Lane line recognition method, device and computer-readable storage medium

Abstract

The invention discloses a lane line recognition method. When the edge strength and direction corresponding to the edge point set of the lane line image are acquired, the starting point is determined based on the edge strength; and then all pairs of pairs are determined based on the starting point. The first point set and the second point set, and calculate the similarity of each pair of the first point set and the second point set; then sort the similarity to determine the target lane line. The invention also discloses a lane line recognition device and a computer-readable storage medium. This method can detect the lane line in the original lane line image without distortion correction, and correct the edge direction of the adjacent area by using the distortion coefficient during the detection process, which solves the problem of excessive stretching of some areas in the prior art and the formation of false lane lines The edge and the problem that affects the overall detection make full use of the similarity of the direction of the edge points of the lane line and the opposite direction of the edge of the opposite lane, which can remove the interference of non-related edges and improve the accuracy of lane line recognition.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a lane line recognition method, device and computer-readable storage medium. Background technique [0002] Lane line recognition is a very important technology for vehicle-mounted intelligent devices such as driving recorders. At the same time, lane line recognition is also a basic problem in unmanned driving or high-precision maps. Among them, the camera is one of the very important hardware devices, including the fisheye camera. Currently, lane line recognition is usually based on a lens with less distortion. When using a fisheye camera to identify lane lines, it is usually necessary to perform distortion correction on the lane line image captured by the fisheye camera. However, the image after distortion correction often appears in certain areas due to insufficient sampling rate and other reasons. Therefore, it is necessary to propose a method for lane line ...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a lane line recognition method, device and computer-readable storage medium, aiming to solve the technical problem of lane line detection in the original lane line image

Images