International Research Journal of Education and Technology

Road Lane detection plays a vital role in the Advanced Driver assistive systems and it improves the vehicle's safe driving. However, Road lane detection is a complex problem because of the varying road conditions that one can encounter while driving. In this project, a vision based lane detection approach capable of reaching realtime operation with robustness to lighting change and shadows is presented. The lane boundaries, lane direction and its radius of curvatures were detected from a stream of videos. The video is recorded from a camera mounted on the top of a vehicle. We have corrected the camera distortion in the input frame. HLS thresholding and Canny edge thresholding techniques are carried out to the undistorted image for getting focus on the lane lines in the binary image. Then the resulted frame is warped into the bird’s eye by applying the perspective transformation technique. The respective lane line pixels are identified using sliding window approach and then left and right lane lines are identified by fitting second-degree polynomials. The lane curvature and deviation from the lane centre are also computed after the identification of the lane. The identified lane boundaries are warped back onto the input image and the radius of lane curvature and vehicle position is calculated and displayed with appropriate comments. Hence this technique is enforced using python programming language and for processing the images Open CV is used.

Keywords—Advanced Driver assistive systems, HLS thresholding, Canny edge thresholding, binary image, perspective transformation, sliding window, second-degree polynomial, python programming, Open CV.