-
Notifications
You must be signed in to change notification settings - Fork 1
Home
Basic pipeline works OK on straight roads like highways but performs very poorly on curves or shaded roads. It detects the road line segments, then extrapolates them and draws them onto the image for display. Within the pipeline some of the tools used are: color selection, region of interest selection, grayscaling, Gaussian smoothing, Canny Edge Detection and Hough Transform line detection.
This pipeline detects lane lines in a variety of conditions, including changing road surfaces, curved roads, and variable lighting. It contains a series of functions using polynomial fits, and splines that can help identify, draw and Measure Curvature of the road lane lines from images and video. It successfully identifies road lines using histogram along all the columns in the lower half of a perspective transform image, sliding windows and fit a polynomial.