This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Inference of Segmented Overlapping Surfaces from Binocular Stereo
June 2002 (vol. 24 no. 6)
pp. 824-837

We present an integrated approach to the derivation of scene descriptions from a pair of stereo images, where the steps of feature correspondence and surface reconstruction are addressed within the same framework. Special attention is given to the development of a methodology with general applicability. In order to handle the issues of noise, lack of image features, surface discontinuities, and regions visible in one image only, we adopt a tensor representation for the data and introduce a robust computational technique called tensor voting for information propagation. The key contributions of this paper are twofold: First, we introduce "saliency" instead of correlation scores as the criterion to determine the correctness of matches and the integration of feature matching and structure extraction. Second, our tensor representation and voting as a tool enables us to perform the complex computations associated with the formulation of the stereo problem in three dimensions at a reasonable computational cost. We illustrate the steps on an example, then provide results on both random dot stereograms and real stereo pairs, all processed with the same parameter set.

[1] S. Barnard and M. Fischler, “Computational Stereo,” ACM Computing Surveys, vol. 14, no. 4, pp. 553–572, 1982.
[2] P.N. Belhumeur, “A Bayesian Approach to Binocular Stereopsis,” Int'l J. Computer Vision, vol. 19, no. 3, pp. 237-260, 1996.
[3] P.N. Belhumeur and D. Mumford, "A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 506-512, June 1992.
[4] Y. Boykov, O. Veksler, and R. Zabih, Markov Random Fields with Efficient Approximations Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 648-655, 1998.
[5] P. Burt and B. Julesz, “A Disparity Gradient Limit for Binocular Fusion,” Perception, vol. 9, pp. 671-682, 1980.
[6] Q. Chen and G. Medioni, “A Volumetric Stereo Matching Method: Application to Image-Based Modeling,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 29-34, 1999.
[7] R.T. Collins, “A Space-Sweep Approach to True Multi-Image Matching,” Proc. Computer Vision and Pattern Recognition, pp. 358-363, 1996.
[8] I. Cox, S. Hingorani, and S. Rao, “A Maximum Likelihood Stereo Algorithm,” Computer Vision and Image Understanding, vol. 63, no. 3, pp. 542–567, 1996.
[9] U. Dhond and J.K. Aggarwal, "Structure From Stereo—A Review," IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1,489-1,510, Nov. 1989.
[10] P. Fua, “From Multiple Stereo Views to Multiple 3D Surfaces,” Int'l J. Computer Vision, vol. 24, no. 1, pp. 19-35, 1997.
[11] D. Geiger, B. Ladendorf, and A. Yuille, “Occlusions and Binocular Stereo,” Int'l J. Computer Vision, vol. 14, pp. 211-226, 1995.
[12] G.H. Granlund and H. Knuttson, Signal Processing for Computer Vision. Kluwer, 1995.
[13] G. Guy and G. Medioni, “Inference of Surfaces, 3D Curves, and Junctions from Sparse, Noisy, 3D Data,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 11, pp. 1265-1277, Nov. 1997.
[14] W. Hoff and N. Ahuja, "Surfaces From Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 2, pp. 121-136, Feb. 1989.
[15] P.V.C. Hough, “Methods and Means for Recognising Complex Patterns,” US Patent 3 069 654, 1962.
[16] H. Ishikawa and D. Geiger, “Occlusions, Discontinuities, and Epipolar Lines in Stereo,” Proc. European Conf. Computer Vision, pp. 232-248, 1998.
[17] B. Julesz, “Binocular Depth Perception of Computer-Generated Patterns,” Bell System Technical J., vol. 39, pp. 1125-1162, 1960.
[18] B. Julesz, Dialogues on Perception. MIT Press, 1995.
[19] H. Knutsson, “Representing Local Structure Using Tensors,” Proc. Sixth Scandinavian Conf. Image Analysis, pp. 244-251, 1989.
[20] M.S. Lee and G. Medioni, "Inferring Segmented Surface Description from Stereo Data," Proc. Computer Vision and Pattern Recognition, pp. 346-352,Santa Barbara, Calif., June 1998.
[21] M.S. Lee and G. Medioni, “Grouping ., -, ->, O-, into Regions, Curves, and Junctions,” Computer Vision and Image Understanding, vol. 76, no. 1, pp. 54-69, 1999.
[22] W.E. Lorensen and H.E. Cline, “Marching Cubes: A High Resolution 3D Surface Construction Algorithm,” Computer Graphics (SIGGRAPH '87 Proc.), vol. 21, pp. 163-169, 1987.
[23] D. Marr and T. Poggio, “A Theory of Human Stereo Vision,” Proc. Royal Soc. London, vol. B204, pp. 301-328, 1979.
[24] D. Marr, Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W.H. Freeman and Co., 1982.
[25] G. Medioni, M. Lee, and C. Tang, A Computational Framework for Segmentation and Grouping. Elsevier Science B.V., 2000.
[26] V.S. Nalwa, A Guided Tour of Computer Vision. Addison-Wesley, 1993.
[27] S.I. Olsen, “Stereo Correspondence by Surface Reconstruction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 3, pp. 309-314, Mar. 1990.
[28] M. Okutomi and T. Kanade, “A Multiple-Baseline Stereo,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp. 353-363, Apr. 1993.
[29] L. Robert and R. Deriche, “Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities,” Proc. Fourth European Conf. Computer Vision, pp. 439-451, 1996.
[30] S. Roy and I.J. Cox, "A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem," Proc. Int'l Conf. Computer Vision, pp. 492-499,Bombay, Jan. 1998.
[31] R. Sara and R. Bajcsy, On Occluding Contour Artifacts in Stereo Vision Proc. Computer Vision and Pattern Recognition, pp. 852-857, 1997.
[32] S.M. Seitz and C.R. Dyer, “Photorealistic Scene Reconstruction by Voxel Coloring,” Computer Vision and Pattern Recognition, pp. 1067-1073, 1997.
[33] C.V. Stewart, “MINPRAN: A New Robust Estimator for Computer Vision,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 10, pp. 925-938, Oct. 1995.
[34] R. Szeliski and P. Golland, “Stereo Matching with Transparency and Matting,” Int'l J. Computer Vision, vol. 32, no. 1, pp. 45-61, 1999.
[35] C.-K. Tang and G. Medioni, “Inference of Integrated Surface, Curve, and Junction Descriptions from Sparse, Noisy 3D Data,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1206-1223, Nov. 1998.
[36] C.K. Tang and G. Medioni, “Curvature-Augmented Tensorial Framework for Integrated Shape Inference from Noisy, 3D Data,” IEEE Trans. Pattern Analysis and Machine Intelligence, to be published.
[37] G. Wei, W. Brauer, and G. Hirzinger, “Intensity- and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1,143-1,159, Nov. 1998.
[38] C.F. Westin, “A Tensor Framework for Multidimensional Signal Processing,” PhD thesis, Linkoeping Univ., Sweden, 1994.
[39] A.L. Yuille and T. Poggio, “A Generalized Ordering Constraint for Stereo Correspondence,” AI Memo 777, AI Lab, MIT, 1984.
[40] Z. Zhang, R. Deriche, O. Faugeras, and Q.T. Luong, “A Rubust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry,” Artificial Intelligence J., vol. 78, pp. 87-119, 1995.

Index Terms:
Binocular stereo, tensor voting, perceptual grouping, surface inference.
Citation:
Mi-Suen Lee, Gérard Medioni, Philippos Mordohai, "Inference of Segmented Overlapping Surfaces from Binocular Stereo," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 6, pp. 824-837, June 2002, doi:10.1109/TPAMI.2002.1008388
Usage of this product signifies your acceptance of the Terms of Use.