Hop-Diffusion Monte Carlo for Epipolar Geometry Estimation between Very Wide-Baseline Images

We present a Monte Carlo approach for epipolar geometry estimation that efficiently searches for minimal sets of inlier correspondences in the presence of many outliers in the putative correspondence set, a condition that is prevalent when we have wide baselines, significant scale changes, rotations in depth, occlusion, and repeated patterns. The proposed Monte Carlo algorithm uses Balanced LOcal and Global Search (BLOGS) to find the best minimal set of correspondences. The local search is a diffusion process using Joint Feature Distributions that captures the dependencies among the correspondences. And, the global search is a hopping search process across the minimal set space controlled by photometric properties. Using a novel experimental protocol that involves computing errors for manually marked ground truth points and images with outlier rates as high as 90 percent, we find that BLOGS is better than related approaches such as MAPSAC [1], NAPSAC [2], and BEEM [3]. BLOGS results are of similar quality as other approaches, but BLOGS generate them in 10 times fewer iterations. The time per iteration for BLOGS is also the lowest among the ones we studied.

[1]  L. Tierney.  Markov Chains for Exploring Posterior Distributions , 1994 .

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[4]  Tat-Jun Chin,et al.  Robust fitting of multiple structures: The statistical learning approach , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Philip H. S. Torr,et al.  Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting , 2002, International Journal of Computer Vision.

[6]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[7]  Philip H. S. Torr,et al.  IMPSAC: Synthesis of Importance Sampling and Random Sample Consensus , 2000, ECCV.

[8]  Slawomir J. Nasuto,et al.  NAPSAC: High Noise, High Dimensional Robust Estimation - it's in the Bag , 2002, BMVC.

[9]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[10]  Zhengyou Zhang,et al.  Determining the Epipolar Geometry and its Uncertainty: A Review , 1998, International Journal of Computer Vision.

[11]  A. Welsh.  On $M$-Processes and $M$-Estimation , 1989 .

[12]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

[13]  Jiri Matas,et al.  Matching with PROSAC - progressive sample consensus , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Xavier Armangué,et al.  Overall view regarding fundamental matrix estimation , 2003, Image Vis. Comput..

[15]  Jiri Matas,et al.  Two-view geometry estimation unaffected by a dominant plane , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Jan-Michael Frahm,et al.  A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus , 2008, ECCV.

[17]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[18]  Sunglok Choi,et al.  Performance Evaluation of RANSAC Family , 2009, BMVC.

[19]  Masatoshi Okutomi,et al.  A branch and contract algorithm for globally optimal fundamental matrix estimation , 2011, CVPR 2011.

[20]  Ilan Shimshoni,et al.  The modified pbM-estimator method and a runtime analysis technique for the RANSAC family , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[21]  Jiri Matas,et al.  Locally Optimized RANSAC , 2003, DAGM-Symposium.

[22]  David W. Murray,et al.  Guided-MLESAC: faster image transform estimation by using matching priors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Yiannis Aloimonos,et al.  A Probabilistic Framework for Correspondence and Egomotion , 2006, WDV.

[24]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[25]  Philip H. S. Torr,et al.  The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix , 1997, International Journal of Computer Vision.

[26]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[27]  Sudeep Sarkar,et al.  BLOGS: Balanced local and global search for non-degenerate two view epipolar geometry , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[28]  Ilan Shimshoni,et al.  Balanced Exploration and Exploitation Model Search for Efficient Epipolar Geometry Estimation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Jan-Michael Frahm,et al.  RANSAC for (Quasi-)Degenerate data (QDEGSAC) , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[30]  Frank Dellaert,et al.  GroupSAC: Efficient consensus in the presence of groupings , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[31]  Charles V. Stewart,et al.  MINPRAN: A New Robust Estimator for Computer Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[33]  Bill Triggs,et al.  Joint feature distributions for image correspondence , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[34]  Zhuowen Tu,et al.  Range image segmentation by an effective jump-diffusion method , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.