Performance Evaluation of Multiresolution Methods in Disparity Estimation
Disparity estimation from stereo imagery has gained substantial interest of research community from its commencement with the recent trend being the use of multiresolution methods. Existing multiresolution based methods are relatively independent and do not, in general, relate to a continuous progress in the research. As a result, the relative advantages and disadvantages of a particular multiresolution method in disparity estimation are hard to understand. Present work is an effort to put different multiresolution methods together to highlight their expediency and suitability along with the comparison to get a better understanding. Three different frameworks are used having different strengths and limitations followed by the comparison in the terms of time complexity, quality of matching and effect of different levels of decomposition. Qualitative and quantitative results have been provided for four types of standard multiresolution methods.
KeywordsStereo Match Disparity Estimation Detail Part Contourlet Transform Stereo Match Algorithm
- 3.Caspary, G., Zeevi, Y.Y.: Wavelet-based multiresolution stereo vision. In: Proceedings of the International Conference on Pattern Recognition, vol. 3, pp. 680–683 (2002)Google Scholar
- 4.Ding, H., Fu, M., Wang, M.: Shift-invariant contourlet transform and its application to stereo matching. In: Proceedings of the International Conference on Innovative Computing, Information and Control, pp. 87–90 (2006)Google Scholar
- 8.Mukherjee, D., Wang, G., Wu, Q.: Stereo matching algorithm based on curvelet decomposition and modified support weights. Accepted at IEEE International Conference on Acoustics, Speech and Signal Processing (2010)Google Scholar
- 10.Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 195–202 (2003)Google Scholar
- 11.Zhang, W., Zhang, Q., Qu, L., Wei, S.: A stereo matching algorithm based on multiresolution and epipolar constraint. In: Proceedings of the International Conference on Image and Graphics, pp. 180–183 (2004)Google Scholar