Research on Lane Line Detection Method Based on Improved Hough Transform

摘要

Lane line is an important reference for safe driving. In order to improve the accuracy and real-time performance of lane line detection, a lane line detection algorithm based on improved Hough transform is proposed in this paper. Firstly, the lifting algorithm of wavelet is used to extract the low-frequency wavelet coefficients of the image, so as to reduce the complexity of the image and improve the efficiency of image processing; Then Canny operator is used to detect the edge of the image region of interest, and threshold is automatically selected according to edge information for threshold processing; Finally, three constraints are proposed from two aspects of angle and lane width to improve the Hough transform to detect lane lines, and the correct lane lines are fitted by linear regression method. Experiments show that the proposed algorithm has good correctness and real-time performance for lane line detection. The recognition accuracy is above 94% and the average processing time of each frame is 25.6ms.