CN110320504B - Unstructured road detection method based on laser radar point cloud statistical geometric model - Google Patents
Unstructured road detection method based on laser radar point cloud statistical geometric model Download PDFInfo
- Publication number
- CN110320504B CN110320504B CN201910690051.4A CN201910690051A CN110320504B CN 110320504 B CN110320504 B CN 110320504B CN 201910690051 A CN201910690051 A CN 201910690051A CN 110320504 B CN110320504 B CN 110320504B
- Authority
- CN
- China
- Prior art keywords
- road
- point cloud
- cloud data
- point
- laser
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an unstructured road detection method based on a laser radar point cloud statistical geometric model. The method comprises the following steps: acquiring original three-dimensional point cloud data by using a vehicle-mounted laser radar; constructing a laser point cloud three-dimensional histogram; fitting data points in the three-dimensional histogram to obtain a basic contour of a road flat area; fitting the basic outline of the road flat area by adopting a least square method to obtain a quadric surface equation of the road flat area; setting a grid resolution ratio R, obtaining a spatial two-dimensional grid map under a Cartesian coordinate system, and counting the maximum height difference of all laser point cloud data in each grid unit; and calculating the distance from the laser point cloud data to the quadric surface, and determining a final passable area according to the maximum height difference of the point cloud data of the grid unit to which the laser point cloud data belongs. The method can be applied to the problem of detection of the travelable area of the unmanned autonomous vehicle on the unstructured road.
Description
Technical Field
The invention relates to an environment perception technology for unmanned driving, in particular to an unstructured road detection method based on a laser radar point cloud statistical geometric model.
Background
The safe driving of an unmanned vehicle relies on its intelligent perception of the surrounding environment. For road surface detection technology, unmanned vehicles generally classify roads into two types, structured and unstructured roads. In view of recent related progress at home and abroad, a road surface detection technology for a structured road is increasingly mature, while an unstructured road (such as a wilderness) generally has complex and changeable visual features of undefined shape, uncertain edges and the like, so that great difficulty and challenge are caused to the research of the road surface detection technology, and no mature solution is provided so far. As a surveying and mapping sensor integrating various high and new technologies, the three-dimensional laser radar has the advantages of wide detection range, high resolution, robustness for environmental factors such as light rays and the like, and capability of meeting the requirement of executing tasks in a complex environment, so that the three-dimensional laser radar is widely applied to the environment perception task of an unmanned vehicle.
The existing road surface detection technology based on the three-dimensional laser radar mainly comprises two major types of grid map-based segmentation algorithms and scanning line-based geometric feature segmentation algorithms. The CN.108460416A discloses a detection method of a travelable road surface area, which comprises the steps of extracting interesting data points of a three-dimensional laser radar, extracting obstacles by adopting a K-Means clustering algorithm and a height characteristic, extracting road edges by combining a DBSCAN clustering method, fitting a road edge curve by least squares, and finally determining the passable road area. Another method for detecting a travelable road surface area is known from cn.108280840a, which determines an azimuth sequence-distance relationship diagram by extracting a single line, draws a line segment map by improving a fuzzy line segment method, and identifies a road surface and an obstacle, thereby finally obtaining a travelable area.
Although the above methods have achieved some degree of success, they are only suitable for use in structured environments. For an unstructured environment, obstacles on two sides of a road sometimes do not exist, and the determination of the road edge by using the obstacle information is not strictly met, so that the road surface detection algorithm cannot be applied.
Disclosure of Invention
The invention aims to solve the technical problem of providing an unstructured road detection method based on a laser radar point cloud statistical geometric model aiming at the defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: an unstructured road detection method based on a laser radar point cloud statistical geometric model comprises the following steps:
(1) acquiring original three-dimensional point cloud data by using a vehicle-mounted laser radar;
(2) the method comprises the following steps of constructing a laser point cloud three-dimensional histogram by utilizing three-dimensional point cloud data:
(2.1) establishing a Cartesian coordinate system by taking the three-dimensional laser radar as a coordinate origin, wherein the X-axis direction is parallel to the ground and points to the advancing direction of the unmanned vehicle, the Y-axis direction is parallel to the ground and points to the left of the unmanned vehicle, the Z-axis direction is vertical to an X-Y plane, and the direction is vertical to the ground and upwards;
(2.2) reciprocal of coordinate in positive X-axis direction
As a horizontal axis coordinate, and a laser radar line bundle as a vertical axis coordinate, and counting the number of laser radar lines on each laser radar line bundle
The number of scanning points of the positions is used for constructing a laser point cloud three-dimensional histogram;
(3) fitting data points in the three-dimensional histogram to obtain a basic contour of a road flat area, and specifically comprising the following steps of:
(3.1) fitting data points in the three-dimensional histogram by using a RANSAC algorithm to obtain a road line equation:
n＝km+b
in the formula, n is a laser radar wire harness, and m is the reciprocal of the coordinate in the positive direction of the X axis in a Cartesian coordinate system; k and b are parameters of a road linear equation;
(3.2) establishing a road model tolerance interval by using a road linear equation, wherein the linear equation of the upper and lower boundaries of the interval is as follows:
n＝km+αb
n＝km+βb
in the formula, alpha is a parameter for determining the upper limit of the interval tolerance, alpha is less than 1, beta is a parameter for determining the lower limit of the interval tolerance, and beta is more than 1;
(3.3) projecting the original laser point cloud data into the three-dimensional histogram, and if the data points projected into the three-dimensional histogram are within the tolerance interval of the road model, determining the data points as road region points; otherwise, if the data point is out of the tolerance interval of the road model, the data point is a non-road region point;
(3.4) counting laser point cloud data falling in a tolerance interval of the road model by utilizing the corresponding relation between the three-dimensional histogram and the original laser point cloud to obtain a basic outline of a road flat area;
(4) fitting point cloud data on the basic outline of the road flat area by adopting a least square method to obtain a quadric surface equation of the road flat area;
(5) setting grid resolution, obtaining a space grid map under a Cartesian coordinate system, and counting the maximum height difference of all laser point cloud data in each grid unit;
(6) calculating the distance from the laser point cloud data to the quadric surface, and determining a final passable area according to the maximum height difference of the grid unit point cloud data to which the laser point cloud data belongs; the method specifically comprises the following steps: setting the maximum threshold value of the distance from the laser point cloud data to the quadric surface as D, and calculating the distance from the laser point cloud data to the quadric surface; if the distance is smaller than D and the maximum height difference of the point cloud data in the grid unit to which the point cloud data belongs is smaller than a threshold value E, judging that the point is a road surface point, and if not, judging that the point is a non-road surface point; and taking the obtained set of all road points as a passable road area to obtain a final road surface detection result.
Further, in the step (3.1), the concrete process of obtaining the road line equation by fitting the data points in the three-dimensional histogram through the RANSAC algorithm is as follows: firstly, randomly selecting two data points to obtain a linear equation, wherein the distance threshold value from a set point to the linear equation is T, and if the distance from the point to the linear equation is less than T, the distance is an inner point; if the distance from the point to the straight line is greater than T, the point is an outer point; and calculating to obtain a linear equation with the most interior points, namely the solved road linear equation.
Further, in the step (4), fitting the point cloud data on the basic contour of the road flat area by using a matlab least square fitting tool bag to obtain a parameter P of the quadric surface0,P1,P2,P3,P4,P5Thus, the following quadratic surface equation is obtained:
f(x,y)＝P0x2+P1y2+P2xy+P3x+P4y+P5
in the formula, X is a coordinate value in the X-axis direction in a Cartesian coordinate system, and Y is a coordinate value in the Y-axis direction in the Cartesian coordinate system; the quadric surface equation is adopted to fit a road surface to meet various scenes such as a simple plane, a complex curved surface and the like.
Further, in the step (5), grid cells in the interested range are selected from the X-Y plane in the grid map, and the maximum difference value of the Z-direction height of the point cloud data in each grid cell is counted.
The invention has the beneficial effects that: the method comprises the steps of constructing a three-dimensional histogram of laser point cloud according to a statistical geometric model of the three-dimensional laser radar point cloud, fitting data points corresponding to a road area in the three-dimensional histogram by using an RANSAC algorithm, and obtaining a road profile through quadratic surface fitting, so that the unstructured road with large road surface fluctuation can be met. In addition, the elevation difference of the grid units is counted by combining a grid map, and the accurate and reliable passable road area is obtained by calculating the distance from the laser point cloud to the road quadric.
Drawings
FIG. 1 is a flow chart of an unstructured road detection method based on a lidar statistical geometric model;
FIG. 2 is a three-dimensional histogram of 64-line lidar data;
FIG. 3 is a graph of results of RANSAC fitting of three-dimensional histograms;
FIG. 4(a) is a graph of the results of a plane equation fit for a road region;
FIG. 4(b) is a graph of a quadratic surface fit result for a road region;
FIG. 5 is a grid map of the laser point cloud;
fig. 6 is a diagram illustrating the practical effect of detecting an unstructured road according to the present invention.
Detailed Description
The following further describes the embodiments of the present invention with reference to the drawings.
As shown in fig. 1, the invention provides an unstructured road detection method based on a laser radar point cloud statistical geometric model, which has the following specific implementation:
wherein H is the height of the laser radar from the ground. FIG. 2 is a three-dimensional histogram of 64-line laser radar data obtained by the present invention.
And 3, screening data of the three-dimensional histogram, and removing interference points with smaller numerical values. Fitting data points of a road flat area in a histogram by using a RANSAC (random sample consensus) straight line fitting algorithm, firstly randomly selecting two points to obtain a straight line equation, wherein a threshold value T from a set point to the straight line equation is 0.1, and if the distance from the point to the straight line is less than T, the point is an inner point; if the distance from the point to the straight line is greater than T, the point is an outer point. Calculating to obtain a linear equation with the most interior points, namely the solved road linear equation:
n＝km+b
according to the experiment, k is 0.2, b is 21.79, n is the laser radar beam, and m is the reciprocal of the positive direction coordinate of the X axis in the Cartesian coordinate system. Because the road flat area is not a perfect plane, a road model tolerance interval is established, and the linear equation of the upper and lower boundaries of the interval is as follows:
n＝km+αb
n＝km+βb
the optimal interval tolerance upper and lower bound parameters are experimentally selected to be alpha 0.5 and beta 1.2.
Projecting the original laser point cloud data to a three-dimensional histogram, and if the data point falls in a tolerance interval of a road straight line, determining that the data point is a road area point; otherwise, if the data point is outside the tolerance interval of the road straight line, the data point is a non-road area point. And counting the laser point clouds in the road straight line tolerance interval to obtain the basic outline of the road flat area. FIG. 3 is a graph showing the results of line fitting according to the present invention.
And 4, fitting the point cloud data of the basic contour of the road flat area by using a least square fitting kit of Matlab to obtain a road quadric equation as follows:
f(x,y)＝P0x2+P1y2+P2xy+P3x+P4y+P5
in the formula P0＝-0.0021，P1＝0.0012，P2＝-1.5926×10-4，P3＝-0.0643，P4＝0.0096,P5-1.7353, parameters obtained from least squares fitting kit using Matlab. The quadratic surface equation can be adopted to fit a scene that the road surface is a complex curved surface. Fig. 4(a) and fig. 4(b) are comparative graphs of the fitting result of the road plane equation and the quadric surface equation obtained by the invention under the same scene.
And 6, through experimental tests, the distance threshold value D from the set point to the quadric surface is 0.2m, and the maximum height difference threshold value E of the grid unit is 0.15 m. And calculating the distance from the laser point cloud to the quadric surface, if the distance is smaller than D and the maximum height difference in the grid unit to which the point belongs is smaller than E, judging that the point is a road surface point, and if not, judging that the point is a non-road surface point. And carrying out the operation on the original laser point cloud to obtain a final road surface detection result. Fig. 6 shows a passable road area finally obtained by the present invention.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (4)
1. A non-structured road detection method based on a laser radar point cloud statistical geometric model is characterized by comprising the following steps: comprises the following steps:
(1) acquiring original three-dimensional point cloud data by using a vehicle-mounted laser radar;
(2) the method comprises the following steps of constructing a laser point cloud three-dimensional histogram by utilizing three-dimensional point cloud data:
(2.1) establishing a Cartesian coordinate system by taking the three-dimensional laser radar as a coordinate origin, wherein the X-axis direction is parallel to the ground and points to the advancing direction of the unmanned vehicle, the Y-axis direction is parallel to the ground and points to the left of the unmanned vehicle, the Z-axis direction is vertical to an X-Y plane, and the direction is vertical to the ground and upwards;
(2.2) reciprocal of coordinate in positive X-axis direction
As a horizontal axis coordinate, and a laser radar line bundle as a vertical axis coordinate, and counting the number of laser radar lines on each laser radar line bundle
The number of scanning points of the positions is used for constructing a laser point cloud three-dimensional histogram;
(3) fitting data points in the three-dimensional histogram to obtain a basic contour of a road flat area, and specifically comprising the following steps of:
(3.1) fitting data points in the three-dimensional histogram by using a RANSAC algorithm to obtain a road line equation:
n＝km+b
in the formula, n is a laser radar wire harness, and m is the reciprocal of the coordinate in the positive direction of the X axis in a Cartesian coordinate system; k and b are parameters of a road linear equation;
(3.2) establishing a road model tolerance interval by using a road linear equation, wherein the linear equation of the upper and lower boundaries of the interval is as follows:
n＝km+αb
n＝km+βb
in the formula, alpha is a parameter for determining the upper limit of the interval tolerance, alpha is less than 1, beta is a parameter for determining the lower limit of the interval tolerance, and beta is more than 1;
(3.3) projecting the original laser point cloud data into the three-dimensional histogram, and if the data points projected into the three-dimensional histogram are within the tolerance interval of the road model, determining the data points as road region points; otherwise, if the data point is out of the tolerance interval of the road model, the data point is a non-road region point;
(3.4) counting laser point cloud data falling in a tolerance interval of the road model by utilizing the corresponding relation between the three-dimensional histogram and the original laser point cloud to obtain a basic outline of a road flat area;
(4) fitting point cloud data on the basic outline of the road flat area by adopting a least square method to obtain a quadric surface equation of the road flat area;
(5) setting grid resolution, obtaining a space grid map under a Cartesian coordinate system, and counting the maximum height difference of all laser point cloud data in each grid unit;
(6) calculating the distance from the laser point cloud data to the quadric surface, and determining a final passable area according to the maximum height difference of the grid unit point cloud data to which the laser point cloud data belongs; the method specifically comprises the following steps: setting the maximum threshold value of the distance from the laser point cloud data to the quadric surface as D, and calculating the distance from the laser point cloud data to the quadric surface; if the distance is smaller than D and the maximum height difference of the point cloud data in the grid unit to which the point cloud data belongs is smaller than a threshold value E, judging that the point is a road surface point, and if not, judging that the point is a non-road surface point; and taking the obtained set of all road points as a passable road area to obtain a final road surface detection result.
2. The unstructured road detection method based on the lidar point cloud statistical geometric model of claim 1, wherein in the step (3.1), the concrete process of obtaining the road straight line equation by fitting the data points in the three-dimensional histogram through the RANSAC algorithm is as follows: firstly, randomly selecting two data points to obtain a linear equation, wherein the distance threshold value from a set point to the linear equation is T, and if the distance from the point to the linear equation is less than T, the distance is an inner point; if the distance from the point to the straight line is greater than T, the point is an outer point; and calculating to obtain a linear equation with the most interior points, namely the solved road linear equation.
3. The unstructured road detection method based on laser radar point cloud statistical geometric model according to claim 1, characterized in that in step (4), a matlab least square fitting tool package is adopted to fit point cloud data on a basic contour of a road flat area to obtain a parameter P of a quadric surface0,P1,P2,P3,P4,P5Thus, the following quadratic surface equation is obtained:
f(x,y)＝P0x2+P1y2+P2xy+P3x+P4y+P5
in the formula, X is a coordinate value in the X-axis direction in a Cartesian coordinate system, and Y is a coordinate value in the Y-axis direction in the Cartesian coordinate system; the quadric equation is adopted to fit the road surface to meet the requirements of simple planes and complex curved surface scenes.
4. The unstructured road detection method based on the lidar point cloud statistical geometric model of claim 1, wherein in the step (5), grid cells in the interested range are selected from an X-Y plane in a grid map, and the maximum difference of the Z-direction heights of the point cloud data in each grid cell is counted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910690051.4A CN110320504B (en) | 2019-07-29 | 2019-07-29 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910690051.4A CN110320504B (en) | 2019-07-29 | 2019-07-29 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110320504A CN110320504A (en) | 2019-10-11 |
| CN110320504B true CN110320504B (en) | 2021-05-18 |
Family
ID=68124775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910690051.4A Active CN110320504B (en) | 2019-07-29 | 2019-07-29 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110320504B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766979A (en) * | 2019-11-13 | 2020-02-07 | 奥特酷智能科技(南京)有限公司 | Parking space detection method for automatic driving vehicle |
| CN113077473A (en) * | 2020-01-03 | 2021-07-06 | 广州汽车集团股份有限公司 | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium |
| CN111208530B (en) * | 2020-01-15 | 2022-06-17 | 北京四维图新科技股份有限公司 | Positioning layer generation method and device, high-precision map and high-precision map equipment |
| CN115151954A (en) * | 2020-02-29 | 2022-10-04 | 华为技术有限公司 | Method and device for detecting a drivable region |
| CN113496491B (en) * | 2020-03-19 | 2023-12-15 | 广州汽车集团股份有限公司 | Road surface segmentation method and device based on multi-line laser radar |
| CN111445578B (en) * | 2020-03-27 | 2023-03-10 | 清华大学 | Map three-dimensional road feature identification method and system |
| CN111580131B (en) * | 2020-04-08 | 2023-07-07 | 西安邮电大学 | Method for identifying vehicles on expressway by three-dimensional laser radar intelligent vehicle |
| CN111766608A (en) * | 2020-06-12 | 2020-10-13 | 苏州泛像汽车技术有限公司 | Environmental perception system based on laser radar |
| CN111985322B (en) * | 2020-07-14 | 2024-02-06 | 西安理工大学 | Road environment element sensing method based on laser radar |
| CN112149572A (en) * | 2020-09-24 | 2020-12-29 | 知行汽车科技（苏州）有限公司 | Road edge detection method, device and storage medium |
| CN112543938B (en) * | 2020-09-29 | 2022-02-08 | 华为技术有限公司 | Generation method and device of grid occupation map |
| CN112731436B (en) * | 2020-12-17 | 2024-03-19 | 浙江大学 | Multi-mode data fusion travelable region detection method based on point cloud up-sampling |
| CN113253294A (en) * | 2021-06-16 | 2021-08-13 | 北京海天瑞声科技股份有限公司 | Method, apparatus and medium relating to ground point detection in 3D radar point cloud data |
| CN114359866A (en) * | 2021-12-31 | 2022-04-15 | 中国第一汽车股份有限公司 | Road boundary detection method and device based on laser radar |
| CN114842450B (en) * | 2022-05-11 | 2023-06-30 | 合众新能源汽车股份有限公司 | Method, device and equipment for detecting drivable area |
| CN115542301B (en) * | 2022-11-24 | 2023-04-07 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Method, device and equipment for calibrating external parameters of laser radar and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103777204A (en) * | 2014-01-09 | 2014-05-07 | 中北大学 | Range finding device and range finding method based on target tracking and recognizing by photoelectric intelligent sensing platform |
| CN104484882A (en) * | 2014-12-24 | 2015-04-01 | 哈尔滨工业大学 | City region power line detection method based on airborne LiDAR (light detection and ranging) data |
| CN105404844A (en) * | 2014-09-12 | 2016-03-16 | 广州汽车集团股份有限公司 | Road boundary detection method based on multi-line laser radar |
| CN106529493A (en) * | 2016-11-22 | 2017-03-22 | 北京联合大学 | Robust multi-lane line detection method based on perspective drawing |
| JP2017060524A (en) * | 2016-12-21 | 2017-03-30 | ジオサーフ株式会社 | Field guidance system and field guidance method as well as software and storage medium with software stored therein |
| CN106991389A (en) * | 2017-03-29 | 2017-07-28 | 蔚来汽车有限公司 | The apparatus and method for determining road edge |
| CN107923850A (en) * | 2015-05-20 | 2018-04-17 | 宽腾矽公司 | Pulse laser and bio-analysis system |
| KR101871441B1 (en) * | 2018-02-27 | 2018-06-27 | 뉴비전엔지니어링(주) | Voice recognition field survey and road linear generation system for high definition electronic map production for autonomous vehicle |
| CN108226951A (en) * | 2017-12-23 | 2018-06-29 | 天津国科嘉业医疗科技发展有限公司 | A kind of quick moving obstacle method for real time tracking based on laser sensor |
| CN109684921A (en) * | 2018-11-20 | 2019-04-26 | 吉林大学 | A kind of road edge identification and tracking based on three-dimensional laser radar |
-
2019
- 2019-07-29 CN CN201910690051.4A patent/CN110320504B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103777204A (en) * | 2014-01-09 | 2014-05-07 | 中北大学 | Range finding device and range finding method based on target tracking and recognizing by photoelectric intelligent sensing platform |
| CN105404844A (en) * | 2014-09-12 | 2016-03-16 | 广州汽车集团股份有限公司 | Road boundary detection method based on multi-line laser radar |
| CN104484882A (en) * | 2014-12-24 | 2015-04-01 | 哈尔滨工业大学 | City region power line detection method based on airborne LiDAR (light detection and ranging) data |
| CN107923850A (en) * | 2015-05-20 | 2018-04-17 | 宽腾矽公司 | Pulse laser and bio-analysis system |
| CN106529493A (en) * | 2016-11-22 | 2017-03-22 | 北京联合大学 | Robust multi-lane line detection method based on perspective drawing |
| JP2017060524A (en) * | 2016-12-21 | 2017-03-30 | ジオサーフ株式会社 | Field guidance system and field guidance method as well as software and storage medium with software stored therein |
| CN106991389A (en) * | 2017-03-29 | 2017-07-28 | 蔚来汽车有限公司 | The apparatus and method for determining road edge |
| CN108226951A (en) * | 2017-12-23 | 2018-06-29 | 天津国科嘉业医疗科技发展有限公司 | A kind of quick moving obstacle method for real time tracking based on laser sensor |
| KR101871441B1 (en) * | 2018-02-27 | 2018-06-27 | 뉴비전엔지니어링(주) | Voice recognition field survey and road linear generation system for high definition electronic map production for autonomous vehicle |
| CN109684921A (en) * | 2018-11-20 | 2019-04-26 | 吉林大学 | A kind of road edge identification and tracking based on three-dimensional laser radar |
Non-Patent Citations (3)
| Title |
|---|
| "MULITSPECTRAL IMAGE COMPRESSION BY CLUSTER ADAPTIVE SUBSPACE REPRESENTATION";HuiLiang Shen 等;《Proceedings of 2010 IEEE 17th International Conference on Image Processing》;20100929;第521-524页 * |
| "基于视点特征直方图的激光点云模型的位姿估计";张彪 等;《光电子.激光》;20130731;第24卷(第7期);第1357-1362页 * |
| "基于车载激光点云数据的路面检测与重建";谭敏;《测绘与空间地理信息》;20150731;第38卷(第7期);第115-118页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110320504A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110320504B (en) | Unstructured road detection method based on laser radar point cloud statistical geometric model | |
| CN105404844B (en) | A kind of Method for Road Boundary Detection based on multi-line laser radar | |
| CN108873013B (en) | Method for acquiring passable road area by adopting multi-line laser radar | |
| CN109858460B (en) | Lane line detection method based on three-dimensional laser radar | |
| Zheng et al. | Improved lane line detection algorithm based on Hough transform | |
| CN109186625B (en) | Method and system for accurately positioning intelligent vehicle by using hybrid sampling filtering | |
| CN103226833B (en) | A kind of point cloud data segmentation method based on three-dimensional laser radar | |
| CN109188459B (en) | Ramp small obstacle identification method based on multi-line laser radar | |
| CN110490888B (en) | Highway geometric feature vectorization extraction method based on airborne laser point cloud | |
| CN108828621A (en) | Obstacle detection and road surface partitioning algorithm based on three-dimensional laser radar | |
| CN108460416A (en) | A kind of structured road feasible zone extracting method based on three-dimensional laser radar | |
| CN106199558A (en) | Barrier method for quick | |
| CN109031346A (en) | A kind of periphery parking position aided detection method based on 3D laser radar | |
| CN112184736B (en) | Multi-plane extraction method based on European clustering | |
| CN113345008B (en) | Laser radar dynamic obstacle detection method considering wheel type robot position and posture estimation | |
| CN111325138B (en) | Road boundary real-time detection method based on point cloud local concave-convex characteristics | |
| CN109597097A (en) | Scan-type obstacle detection method based on multi-thread laser | |
| CN115049700A (en) | Target detection method and device | |
| CN111354083B (en) | Progressive building extraction method based on original laser point cloud | |
| CN114051628B (en) | Method and device for determining target object point cloud set | |
| CN114488190A (en) | Laser radar 3D point cloud ground detection method | |
| CN114821526A (en) | Obstacle three-dimensional frame detection method based on 4D millimeter wave radar point cloud | |
| CN114638934A (en) | Post-processing method for dynamic barrier in 3D laser slam graph building | |
| Zhu et al. | A real-time road boundary detection algorithm based on driverless cars | |
| CN112034482A (en) | Road boundary real-time extraction and measurement method and device |
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 |