Object detection using binocular vision

The prevalent traffic conditions have necessitated the need for automotive industries to do greater research on passenger and vehicle safety systems. The present work addresses one of such obstacle detection system that is based on stereo vision, a cost efficient and accurate sensor for scene construction. Stereo-based obstacle detection system has the ability to provide the distance of obstacle from the car and can warn the driver based on the distance to collision. There are two different approaches for detecting obstacles using stereo vision: disparity based and inverse perspective projection based. The present method is based on disparity approach. In the proposed method, dense stereo disparity information is used for 3D reconstruction of the scene and the triangulated information is used to build the Digital Elevation Map (DEM) for detecting obstacles. The system is implemented in MATLAB™ (R2010b).