Disparity measurement using dynamic programming

In this paper, we proposed a method of depth map measurement with dynamic programming which calculates the disparity of binocular stereo camera. We scan the intensity horizontally of the two images captured by the stereo camera and record the cumulative error value of each pixel in the scanline to find the minimum cumulative error to get the optimized path. With the optimized path, we can find the reasonable and dense depth map. Furthermore, in order to reach real-time processing, we proposed a simplifying algorithm to reduce the computational complexity of dynamic programming.