A lane line detection method

Abstract

The present invention relates to a lane line detection method, wherein the method includes: acquiring an image in front of the vehicle, converting the image into a grayscale image; using the grayscale information of the image to roughly locate the lane line, And record the coarse positioning points; perform fine positioning on the coarse positioning points, and retain the fine points; classify the fine points to obtain multiple straight line classes; obtain the lane line according to the multiple straight line classes. The technical scheme of the present invention performs down-sampling on the entire image in vertical strips and blocks, and utilizes the characteristics of vertical arrangement when detecting edges. The horizontal direction of the lanes in each strip changes drastically, and the suspicious edge points of the lanes are determined, and then the suspicious edge points are determined. Points are processed, so the amount of calculation is reduced, and interference points can be eliminated to improve the real-time performance of the algorithm and the reliability of the lane.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a lane line detection method. Background technique [0002] With the rapid development of automobile assisted driving and unmanned vehicle technology, whether the machine vision sensor can accurately obtain the signs, signs or lane line information around the vehicle is the most important part of the automobile assisted driving system, among which the real-time detection and early warning of lane lines Technology ensures that vehicles can go their own way, and plays an important role in departure warning and lane keeping. [0003] At present, in the research of lane line detection, lanes are mainly divided into straight line model, quadratic curve model or segment switching model, etc. In the straight line model, most of them use the edge search method to detect the edge of the lane first, and then use the Hough transform to identify the lane. The edge sear...

AI Technical Summary

Problems solved by technology

In addition, since this method only removes the image background block area from a global perspective, it does not substantially reduce the interference of non-lane information. This method is not applicable when the image collected by the sensor itself does not contain a large area of ​​background area.

Images