Obstacle Detection System for Visually Impaired People Based on Stereo Vision

An obstacle system based on visual selective feature and stereo vision is stated in this paper. By extracting feature vectors with color, intensity and direction, the corresponding saliency map is constructed. Then, obstacle area is figured out through threshold segmentation to the saliency map, and 3-D information of the obstacles is computed by using stereo vision. Finally, obstacle information is transformed into voice which can be delivered to the blind. Indoor and outdoor experiment has proved practicality and effectiveness of this method.