Lane line identification method, device and equipment and storage medium

Abstract

The invention relates to the technical field of image processing, and provides a lane line identification method and device, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing and edge detection of a lane image, so as to obtain the position coordinates and direction angle of an edge point; Acquiring the position of the vanishing line in the coordinate system; according to the candidate vanishing point coordinates on the vanishing line and the position coordinates and direction angles of the edge points, voting the candidate vanishing points in avoting function to determine vanishing point coordinates, and according to the number of the edge points of different direction angles recorded by the candidate vanishing points, sorting to obtain parameter information of a straight line; performing Confidence coefficient calculation according to the parameter information of the straight line to obtain a reference lane line; According to the technical scheme, the fuzzy lane line edge can be effectively detected, noise can be restrained, the detection time of the vanishing point and the straight line is short, the accuracy is high, and the laneline recognition real-time performance is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a lane line recognition method, device, equipment and storage medium. Background technique [0002] With the popularization of automobiles, the use of sensors to improve the ability to identify road objects and provide drivers with more safety warnings and assistance, thereby improving the active safety of vehicles, has become an important direction for the development of intelligent transportation systems. At present, in the lane line recognition, the lane line is mainly described by the straight line model, and the straight line recognition is carried out through the Hough transform. This method can effectively identify the straight lane line, but the effect on the curve recognition is poor, and it is not good for the higher order of the lane maintenance. For driving assistance functions, using a straight line model to describe lane lines is not enough for use....

AI Technical Summary

Problems solved by technology

At present, in the lane line recognition, the lane line is mainly described by the straight line model, and the straight line recognition is carried out through the Hough transform. This method can effectively identify the straight lane line, but the effect on the curve recognition is poor, and it is not good for the higher order of the lane maintenance. For driving assistance functions, using a straight line model to describe lane lines is not enough for use. There are a lot of interference points in the detection of lane lines, especially in various road conditions, which reduces the accuracy of lane detection.

Images