Vision based obstacle detection and collision risk estimation of an unmanned surface vehicle

This paper proposes vision based collision risk estimation method for an unmanned surface vehicle. Vision based target motion analysis was performed to transform vision information of obstacles into motion information. In vision based target motion analysis, camera model and optical flow are adopted. Collision risk was calculated by fuzzy estimator which uses target motion information and vision information as input variables. To validate suggested collision risk estimation method, an unmanned surface vehicle experiment was performed.