This thesis presents a new dense disparity estimation method based on color segmentation and energy minimization. Segmentation-based methods have an advantage of clear representation of disparities on discontinuous region. This thesis remodels the energy minimization methods to fit with segmentation-based method.
In the proposed method, the initial disparity map is obtained by variable block matching of the segmented plane and RANdom SAmple Consensus (RANSAC) fitting. Then energy minimization using cost relaxation and incremental warping is performed on small segmented planes and overall segmented planes, respectively to refine the disparity planes more accurately. At the end of the method, erroneous stripes that are not corrected by the segmentation-based approach are removed by pixel-based method.
Experimental results showed that the proposed method has better error rate compared to the conventional global matching methods on various stereo image pairs. And the proposed method demonstrated reasonable processing time.