ROAD REGION ESTIMATION AND OBSTACLES EXTRACTION USING A MONOCULAR CAMERA

An obstacles detection method is proposed which employs a camera mounted on a vehicle. Although various methods of obstacles detection have already been reported, they normally detect only moving obstacles and not static obstacles, and a detected obstacle is represented by a rectangular frame that surrounds this obstacle, which does not provide shape of the obstacle. In this paper, a method is proposed for detecting obstacles on a road, irrespective of moving or static, by use of background modeling and road region detection. The output of the proposed method is the shape of obstacles. Background modeling is often used to detect moving objects when a camera is static. In this paper, we apply it to a moving camera case in order to obtain foreground images. Then we extract the road region using SVM. In this road region, we carry out region classification. We can delete all the objects which are not obstacles in the foreground images based on the result of the region classification. In the performed experiments, it is shown that the proposed method is able to extract the shape of both static and moving obstacles when a car is driving.