JSIP  Vol.6 No.3 , August 2015
Census and Segmentation-Based Disparity Estimation Algorithm Using Region Merging
ABSTRACT
Disparity estimation is an ill-posed problem in computer vision. It is explored comprehensively due to its usefulness in many areas like 3D scene reconstruction, robot navigation, parts inspection, virtual reality and image-based rendering. In this paper, we propose a hybrid disparity generation algorithm which uses census based and segmentation based approaches. Census transform does not give good results in textureless areas, but is suitable for highly textured regions. While segment based stereo matching techniques gives good result in textureless regions. Coarse disparities obtained from census transform are combined with the region information extracted by mean shift segmentation method, so that a region matching can be applied by using affine transformation. Affine transformation is used to remove noise from each segment. Mean shift segmentation technique creates more than one segment of same object resulting into non-smoothness disparity. Region merging is applied to obtain refined smooth disparity map. Finally, multilateral filtering is applied on the disparity map estimated to preserve the information and to smooth the disparity map. The proposed algorithm generates good results compared to the classic census transform. Our proposed algorithm solves standard problems like occlusions, repetitive patterns, textureless regions, perspective distortion, specular reflection and noise. Experiments are performed on middlebury stereo test bed and the results demonstrate that the proposed algorithm achieves high accuracy, efficiency and robustness.

Cite this paper
Borisagar, V. and Zaveri, M. (2015) Census and Segmentation-Based Disparity Estimation Algorithm Using Region Merging. Journal of Signal and Information Processing, 6, 191-202. doi: 10.4236/jsip.2015.63018.
References
[1]   Scharstein, D. and Szeliski, R. (2002) A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision, 47, 7-42.
http://dx.doi.org/10.1023/A:1014573219977

[2]   Fua, P. (1993) A Parallel Stereo Algorithm That Produces Dense Depth Maps and Preserves Image Features. Machine Vision and Applications, 6, 35-49. http://dx.doi.org/10.1007/BF01212430

[3]   Scharstein, D. and Szeliski, R. (1996) Stereo Matching with Non-Linear Diffusion. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 28, 343-350.
http://dx.doi.org/10.1109/CVPR.1996.517095

[4]   Zabih, R. and Woodfill, J. (1994) Non-Parametric Local Transforms for Computing Visual Correspo-ndence. Proceedings of Third European Conference of Computer Vision, 801, 151-158.

[5]   Zitnick, C.L. and Kang, S.B. (2007) Stereo for Image-Based Rendering using Image Over-Segment-ation. International Journal of Computer Vision, 75, 49-65.
http://dx.doi.org/10.1007/s11263-006-0018-8

[6]   Wei, Y. and Quan, L. (2004) Region-Based Progressive Stereo Matching. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, 106-113.

[7]   Birchfield, S. and Tomasi, C. (1999) Multiway Cut for Stereo and Motion with Slanted Surfaces. Proceedings of the 7th IEEE International Conference on Computer Vision, 1, 489-495.
http://dx.doi.org/10.1109/ICCV.1999.791261

[8]   Hirschmuller, H. and Scharstein, D. (2007) Evaluation of Cost Functions for Stereo Matching. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, 17-22 June 2007, 1-8. http://dx.doi.org/10.1109/cvpr.2007.383248

[9]   Scharstein, D. (1994) Matching Images by Comparing Their Gradient Fields. Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1, 572-575.
http://dx.doi.org/10.1109/ICPR.1994.576363

[10]   Seitz, P. (1989) Using Local Orientation Information as Image Primitive for Robust Object Recog-nition. SPIE Visual Communications and Image Processing IV, 1199, 1630-1639.
http://dx.doi.org/10.1117/12.970173

[11]   Hirschmuller, H. and Scharstein, D. (2009) Evaluation of Stereo Matching Costs on Images with Radiometric Differences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31, 1582-1599.http://dx.doi.org/10.1109/TPAMI.2008.221

[12]   Lee, Z., Juang, J. and Nguyen, T.Q. (2013) Local Disparity Estimation with Three-Moded Cross Census and Advanced Support Weight. IEEE Transactions on Multimedia, 15, 1855-1864.
http://dx.doi.org/10.1109/TMM.2013.2270456

[13]   Gautama, S., Lacroix, S. and Devy, M. (1999) Evaluation of Stereo Matching Algorithms for Occupant Detection. Proceedings of the International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, Corfu, 26-27 September 1999, 177-184.
http://dx.doi.org/10.1109/RATFG.1999.799242

[14]   Banks, J. and Corke, P. (1991) Quantitative Evaluation of Matching Methods and Validity Measures for Stereo Vision. IEEE International Journal of Robotics Research, 20, 512-532.
http://dx.doi.org/10.1177/02783640122067525

[15]   Hirschmller, H. (2001) Improvements in Real-Time Correlation Based Stereo Vision. Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision, Kauai, 9-10 December 2001, 141-148.
http://dx.doi.org/10.1109/SMBV.2001.988772

[16]   Humenberger, M., Engelke, T. and Kubinger, W. (2010) A Census-Based Stereo Vision Algorithm Using Modified Semi-Global Matching and Plane Fitting to Improve Matching Quality. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), San Francisco, 13-18 June 2010, 77- 84. http://dx.doi.org/10.1109/CVPRW.2010.5543769

[17]   Tsai, T.H., Nelson Chang, Y.C., Tseng, Y.C. and Chang, T.S. (2007) Census Diffusion with Segment Constraint for Disparity Estimation in Stereo Vision. Proceedings of the Computer Vision, Graphics and Image Processing (CVGIP), Taiwan, 19-21 August 2007.

[18]   Xiao, J., Xia, L.Y., Lin, L.Q. and Zhang, Z.T. (2010) A Segment-Based Stereo Matching Method with Ground Control Points. Proceedings of the 2nd Conference on Environmental Science and Infor-mation Application Technology, Wuhan, 17-18 July 2010, 306-309.

[19]   Hong, L. and Chen, G. (2004) Segment-Based Stereo Matching Using Graph Cuts. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, 74-81.
http://dx.doi.org/10.1109/CVPR.2004.1315016

[20]   Bleyer, M. and Gelautz, M. (2005) Graph-Based Surface Reconstruction from Stereo Pairs Using Image Segmentation. Proceedings of SPIE 5665, Video Metrics VIII, 5665, 288-299.

[21]   Klaus, A., Sormann, M. and Karner, K. (2006) Segment Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure. Proceedings of the International Conference on Pattern Recognition, Hong Kong, 20-24 August 2006, 15-18.
http://dx.doi.org/10.1109/icpr.2006.1033

[22]   Huang, X.D. and Dubois, E. (2006) 3D Reconstruction Based on a Hybrid Disparity Estimation Algorithm. Proceedings of the IEEE International Conference on Image Processing, Atlanta, 8-11 October 2006, 1025-1028.http://dx.doi.org/10.1109/icip.2006.312674

[23]   Comanicu, D. and Meer, P. (2002) Mean Shift: A Robust Approach toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 603-619.
http://dx.doi.org/10.1109/34.1000236

[24]   Yin, Y., Jin, M. and Xie, S.Y. (2010) A Stereo Pairs Disparity Matching Algorithm by Mean-Shift Segmentation. Proceedings of the Third International Workshop on Advanced Computational Intelligence, Suzhou, 25-27 August 2010, 639-642. http://dx.doi.org/10.1109/IWACI.2010.5585232

[25]   Wang, Z.-F. and Zheng, Z.-G. (2008) A Region Based Stereo Matching Algorithm Using Cooperative Optimization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, 23-28 June 2008, 1-8.

[26]   Manduchi, R. and Tomasi, C. (1998) Bilateral Filtering for Gray and Color Images. Proceedings of the IEEE International Conference on Computer Vision, Bombay, 4-7 January 1998, 836-846.

[27]   Bobick, A.F. and Intille, S.S. (1999) Large Occlusion Stereo. International Journal of Computer Vision, 33, 181-200.http://dx.doi.org/10.1023/A:1008150329890

[28]   Wang, X. (2009) Disparity Estimation Using a Color Segmentation. Master’s Dissertation, Universitat Politecnica De Catalunya, Barcelona.

[29]   http://vision.middlebury.edu/stereo/

[30]   Borisagar, V.H. and Zaveri, M.A. (2011) A Novel Segment-Based Stereo Matching Algorithm for Disparity Map Generation. Proceedings of the 2011 International Conference on Computer and Software Modeling, 14, 25-29.

 
 
Top