A Snake-Based Segmentation Algorithm for Objects with Boundary Concavities in Stereo Images

We propose a snake-based object segmentation algorithm for pairs of stereo images. Unlike previously developed snake-based algorithms, the algorithm in this paper performs well even when the background is cluttered. Moreover, the algorithm can successfully extract the contour of an object even in the presence of boundary concavities, and this algorithm is not sensitive to the placement of initial snake points. The algorithm uses a new energy function defined over the disparity space between the pair of stereo images to successfully locate the boundary of an object in a complex image. Experimental results have shown that the developed algorithm produces more accurate segmentation results than those of the well-known conventional snake algorithm reported by Williams and Shah (1992)