Atena Sadat Kalaki - Computer Engineering and Information Technology Department AmirKabir University of Technology Tehran, Iran
Reza Safabakhsh - Computer Engineering and Information Technology Department AmirKabir University of Technology Tehran, Iran

In order to gain higher efficiency in obstacle avoidance task in autonomous vehicles from the aspect of processing cost and operating in real-time, it`s critical to find aregion of interest (ROI) which obstacles are more possible to appear and degrade the obstacle`s search zone to it. In this paperwe propose novel methods to find this ROI using computer vision technologies. The road scenes are acquired with a monocular camera. Current lane of autonomous vehicle is recognized bydetection of lane markings. Adjacent lanes are also estimated based on some geometric calculations. A novel lane matchingmechanism is suggested to validate detected lane markings. Finally a method for lane departure warning is proposed. Theexperimental results show that the proposed algorithms correctly find lanes region with high accuracy in real-time, are robust tonoise and shadows, testing on Hemmat highway in Tehran and another dataset in the daytime

Lane detection; Current lane; Adjacent lane; Lane matching; Lane departure warning