Evaluation of correspondence errors for stereo

The computation of a scalar correspondence error is the fundamental step in most stereo algorithms. The quality of the results obtained by the reconstruction algorithm directly depends on the characteristics of such error. We developed a procedure to evaluate different methods proposed for the computation of the correspondence error. The evaluation is based on exploring the shape of the error surface and tests it for uniqueness, isolation and compatibility. Experiments are reported which assess the behaviour of three different methods for correspondence error calculation. For the scenes used, it is possible to identify the most appropriate method to compute the correspondence error.

[1]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[2]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[3]  Sébastien Roy,et al.  Stereo Without Epipolar Lines: A Maximum-Flow Formulation , 1999, International Journal of Computer Vision.

[4]  Alan L. Yuille,et al.  Occlusions and binocular stereo , 1992, International Journal of Computer Vision.

[5]  Takeo Kanade,et al.  A Multiple-Baseline Stereo , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[7]  Emanuele Trucco,et al.  Efficient stereo with multiple windowing , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Richard Szeliski,et al.  Handling occlusions in dense multi-view stereo , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

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

[10]  Stefan Scherer,et al.  The discriminatory power of ordinal measures - towards a new coefficient , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[11]  Zezhi Chen,et al.  A new image rectification algorithm , 2003, Pattern Recognit. Lett..

[12]  Irwin Sobel,et al.  An Isotropic 3×3 image gradient operator , 1990 .

[13]  R. A. Hollister,et al.  A Rank Correlation Coefficient Resistant to Outliers , 1987 .

[14]  Aly A. Farag,et al.  Robust Correspondence Methods For Stereo Vision , 2003, Int. J. Pattern Recognit. Artif. Intell..

[15]  An Luo,et al.  An intensity-based cooperative bidirectional stereo matching with simultaneous detection of discontinuities and occlusions , 1995, International Journal of Computer Vision.

[16]  Peter N. Belhumeur,et al.  A Bayesian approach to binocular steropsis , 1996, International Journal of Computer Vision.

[17]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1999, International Journal of Computer Vision.

[18]  Alan L. Yuille,et al.  Local, global, and multilevel stereo matching , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Herbert Freeman,et al.  Machine Vision for Three-Dimensional Scenes , 1990 .

[20]  Aaron F. Bobick,et al.  Large Occlusion Stereo , 1999, International Journal of Computer Vision.

[21]  Joachim M. Buhmann,et al.  Regularizing phase-based stereo , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[22]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[23]  Reinhard Klette,et al.  Computer vision - three-dimensional data from images , 1998 .

[24]  Shree K. Nayar,et al.  Ordinal Measures for Image Correspondence , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

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

[26]  Larry H. Matthies,et al.  Kalman filter-based algorithms for estimating depth from image sequences , 1989, International Journal of Computer Vision.

[27]  Takeo Kanade,et al.  A stereo machine for video-rate dense depth mapping and its new applications , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Jitendra Malik,et al.  Computational framework for determining stereo correspondence from a set of linear spatial filters , 1992, Image Vis. Comput..

[29]  Michael Kass,et al.  Linear image features in stereopsis , 1986, International Journal of Computer Vision.

[30]  Richard Szeliski,et al.  Symmetric Sub-Pixel Stereo Matching , 2002, ECCV.

[31]  K. Nakayama,et al.  Toward a general theory of stereopsis: binocular matching, occluding contours, and fusion. , 1994, Psychological review.

[32]  John K. Tsotsos,et al.  Techniques for disparity measurement , 1991, CVGIP Image Underst..

[33]  A. Verri,et al.  A compact algorithm for rectification of stereo pairs , 2000 .

[34]  Michael A. Gennert,et al.  Brightness-based Stereo Matching , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[35]  M. Kendall,et al.  Rank Correlation Methods , 1949 .

[36]  Yuichi Ohta,et al.  Occlusion detectable stereo-occlusion patterns in camera matrix , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[37]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.