Occlusion filling in dynamic programming with simple index treatment

One of the problems in stereo matching algorithm is that it is impossible to estimate the most left positioned pixels with left reference system or the most right positioned pixels with right reference system because of the characteristic of stereo vision. That means in stereo matching algorithm, it cannot estimate disparity in occlusion parts. We used very simple index treatment to solve this problem, to compare original DP algorithm exactly, and to make not complex system. We could see that occlusion areas are filled when we used improved DP. If we add more techniques that are used frequently to other stereo matching algorithm, we could get more exact and reliable results.