CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.05 - May

Subscribe

Issue No.05 - May (2012 vol.34)

pp: 930-942

Neus Sabater , ENS, CNRS-CMLA, Cachan

Andrés Almansa , Telecom ParisTech, Paris

Jean-Michel Morel , ENS, CNRS-CMLA, Cachan

ABSTRACT

This paper introduces a statistical method to decide whether two blocks in a pair of images match reliably. The method ensures that the selected block matches are unlikely to have occurred “just by chance.” The new approach is based on the definition of a simple but faithful statistical background model for image blocks learned from the image itself. A theorem guarantees that under this model, not more than a fixed number of wrong matches occurs (on average) for the whole image. This fixed number (the number of false alarms) is the only method parameter. Furthermore, the number of false alarms associated with each match measures its reliability. This a contrario block-matching method, however, cannot rule out false matches due to the presence of periodic objects in the images. But it is successfully complemented by a parameterless self-similarity threshold. Experimental evidence shows that the proposed method also detects occlusions and incoherent motions due to vehicles and pedestrians in nonsimultaneous stereo.

INDEX TERMS

Stereo vision, block matching, number of false alarms (NFA), a contrario detection.

CITATION

Neus Sabater, Andrés Almansa, Jean-Michel Morel, "Meaningful Matches in Stereovision",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.34, no. 5, pp. 930-942, May 2012, doi:10.1109/TPAMI.2011.207REFERENCES

- [1] M.Z. Brown, D. Burschka, and G.D. Hager, "Advances in Computational Stereo,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 8, pp. 993-1008, Aug. 2003.- [2] N. Burrus, T.M. Bernard, and J.-M. Jolion, "Image Segmentation by A Contrario Simulation,"
Pattern Recognition, vol. 42, no. 7, pp. 1520-1532, July 2009.- [3] F. Cao, "Application of the Gestalt Principles to the Detection of Good Continuations and Corners in Image Level Lines,"
Computing and Visualisation in Science, vol. 7, pp. 3-13, 2004.- [4] F. Cao, J.-L. Lisani, J.-M. Morel, and P.M.F. Sur,
A Theory of Shape Identification. Springer, 2008.- [5] J. Delon and B. Rougé, "Small Baseline Stereovision,"
J. Math. Imaging and Vision, vol. 28, no. 3, pp. 209-223, 2007.- [6] A. Desolneux, L. Moisan, and J. Morel,
From Gestalt Theory to Image Analysis: A Probabilistic Approach. Springer, 2007.- [7] G. Egnal and R.P. Wildes, "Detecting Binocular Half-Occlusions: Empirical Comparisons of Five Approaches,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 8, pp. 1127-1133, Aug. 2002.- [8] V. Eruhimov, "Stereo_Match.Cpp Sample Program," Provided with OpenCV Software Library Version 2.2.0 http://opencv. willowgarage.comwiki/, Jan. 2010.
- [9] S. Forstmann, Y. Kanou, J. Ohya, S. Thuering, and A. Schmitt, "Real-Time Stereo by Using Dynamic Programming,"
Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshop, vol. 3, pp. 29-36, 2004.- [10] W.E.L. Grimson and D.P. Huttenlocher, "On the Verification of Hypothesized Matches in Model-Based Recognition,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 12, pp. 1201-1213, Dec. 1991.- [11] C.G. Harris and M. Stephens, "A Combined Corner and Edge Detector,"
Proc. Fourth Alvey Vision Conf., pp. 147-151, 1988.- [12] L. Igual, J. Preciozzi, L. Garrido, A. Almansa, V. Caselles, and B. Rougé, "Automatic Low Baseline Stereo in Urban Areas,"
Inverse Problems and Imaging, vol. 1, no. 2, pp. 319-348, 2007.- [13] H. Ishikawa, "Exact Optimization for Markov Random Fields with Convex Priors,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1333-1336, Oct. 2003.- [14] S.B. Kang, R. Szeliski, and J. Chai, "Handling Occlusions in Dense Multi-View Stereo,"
Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 103-110, 2001.- [15] A. Klaus, K. Sormann, and M. Karner, "Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure,"
Proc. Int'l Conf. Pattern Recognition, pp. 15-18, 2006.- [16] V. Kolmogorov and R. Zabih, "Graph Cut Algorithms for Binocular Stereo with Occlusions,"
Math. Models in Computer Vision: The Handbook, Springer-Verlag, 2005.- [17] D. Lowe,
Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, 1985.- [18] D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints,"
Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.- [19] J. Mairal, M. Elad, and G. Sapiro, "Sparse Representation for Color Image Restoration,"
IEEE Trans. Image Processing, vol. 17, no. 1, pp. 53-69, Jan. 2008.- [20] R. Manduchi and C. Tomasi, "Distinctiveness Maps for Image Matching,"
Proc. Int'l Conf. Image Analysis and Processing, pp. 26-31, 1999.- [21] K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors,"
Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 257-263, 2003.- [22] A. Mittal and N. Paragios, "Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation,"
Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 302-309, 2004.- [23] L. Moisan and B. Stival, "A Probabilistic Criterion to Detect Rigid Point Matches between Two Images and Estimate the Fundamental Matrix,"
Int'l J. Computer Vision, vol. 57, no. 3, pp. 201-218, 2004.- [24] P. Mordohai and G. Medioni, "Stereo Using Monocular Cues within the Tensor Voting Framework,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 6, pp. 968-982, June 2006.- [25] P. Musé, F. Sur, F. Cao, Y. Gousseau, and J.-M. Morel, "An A Contrario Decision Method for Shape Element Recognition,"
Int'l J. Computer Vision, vol. 69, no. 3, pp. 295-315, 2006.- [26] P. Musé, F. Sur, and J.-M. Morel, "Sur les Seuils de Reconnaissance des Formes,"
Traitement du Signal, vol. 20, no. 3, pp. 279-294, http://cat.inist.fr?aModele=afficheN&cpsidt=15370125 , 2003.- [27] G. Née, S. Jehan-Besson, L. Brun, and M. Revenu, "Significance Tests and Statistical Inequalities for Region Matching,"
Proc. Int'l Workshop Structural, Syntactic, and Statistical Pattern Recognition, pp. 350-360, http://dx.doi.org/10.1007978-3-540-89689-0_39 , 2008.- [28] Y. Ohta and T. Kanade, "Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, no. 2, pp. 139-154, Mar. 1985.- [29] K.A. Patwardhan, G. Sapiro, and V. Morellas, "Robust Foreground Detection in Video Using Pixel Layers,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 4, pp. 746-751, Apr. 2008.- [30] T. Pock, T. Schoenemann, G. Graber, H. Bischof, and D. Cremers, "A Convex Formulation of Continuous Multi-Label Problems,"
Proc. European Conf. Computer Vision, pp. 792-805, http://portal.acm.orgcitation.cfm?id=1478172.1478235 , 2008.- [31] J. Rabin, J. Delon, and Y. Gousseau, "A Contrario Matching of Sift-Like Descriptors,"
Proc. Int'l Conf. Pattern Recognition, 2008.- [32] A. Robin, L. Moisan, and S. Le Hégarat-Mascle, "An A-Contrario Approach for Sub-Pixel Change Detection in Satellite Imagery," Technical Report MAP5 Nro. 2009-15, Université Paris Descartes, 2009.
- [33] N. Sabater, J.-M. Morel, A. Almansa, and G. Blanchet, "Discarding Moving Objects in Quasi-Simultaneous Stereovision,"
Proc. IEEE Int'l Conf. Image Processing, 2010.- [34] R. Sara, "Finding the Largest Unambiguous Component of Stereo Matching,"
Proc. European Conf. Computer Vision, pp. 900-914, 2002.- [35] D. Scharstein and R. Szeliski, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,"
Int'l J. Computer Vision, vol. 47, nos. 1-3, pp. 7-42, 2002.- [36] C. Schmid and A. Zisserman, "The Geometry and Matching of Lines and Curves over Multiple Views,"
Int'l J. Computer Vision, vol. 40, no. 3, pp. 199-234, 2000.- [37] C.E. Shannon, "A Mathematical Theory of Communication,"
ACM SIGMOBILE Mobile Computing and Comm. Rev., vol. 5, no. 1, pp. 3-55, 2001.- [38] 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.- [39] C. Tomasi and R. Manduchi, "Stereo Matching as a Nearest-Neighbor Problem,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 3, pp. 333-340, Mar. 1998.- [40] O. Veksler, "Dense Features for Semi-Dense Stereo Correspondence,"
Int'l J. Computer Vision, vol. 47, nos. 1-3, pp. 247-260, 2002.- [41] O. Veksler, "Extracting Dense Features for Visual Correspondence with Graph Cuts,"
Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 689-694, 2003.- [42] Q. Yang, L. Wang, R. Yang, H. Stewenius, and D. Nister, "Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation and Occlusion Handling,"
Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 2347-2354, 2006. |