EDGE-BASED BINOCULAR STEREOPSIS ALGORITHM - A MATCHING MECHANISM WITHPROBABILISTIC FEEDBACK

A novel algorithm for edge-based stereopsis which has a probabilistic feedback mechanism is introduced. Although the ''second algorithm'' of Marr and Poggio is one of the most effective edge-based stereopsis al gorithms, it contains an inter-resolutional correspondence problem. To solve this problem, we developed an algorithm based on the probabilis tic feedback from the ''reconstruction process'' to the ''matching pro cess''. Its architecture is reasonable as a model of human stereo visi on, based upon anatomical and physiological fact. We also explain the computational theory of binocular stereopsis and its implementation ba sed on the ''second algorithm'' in single resolution, show the advanta ge of the probabilistic feedback and the double eye-dominant mechanism s, and also discuss its adequacy as a model of human stereo vision. Co pyright (C) 1996 Elsevier Science Ltd