Lane line extraction method and device

Abstract

The invention relates to a lane line extraction method. The method comprises the following steps: three dimensional laser point cloud data is obtained and analyzed, road border lines are extracted and obtained from the three dimensional laser point cloud data, points at the middle of the two road border lines are used as candidate point cloud set for a lane line, a highlight point image is generated according to reflectivity of each candidate point in the candidate point cloud set for the lane line, wheelpath data is obtained, object highlight points in the highlight point image are screened according to a special relationship between the wheelpath data and three dimensional laser point cloud data, and a lane line is obtained after straight line extraction operation is performed. Lane line extraction speed and lane line extraction accuracy are improved, the object highlight points are screened based on the wheelpath data, the lane line is obtained after the straight line extraction operation is performed, the lane line can be obtained accurately and conveniently, and a lane line extraction device is also provided.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for extracting lane lines. Background technique [0002] With the development of computer technology and automation technology, automatic driving technology has received high attention. Automatic driving technology cannot be separated from the support of high-precision maps. How to generate high-precision maps has become one of the bottlenecks of automatic driving. High-precision lane lines are also very important as an important part of high-precision maps. [0003] Existing lane line extraction methods are often based on images or videos, and have the following disadvantages: first, they are sensitive to light, and the gray values ​​of the generated images of lane lines are different under different lighting conditions, which increases the speed of lane line extraction. Secondly, the extraction accuracy is not high. Extracting three-dimensional lane line ...

AI Technical Summary

Problems solved by technology

[0003] Existing lane line extraction methods are often based on images or videos, and have the following disadvantages: first, they are sensitive to light, and the gray values ​​of the generated images of lane lines are different under different lighting conditions, which increases the speed of lane line extraction. Secondly, the extraction accuracy is not high. Extracting three-dimensional lane line information from two-dimensional images usually regards the road surface as a plane, but the actual road surface is usually not a plane, which leads to the problem of low extraction accuracy.

Images