Lane line type detection method and early warning device

Abstract

The lane line type detection method comprises the following steps: (1) shooting a road surface in front of a vehicle body to obtain a road surface image; (2) obtaining a region-of-interest image fromthe pavement image, and performing the following two operations on the region-of-interest image: 1, converting the region-of-interest image into a grayscale image, and then performing image convolution filtering on the grayscale image so as to obtain an edge grayscale image; 2, converting an original RGB image of the region-of-interest image into a Lab color space image; (3) performing line segmentation on the edge grayscale image to obtain multiple lines of segmented images; and respectively identifying lane line marks for each row of segmented images, combining the lane line marks into a complete fitting lane line, and finally performing lane line classification according to the fitting lane line and the Lab color space image. According to the method, various illumination environments can be dealt with, the efficiency can be improved, the calculated amount can be reduced, the error rate can be reduced, an actual lane can be fitted more accurately than a straight line, yellow and white can be distinguished well, the lane line category recognition rate can be improved, and lane lines with different features can be recognized.

Description

technical field [0001] The invention relates to the field of electronic information, in particular to a detection method and an early warning device for lane line types. Background technique [0002] With the development of road transportation, there are more and more types of lane lines on the road surface. In common actual road conditions, lane lines can be distinguished in the following categories: (1) dashed line: white single dashed line, yellow single dashed line, white double dashed line, yellow double dashed line (tidal lane line); (2) solid line: white single solid line Line, yellow single solid line, white double solid line, yellow double solid line; (3) dotted line + solid line: inner dotted line + outer solid line (white), inner solid line + outer dotted line (white), middle dotted line + both sides Dotted line (white), solid line in the middle + dotted lines on both sides (white). [0003] In the prior art, a binary image of an edge is obtained by filtering a ...

AI Technical Summary

Problems solved by technology

However, the existing technology generally uses a straight line to fit the lane line, which has obvious limitations for the road conditions of the curve.

[0005] In order to break through the above limitations, or use the method of deep learning to detect lanes, this method requires a large amount of labeled data for training, and at the same time requires high hardware requirements for algorithm operations

[0006] Moreover, the above methods in the prior art do not distinguish the detected lane line categories in detail, so that it is impossible to provide warning reminders that are more in line with traffic rules for various actual lane line conditions.

Images