Real-time fuzzy vehicle detection based on contour size similarity

In this paper, a real time obstacle detection algorithm based on Contour Size Similarity (CSS) for autonomous vehicles is carried out by a single camera, which is capable of detecting multiple obstacles, identifying the difference between obstacles and patterns or shadows on the surface of the road. The task of detection can be fulfilled under the circumstances of general brightness or in the presence of strong sunshine. CSS makes use of the contour size of objects and compares the similarity between objects and obstacles detected by fuzzy rules in order to judge whether the objects in the images are the obstacles to be detected. Vehicles and obstacles with similar contour of vehicles can be detected by CSS. Then, the nearest obstacles can be found by section division and compute the distance to provide the necessary information for autonomous vehicles. The result can be applied to an advanced safety vehicle or vehicle detector as traffic information.