Optimizing Disparity Candidates Space in Dense Stereo Matching

In this paper, a new approach for optimizing disparity candidates space is proposed for the solution of dense stereo matching problem. The main objectives of this approach are the reduction of average number of disparity candidates per pixel with low computational cost and high assurance of retaining the correct answer. These can be realized due to the effective use of multiple radial windows, intensity information, and some usual and new constraints, in a reasonable manner. The new space improved by the new idea validation and correction retains those candidates, which satisfy more constraints and especially being more promising to satisfy the implied assumption in using support windows, i.e. the disparity consistency of the window pixels. To evaluate the proposed space, the weighted window is used to estimate dense disparity map in this space. The experimental results on the standard stereo images indicate an overall speedup factor of 11 and the improved disparity map.