 1, wherein the lane line point cloud in the detection lane line edge extent
Profile point, according to the profile point be fitted vector quantization lane line edge line further include:
According to the linear equation of the lane line central axes, the equation of lane lines left and right edges line is established respectively, according to the vehicle
The equation of diatom left and right edges line, is fitted lane lines left and right edges.
6. a kind of lane line vectoring arrangement characterized by comprising
Module is obtained, for obtaining original lane line point cloud；
Extraction module, after based on least square method fitting lane line central axes, according to original lane line point cloud to the vehicle
The statistical information of diatom central axes distance extracts the lane line point cloud in lane line edge extent；
Fitting module is fitted for detecting the profile point of the lane line point cloud in lane line edge extent according to the profile point
The lane line edge line of vector quantization.
7. device according to claim 6, which is characterized in that the extraction module includes:
Computing unit, for the frequency minute based on all the points in the original lane line point cloud to lane line central axes distance
Cloth histogram calculates the standard variance of point cloud distribution；
Extraction unit extracts the lane line point cloud within the scope of edge lane line for being less than preset value when the standard variance.
8. device according to claim 7, which is characterized in that the extraction unit further include:
Removal unit, for when the standard variance be greater than preset value, then constantly remove in the original lane line with the vehicle
The corresponding point of diatom central axes maximum distance, until the standard variance is less than preset value.
9. a kind of device, including memory, processor and storage can be run in the memory and on the processor
Computer program, which is characterized in that the processor is realized when executing the computer program as appointed in claim 1 to 5
The step of one lane line vectorization method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realizing the lane line vectorization method as described in any one of claim 1 to 5 when the computer program is executed by processor
Step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910719035.3A CN110458083B (en) | 2019-08-05 | 2019-08-05 | Lane line vectorization method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910719035.3A CN110458083B (en) | 2019-08-05 | 2019-08-05 | Lane line vectorization method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458083A true CN110458083A (en) | 2019-11-15 |
| CN110458083B CN110458083B (en) | 2022-03-25 |
Family
ID=68484895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910719035.3A Active CN110458083B (en) | 2019-08-05 | 2019-08-05 | Lane line vectorization method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458083B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111141296A (en) * | 2019-12-24 | 2020-05-12 | 武汉中海庭数据技术有限公司 | Preprocessing method and system for multi-channel fragment data of lane line crowdsourcing data |
| CN111353466A (en) * | 2020-03-12 | 2020-06-30 | 北京百度网讯科技有限公司 | Lane line recognition processing method, lane line recognition processing device, and storage medium |
| CN112330604A (en) * | 2020-10-19 | 2021-02-05 | 香港理工大学深圳研究院 | Method for generating vectorized road model from point cloud data |
| CN113780069A (en) * | 2021-07-30 | 2021-12-10 | 武汉中海庭数据技术有限公司 | Lane line separation drawing method and device under convergence scene |
| CN113780067A (en) * | 2021-07-30 | 2021-12-10 | 武汉中海庭数据技术有限公司 | Lane linear marker detection method and system based on semantic segmentation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392212A (en) * | 2014-11-14 | 2015-03-04 | 北京工业大学 | Method for detecting road information and identifying forward vehicles based on vision |
| CN104850834A (en) * | 2015-05-11 | 2015-08-19 | 中国科学院合肥物质科学研究院 | Road boundary detection method based on three-dimensional laser radar |
| CN105260713A (en) * | 2015-10-09 | 2016-01-20 | 东方网力科技股份有限公司 | Method and device for detecting lane line |
| CN106408581A (en) * | 2016-09-12 | 2017-02-15 | 厦门大学 | Rapid three-dimensional point cloud linear extraction method |
| CN106780524A (en) * | 2016-11-11 | 2017-05-31 | 厦门大学 | A kind of three-dimensional point cloud road boundary extraction method |
| CN108062517A (en) * | 2017-12-04 | 2018-05-22 | 武汉大学 | Unstructured road boundary line extraction method based on vehicle-mounted laser point cloud |
| CN108241819A (en) * | 2016-12-23 | 2018-07-03 | 高德软件有限公司 | The recognition methods of pavement markers and device |
-
2019
- 2019-08-05 CN CN201910719035.3A patent/CN110458083B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392212A (en) * | 2014-11-14 | 2015-03-04 | 北京工业大学 | Method for detecting road information and identifying forward vehicles based on vision |
| CN104850834A (en) * | 2015-05-11 | 2015-08-19 | 中国科学院合肥物质科学研究院 | Road boundary detection method based on three-dimensional laser radar |
| CN105260713A (en) * | 2015-10-09 | 2016-01-20 | 东方网力科技股份有限公司 | Method and device for detecting lane line |
| CN106408581A (en) * | 2016-09-12 | 2017-02-15 | 厦门大学 | Rapid three-dimensional point cloud linear extraction method |
| CN106780524A (en) * | 2016-11-11 | 2017-05-31 | 厦门大学 | A kind of three-dimensional point cloud road boundary extraction method |
| CN108241819A (en) * | 2016-12-23 | 2018-07-03 | 高德软件有限公司 | The recognition methods of pavement markers and device |
| CN108062517A (en) * | 2017-12-04 | 2018-05-22 | 武汉大学 | Unstructured road boundary line extraction method based on vehicle-mounted laser point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 孔栋,孙亮,王建强,王晓原: "基于 3D 激光雷达点云的道路边界识别算法", 《广西大学学报(自然科学版)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111141296A (en) * | 2019-12-24 | 2020-05-12 | 武汉中海庭数据技术有限公司 | Preprocessing method and system for multi-channel fragment data of lane line crowdsourcing data |
| CN111353466A (en) * | 2020-03-12 | 2020-06-30 | 北京百度网讯科技有限公司 | Lane line recognition processing method, lane line recognition processing device, and storage medium |
| CN111353466B (en) * | 2020-03-12 | 2023-09-22 | 北京百度网讯科技有限公司 | Lane line recognition processing method, equipment and storage medium |
| CN112330604A (en) * | 2020-10-19 | 2021-02-05 | 香港理工大学深圳研究院 | Method for generating vectorized road model from point cloud data |
| CN113780069A (en) * | 2021-07-30 | 2021-12-10 | 武汉中海庭数据技术有限公司 | Lane line separation drawing method and device under convergence scene |
| CN113780067A (en) * | 2021-07-30 | 2021-12-10 | 武汉中海庭数据技术有限公司 | Lane linear marker detection method and system based on semantic segmentation |
| CN113780069B (en) * | 2021-07-30 | 2024-02-20 | 武汉中海庭数据技术有限公司 | Lane line separation drawing method and device under confluence scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458083B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458083A (en) | A kind of lane line vectorization method, device and storage medium | |
| CN109270927B (en) | Road data generation method and device | |
| CN107767383B (en) | Road image segmentation method based on superpixels | |
| CN112441022B (en) | Lane center line determining method and device | |
| CN110426051A (en) | A kind of lane line method for drafting, device and storage medium | |
| CN110287904A (en) | A kind of lane line extracting method, device and storage medium based on crowdsourcing data | |
| CN102982545B (en) | A kind of image depth estimation method | |
| CN108022262A (en) | A kind of point cloud registration method based on neighborhood of a point center of gravity vector characteristics | |
| CN113682318B (en) | Vehicle running control method and device | |
| CN110704559B (en) | Multi-scale vector surface data matching method | |
| CN110543473B (en) | Crowdsourcing data fusion optimization method and device and storage medium | |
| CN103955945A (en) | Self-adaption color image segmentation method based on binocular parallax and movable outline | |
| CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
| CN112634297A (en) | High-precision map making method and device, electronic equipment and storage medium | |
| CN112883236B (en) | Map updating method and device, electronic equipment and storage medium | |
| CN112418193B (en) | Lane line identification method and system | |
| CN112435336B (en) | Curve type identification method and device, electronic equipment and storage medium | |
| CN106408029A (en) | Image texture classification method based on structural difference histogram | |
| CN113762397B (en) | Method, equipment, medium and product for training detection model and updating high-precision map | |
| CN115171094A (en) | Road element determination method, device, equipment and storage medium | |
| CN111210452B (en) | Certificate photo portrait segmentation method based on graph segmentation and mean shift | |
| CN104143189A (en) | Method for extracting spatial features of 3D point cloud data of power transmission equipment | |
| CN103530905B (en) | A kind of removing method for the flat Delta Region of level line | |
| CN113723405A (en) | Method and device for determining area outline and electronic equipment | |
| 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 |