The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.07 - July (2008 vol.30)
pp: 1230-1242
ABSTRACT
The estimation of the epipolar geometry is especially difficult when the putative correspondences include a low percentage of inlier correspondences and/or a large subset of the inliers is consistent with a degenerate configuration of the epipolar geometry that is totally incorrect. This work presents the Balanced Exploration and Exploitation Model Search (BEEM) algorithm that works very well especially for these difficult scenes. The algorithm handles these two problems in a unified manner. It includes the following main features: (1) Balanced use of three search techniques: global random exploration, local exploration near the current best solution and local exploitation to improve the quality of the model. (2) Exploits available prior information to accelerate the search process. (3) Uses the best found model to guide the search process, escape from degenerate models and to define an efficient stopping criterion. (4) Presents a simple and efficient method to estimate the epipolar geometry from two SIFT correspondences. (5) Uses the locality-sensitive hashing (LSH) approximate nearest neighbor algorithm for fast putative correspondences generation. The resulting algorithm when tested on real images with or without degenerate configurations gives quality estimations and achieves significant speedups compared to the state of the art algorithms.
INDEX TERMS
Computer vision, Vision and Scene Understanding, 3D/stereo scene analysis, Motion
CITATION
Liran Goshen, Ilan Shimshoni, "Balanced Exploration and Exploitation Model Search for Efficient Epipolar Geometry Estimation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 7, pp. 1230-1242, July 2008, doi:10.1109/TPAMI.2007.70768
REFERENCES
[1] M. Fischler and R. Bolles, “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Comm. ACM, vol. 24, no. 6, pp. 381-395, June 1981.
[2] P. Torr, “Motion Segmentation and Outlier Detection,” PhD thesis, Dept. of Eng. Science, Univ. of Oxford, 1995.
[3] O. Chum, J. Matas, and J. Kittler, “Locally Optimized RANSAC,” Proc. German Pattern Recognition Symp., pp. 236-243, 2003.
[4] B. Tordoff and D. Murray, “Guided Sampling and Consensus for Motion Estimation,” Proc. Seventh European Conf. Computer Vision, pp. I: 82-I: 96, 2002.
[5] O. Chum and J. Matas, “Matching with PROSAC: Progressive Sample Consensus,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I: 220-I: 226, 2005.
[6] D. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, Nov. 2004.
[7] L. Goshen and I. Shimshoni, “Guided Sampling via Weak Motion Models and Outlier Sample Generation for Epipolar Geometry Estimation,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I: 1105-I: 1112, 2005.
[8] J. Domke and Y. Aloimonos, “A Probabilistic Framework for Correspondence and Egomotion,” Proc. Workshop Dynamical Vision, 2005.
[9] F. Schaffalitzky and A. Zisserman, “Multi-View Matching for Unordered Image Sets, or 'How Do I Organize My Holiday Snaps?'” Proc. Seventh European Conf. Computer Vision, pp. I: 414-I:431, 2002.
[10] O. Chum, J. Matas, and S. Obdrzalek, “Enhancing RANSAC by Generalized Model Optimization,” Proc. Sixth Asian Conf. Computer Vision, pp. II: 812-II: 817, 2004.
[11] R. Hartley, “In Defense of the Eight-Point Algorithm,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 6, pp. 580-593, June 1997.
[12] M. Perdoch, J. Matas, and O. Chum, “Epipolar Geometry from Two Correspondences,” Proc., Int'l Conf. Pattern Recognition, pp.IV: 215-IV: 219, 2006.
[13] L. Goshen and I. Shimshoni, “Balanced Exploration and Exploitation Model Search for Efficient Epipolar Geometry Estimation,” Proc. Ninth European Conf. Computer Vision, 2006.
[14] A. Makadia, C. Geyer, S. Sastry, and K. Daniilidis, “Radon-Based Structure from Motion without Correspondences,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I: 796-I: 803, 2005.
[15] O. Chum, T. Werner, and J. Matas, “Two-View Geometry Estimation Unaffected by a Dominant Plane,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I: 772-I: 779, 2005.
[16] M. Irani and P. Anandan, “Parallax Geometry of Pairs of Points for 3D Scene Analysis,” Proc. Fourth European Conf. Computer Vision, pp. I: 17-I: 30, 1996.
[17] A. Gionis, P. Indyk, and R. Motwai, “Similarity Search in High Dimensions via Hashing,” Proc. 25th Int'l Conf. Very Large Data Bases, pp. 518-529, 1999.
[18] M. Grabner, H. Grabner, and H. Bischof, “Fast Approximated Sift,” Proc. Seventh Asian Conf. Computer Vision, pp. 918-927, 2006.
[19] S. Sinha, J. Frahm, M. Pollefeys, and Y. Genc, “GPU-Based Video Feature Tracking and Matching,” Proc. Workshop Edge Computing Using New Commodity Architectures, 2006.
[20] H. Chen and P. Meer, “Robust Regression with Projection Based M-Estimators,” Proc. Int'l Conf. Computer Vision, pp. 878-885, 2003.
[21] S. Rozenfeld and I. Shimshoni, “The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. I: 1113-I: 1120, 2005.
[22] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2003.
[23] T. Tuytelaars and L. Van Gool, “Matching Widely Separated Views Based on Affine Invariant Regions,” Int'l J. Computer Vision, vol. 59, no. 1, pp. 61-85, 2004.
[24] T. Kadir, A. Zisserman, and M. Brady, “An Affine Invariant Salient Region Detector,” Proc. Eighth European Conf. Computer Vision, pp. 345-357, 2004.
[25] J. Matas, O. Chum, M. Urban, and T. Pajdla, “Robust Wide-Baseline Stereo from Maximally Stable Extremal Regions,” Proc. 13th British Machine Vision Conf., pp. 384-393, 2002.
[26] K. Mikolajczyk and C. Schmid, “An Affine Invariant Interest Point Detector,” Proc. Seventh European Conf. Computer Vision, pp. I: 128-I: 142, 2002.
[27] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Van Gool, “A Comparison of Affine Region Detectors,” Int'l J. Computer Vision, vol. 65, no. 12, pp. 43-72, 2005.
[28] B. Georgescu, I. Shimshoni, and P. Meer, “Mean Shift Based Clustering in High Dimensions: A Texture Classification Example,” Proc. Ninth Int'l Conf. Computer Vision, pp. 456-463, 2003.
[29] R. Weber, H. Schek, and S. Blott, “A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces,” Proc. 24th Int'l Conf. Very Large Data Bases, pp. 194-205, 1998.
[30] D. Nister, “An Efficient Solution to the Five-Point Relative Pose Problem,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 6, pp. 756-777, June 2004.
18 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool