Obstacle detection in urban traffic using stereovision

Obstacle detection and classification in complex urban area are highly demanding, but desirable for protection of vulnerable road users. This paper presents an in-vehicle stereovision-based system for short-range object detection. The basic principles have been given for designing the optical parameters of the system such as baseline, angular coverage, spatial resolution and dynamic range. A novel feature-indexed approach has been proposed to achieve fast and quality stereo matching. Consequently, the depth map is generated by reconstructing all image points into the world coordinates. Object segmentation based on the depth map makes use of 3-dimensional information of the objects, and enables reliable and robust object detection.