Lane line historical frame recognition method

Abstract

The invention discloses a lane line historical frame recognition method. The method comprises performing Gaussian filter preprocessing on acquired road images and performing adverse projection on the images to be converted into airscapes; performing binarization processing on the airscapes through an adaptive threshold binarization method and performing Hough transformation on the airscapes to extract lines; determining which lines in Hough transformation results are lane lines based on the line angle LX.theta, the line distance LX.rho, the line ticket number LX.V and the line initial point distance LX.S of each line LX, wherein X =1, 2, ......N and the space and positions of the lane lines obtained in the previous period. By the aid of the method, interferences of complex road conditions of characters, multiple interference lines, shadow shielding, lane line damage, stain coverage and the like are removed effectively, and the recognition rate and the stability of lane lines are improved greatly; the method can be widely applied to car safety auxiliary driving systems to assist drivers for the maintaining of traveling of cars in the lanes in the monotonous driving environment.

Description

technical field [0001] The invention relates to a lane line recognition method, in particular to a lane line history frame based recognition method. Background technique [0002] With the rapid development of the national economy, the continuous construction and completion of various highway mileages in our country, the number of cars has also been continuously increased, so that traffic accidents have also shown an increasing trend. In order to reduce traffic accidents, people try to install various safety devices on cars, such as a lane line feature extraction and recognition method for complex road conditions announced by Chinese invention patent CN102592114B on July 31, 2013. The method described in this patent first converts the color road image into a grayscale image and performs median filtering; then, divides the filtered image into the region of interest, and applies the symmetrical local threshold segmentation method to segment the road in the region of interest. ...

AI Technical Summary

Problems solved by technology

Although this patent can quickly and effectively detect lane lines, there are also shortcomings. First, due to the influence of the camera imaging principle, the lane lines in the image appear to be near wide and far narrow, and symmetrical local threshold segmentation is used. When the binarization method is used, the C value is calculated from the pixel width of the intact lane line measured under normal conditions, which is different from the pixel width of the lane line when the vehicle is driving. The ever-changing actual discrepancies lead to the effect of binarization being greatly negatively affected by the value of c; secondly, the premise of using the de-correlation RANSAC method to correctly identify lane lines is that the number of lane line feature points must be the most after binarization processing, if When the feature points of the interference line after binarization are greater than the number of lane lines, misrecognition will occur, and it is difficult to recognize the correct left and right lane lines when there are many words or interference lines near the lane line; Make any restrictions on the existence of lane lines. If there is no lane line in the left or right area of ​​interest, but there is an interference line, then misidentification will occur.

Images