Vision-Based Extrapolation of Road Lane Lines in Controlled Conditions

Keeping vehicle in the right track while driving is common task for humans, as they perceive lane lines with ease. Naturally, one of the essential tasks for autonomous vehicle would be to detect lane lines. Except for using them as constant reference in steering controller, they are used as inputs in other driver assistance functions like lane departure warning, for example. Different road and weather conditions make it difficult to detect lane lines, as marking can become indistinct or disappear. Many simple vision-based algorithms rely on detection of edges of the markings with Canny edge detection and previously mentioned problems can affect proper extrapolation of lanes. This paper also belongs to vision-based group of algorithms that use camera. It presents usage of color thresholding to detect lane edges and together with perspective transformations and Hough transform to extrapolate lane segments in image with controlled conditions. These conditions include straight road and sunny weather. We used OpenCV computer vision framework that supports mentioned functionalities and algorithms, with Python, to obtain and compare results.