Unlock instant, AI-driven research and patent intelligence for your innovation.

Lane line extraction method based on vehicle-mounted laser point cloud

A vehicle-mounted laser and extraction method technology, applied in image data processing, instruments, calculations, etc., can solve problems such as the inability to meet the requirements of lane line extraction, and achieve the effects of improving stability, improving efficiency, and reducing irregular arrangement

Pending Publication Date: 2021-03-26
CENTRAL UNIVERSITY OF FINANCE AND ECONOMICS
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing methods are still unable to meet the requirements of lane line extraction under complex road conditions in large-scale cities. This application provides a lane line extraction method based on vehicle-mounted laser point clouds

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
  • Lane line extraction method based on vehicle-mounted laser point cloud
  • Lane line extraction method based on vehicle-mounted laser point cloud
  • Lane line extraction method based on vehicle-mounted laser point cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] This application proposes a method for extracting lane lines based on vehicle-mounted laser point clouds for urban road networks based on vehicle-mounted laser scanning point clouds. In order to achieve the above goals, the application adopts the following technical solutions:

[0051] A kind of lane line extraction method based on vehicle-mounted laser point cloud of urban road network based on vehicle-mounted laser scanning point cloud, comprises the following steps:

[0052] S1. Carry out coordinate transformation on the original point cloud based on the driving trajectory data and the coordinate system conversion function to obtain the point cloud data of coordinate transformation; S2. Perform voxel-based segmentation processing on the point cloud data of the coordinate transformation to remove non-road points Cloud data; S3. Based on the road design standard, detect the road boundary line and extract the road surface to obtain road surface point cloud data; S4. Den...

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 belongs to the technical field of intelligent transportation, and particularly relates to a lane line extraction method based on vehicle-mounted laser point cloud. An existing method cannot meet the lane line extraction requirement under the large-scale urban complex road condition. The invention provides a lane line extraction method based on vehicle-mounted laser point cloud, and the method comprises the following steps: 1), carrying out the coordinate conversion of original point cloud, and obtaining point cloud data of coordinate conversion; 2) processing the point cloud data, and removing non-road surface point cloud data; 3) extracting road surface point cloud data; 4) denoising the road surface point cloud data, and extracting a road marker line; and 5) performing laneline extraction on the pavement point cloud data, and generating a road center line to obtain a complete urban road lane line. According to the invention, the lane lines of the large-scale urban complex road network can be extracted quickly and accurately.

Description

technical field [0001] The present application belongs to the technical field of intelligent transportation, and in particular relates to a lane line extraction method based on a vehicle-mounted laser point cloud. Background technique [0002] As an important part of the intelligent transportation system and smart city, the urban traffic road network lane line needs periodic monitoring and maintenance. Its intelligent supervision effectively guarantees the accuracy of high-definition maps and the reliability of automatic driving. Traditional urban road lane line extraction methods based on vehicle-mounted laser point clouds are mainly divided into two methods: manual field measurement and digital photogrammetry. The manual operation method is to assign road patrol personnel to manually detect the road lane lines to ensure that the lane line markings are clear, complete, and undamaged. However, this method is subject to factors such as high labor costs, complex and dangerous ...

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): G06T7/136G06T5/00G06T7/66
CPCG06T7/136G06T7/66G06T2207/10028G06T2207/30256G06T2207/30241G06T5/70
Inventor 马凌飞李军陈一平
Owner CENTRAL UNIVERSITY OF FINANCE AND ECONOMICS