Detecting and tracking method for lane lines of autonomous vehicle navigation

Abstract

The invention discloses a detecting and tracking method for lane lines of autonomous vehicle navigation. The method comprises firstly converting video frames into grayscale images, describing a tight degree of local connection of each point in the images through fuzzy connection degree and membership function, and extracting general contour of roads; secondly, extracting edges by using a Canny operator, refining the images by using a refinement algorithm and detecting control points of the road edges; and thirdly, fitting the edge points of the roads by using a non-uniform B-spline interpolation (NUBS), that is, calculating the fitting points by using controlling points. Experimental results show that the method takes grayscale of the roads and gradient characteristics into account, and thus reduces interferences of shadows or other noises and is relatively high in accuracy. A probability of successful detection of the lane lines is 92 % for detection of 50 images.

Description

technical field [0001] The invention relates to a self-guiding method for intelligent vehicles, in particular to a lane detection and tracking method for self-navigating vehicles capable of handling arbitrary curved roads. Background technique [0002] In recent years, with the rapid development of my country's economic construction, the urban population and transportation are also booming. These developments have greatly promoted the convenience of personnel and material exchanges, and have also produced increasingly prominent negative Effects, such as frequent traffic congestion, road blockage and traffic accidents, etc., these negative effects are more and more seriously plagued the traffic in major cities. According to the investigation report of my country's traffic conditions in recent years, the death rate caused by traffic accidents in my country is much higher than that of developed countries and some developing countries. In response to the above-mentioned increasi...

AI Technical Summary

Problems solved by technology

However, this method still has the following disadvantages: first, the storage capacity required by the Hough transform is large, once the parameter space increases, the amount of calculation will increase sharply, and at the same time consume a huge amount of storage space; second, the huge amount of calculation will also increase As a result, the detection speed is too slow to achieve real-time control; third, the accuracy is not high enough, and the expected information cannot be detected and wrong judgments are made instead, resulting in a large amount of redundant data; fourth, image space and parameter space need to be One-to-many mapping and exhaustive search operation, so the time and space complexity required for its calculation are high, thus increasing the time of lane line detection

Images