An Improved Stereo Match Algorithm Based on Support-Weight Approach

Local stereo matching methods are still used widely because they are fast and simple. But the accuracy of local methods is much poorer than the global methods. They usually achieve accuracy at the expense of speed. Simple local methods are fast, but exhibit systematic errors. In this paper we propose an improved method based on support-weight approach, which can enhance the matching efficiency and accuracy. By utilizing a adaptive support-window which will change the size of the window relying on different area, we use a new disparity cost volume function which is much more simple than the traditional one. From the experimental result, we can see the accuracy of the disparity map is as better as the traditional one while the computational time is reduced. The proposed method includes three procedures, At first, we need to confirm the pixels 'window size in order to calculate the disparity, secondly, the adaptive support-weight of each pixel in left image will be calculated, the final step is to select the most optimal disparity in the right image. After the three steps, we can get the best matching point in the right image which is corresponding to the right image.