Object Extraction from Stereo Vision Using Continuity of Disparity Map

This paper describes a method for object detection from three-dimensional image using stereo vision. Each object has a different disparity distribution. In other words, an object's disparity distribution is discontinuous at the border between itself and another adjacent object. Focusing attention on this point, the image is divided into objects. Furthermore, objects having sharply-defined contour are detected using superpixels.