A Real-Time Rear Obstacle Detection System Based On a Fish-Eye Camera

This paper proposes a rear vision camera-based vehicle detection system which could detect if any rear vehicle exists in ego lane and if any vehicles in adjacent lanes are overtaking. The source image is firstly applied with distortion calibration which helps the following Hough transform to detect the existence of lane lines. The rear vehicle in ego lane is detected by a combination of feature-based approach and appearance-based approach. When a vehicle in adjacent lane is overtaking, the vanishing of its symmetry makes itself very difficult to be detected. Therefore, we propose a new detection algorithm applying corner detection and motion vector whose calculation are based on Local Binary Pattern (LBP) to find if any vehicles in adjacent lanes are overtaking. Our proposed algorithm achieves high detecting rate and low computing power and is successfully implemented in ADI-BF561 600MHz dual core DSP.