Supercharge Your Innovation With Domain-Expert AI Agents!

Road boundary detection method

A boundary detection and road technology, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems of discontinuous length, irregular shape, and inability to filter out road vehicle interference.

Pending Publication Date: 2021-09-10
北京踏歌智行科技有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the problems that most of the existing road boundary detection algorithms are oriented to structured roads with obvious road boundaries and cannot filter out vehicle interference in the road, the present invention proposes a laser radar road boundary detection method suitable for unstructured roads in mining areas. The detection method of the present invention can detect road boundaries with irregular shapes, non-uniform heights, and discontinuous lengths, and can filter out disturbances such as vehicles and pedestrians in the road

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Road boundary detection method
  • Road boundary detection method
  • Road boundary detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as Figure 1-2 As shown, a road boundary detection method, the lidar is installed on the self-driving mine car for real-time detection of road boundaries, the method includes the following steps:

[0045] S1: Input the point cloud of the lidar, after preprocessing and ground detection, obtain the obstacle point cloud, which includes road boundaries and other obstacles;

[0046] S2: Carry out road boundary detection through the obstacle point cloud obtained in step S1 and the inputted forward planning path point;

[0047] S2-1: According to the input forward planning path point P 0 , P 1 ,...,P n , where P 0 , P1 ,...,P n P, P is the set of planned path points ahead, the straight line P 0 P 1 , straight line P 1 P 2 ,..., straight line P n-1 P n Respectively constitute the adjacent path point straight line L i , i=0,1,...,n-1, the length of each straight line is N, in this embodiment N=3m, calculate the straight line L respectively 0 ~ L n-1 The ortho...

Embodiment 2

[0059] Such as Figure 9 (a) is the point cloud effect on the straight road, the left and right convex parts are the road boundary, the middle is the road area, and the left front is a car. Adopt the method of the present invention to carry out road boundary detection, the result obtained is as shown in the figure, wherein, Figure 9 (b) is the road boundary detected according to the planned path point and combined with the road width distribution information, which can filter out the interference of the left front car on the boundary. Figure 9 (c) A section of boundary detection is discontinuous due to the occlusion of the car, and the occluded road boundary is complemented by interpolation of the front and rear boundary points. Figure 9 (d) is to apply a quadratic curve to fit the detected road boundaries to obtain smooth boundary points.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a mining area road boundary detection method based on a few-wire-harness laser radar, and the method comprises the steps: inputting a point cloud of the laser radar, and obtaining an obstacle point cloud which comprises a road boundary and other obstacles after preprocessing and ground detection; performing road boundary detection by obtaining obstacle point cloud and planned front path points; and obtaining road boundaries and obstacles through detection. Through the technical scheme of the invention, road boundaries with irregular shapes, non-uniform heights and discontinuous lengths can be detected, and interferences of vehicles, pedestrians and the like in roads can be filtered out. The detection method has the advantages of being high in detection accuracy, good in real-time performance, high in robustness and the like.

Description

technical field [0001] The invention belongs to the technical field of road boundary detection, in particular to a laser radar road boundary detection method suitable for unstructured roads in mining areas. Background technique [0002] Road boundary detection is an important part of the environment perception of autonomous driving vehicles. It divides the perceived environment into drivable area roads, road boundaries and environments outside the road boundaries. It can assist vehicle positioning, and can identify road areas, reduce the perception range, and improve environment perception. Subsequent processing efficiency and accuracy. [0003] The commonly used sensors for road boundary detection include millimeter-wave radar, camera and lidar. Millimeter-wave radar can detect the position and speed of the target, but the ranging error is large; the camera has rich texture information, but is greatly affected by light; the laser radar can It measures distance accurately a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/13G06K9/00
CPCG06T7/13G06T2207/10028G06T2207/30256
Inventor 李华志黄立明张娜余贵珍
Owner 北京踏歌智行科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com