Lane line recognition method and device, electronic equipment and storage medium

Abstract

The invention discloses a lane line recognition method and device, electronic equipment and a storage medium. The lane line identification method comprises the following steps of: starting from a position close to a vehicle end, sequentially judging whether discrete interested points on each row in an interested area of a lane line are background points one by one; if the point is not the background point, creating a sliding window containing the point; judging whether the adjacent discrete interested points of the foreground point are background points or not and whether the category of the adjacent discrete interested points is the same as the category of the foreground point in the current sliding window or not; if so, increasing the current sliding window; and if the adjacent discreteinterested points are background points, obtaining a local maximum point based on each foreground point in the current sliding window. According to the lane line recognition method, the post-processing time of lane line detection is greatly shortened, so that the required lane line information can be provided for a user in time, and traffic accidents can be effectively prevented.

Description

technical field [0001] The present disclosure relates to the field of deep learning, and in particular to a method, device, electronic device and storage medium for lane line recognition through deep learning. Background technique [0002] How to effectively prevent traffic accidents is a major focus of social attention. In terms of traffic accident prevention, lane line detection technology can effectively reduce the risk of traffic accidents caused by fatigue driving, novice driving, and automatic driving because it can detect and identify lane lines in advance and present them to users. Therefore, lane line detection is an important research field in automatic driving or assisted driving. [0003] At present, deep learning technology has made great breakthroughs in the image field. Some people in the industry have proposed to detect and identify (post-processing) lane lines by using deep learning. Location. [0004] However, in the existing lane line detection methods...

AI Technical Summary

Problems solved by technology

[0012] It can be seen that the above-mentioned fitting processing steps are very complicated, so it is also very time-consuming

The result of the too long time spent in the fitting process will be that the lane line information cannot be presented to the user quickly and in a timely manner, which will obviously affect the user's use and seriously hinder the effective avoidance of traffic accidents

Images