Fast Adaptive Graph-Cuts Based Stereo Matching

Stereo vision is one of the central research problems in computer vision. The most difficult and important issue in this area is the stereo matching process. One technique that performs this process is the Graph-Cuts based algorithm and which provides accurate results [1]. Nevertheless, this approach is too slow to use due to the redundant computations that it invokes. In this work, an Adaptive Graph-Cuts based algorithm is implemented. The key issue is to subdivide the image into several regions using quadtrees and then define a global energy function that adapts itself for each of these subregions. Results show that the proposed algorithm is 3 times faster than the other Graph-Cuts algorithm while keeping the same quality of the results.

[1]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[2]  Lutz Falkenhagen.  Hierarchical Block-Based Disparity Estimation Considering Neighbourhood Constraints , 1997 .

[3]  Vladimir Kolmogorov,et al.  Multi-camera Scene Reconstruction via Graph Cuts , 2002, ECCV.

[4]  J. Kenney,et al.  Mathematics of statistics , 1940 .

[5]  Takeo Kanade,et al.  A multiple-baseline stereo , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Jelena Kovacevic,et al.  Quadtrees for embedded surface visualization: constraints and efficient data structures , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[7]  Carlos Wai Yin Leung.  Efficient methods for 3D reconstruction from multiple images , 2006 .

[8]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[9]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[10]  Sang Uk Lee,et al.  A dense stereo matching using two-pass dynamic programming with generalized ground control points , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Changming Sun,et al.  Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface Techniques , 2002, International Journal of Computer Vision.

[12]  Changming Sun,et al.  Fast Stereo Matching by Iterated Dynamic Programming and Quadtree Subregioning , 2004, BMVC.

[13]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[14]  Lawrence O'Gorman,et al.  Practical Algorithms for Image Analysis: Description, Examples and Code , 2000 .

[15]  Neill W Campbell,et al.  IEEE International Conference on Computer Vision and Pattern Recognition , 2008 .

[16]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..