V-disparity Based UGV Obstacle Detection in Rough Outdoor Terrain

This paper presents a fast obstacle detection system based on stereo vision for unmanned ground vehicle (UGV) navigation in unstructured environment. In order to make the UGV adaptable to more complex terrains, we propose a new estimation method of the main ground disparity (MGD) from the V-disparity images. Then, by comparing the disparity of the MGD with local 3D reconstruction, a coarse-to-fine method to find and localize obstacles is introduced in the paper. The obstacle detection system is tested practically on our UGV platform in some outdoor unstructured environments. The experimental results validate the efficacy of our system.