RATSAC - Random Tree Sampling for Maximum Consensus Estimation

The maximum consensus problem lies at the core of several important computer vision applications as it is one of the most popular criteria for robust estimation. Although considerable efforts have been devoted to solving this problem, exact algorithms are still impractical for real-world data. Randomized hypothesize-and-test approaches such as RANSAC and its variants are therefore still the key players in the field. Revolving around the original RANSAC algorithm, different sampling schemes have been proposed. Despite achieving substantial improvements, these RANSAC variants are still insufficient for highly contaminated data. With the aim to improve the class of randomized techniques, this paper contributes a novel approach to solve the maximum consensus problem using Monte Carlo Tree Search. Based on the theory of the LP-type problems, we reformulate the maximum consensus as an instance of tree search, which advocates the use of Monte Carlo Tree Search to explore the tree. We empirically demonstrate that our method outperforms other state- of-the-art methods in common geometric estimation problems.

[1]  Kristy Sim,et al.  Removing outliers using the L∞ Norm , 2006, CVPR 2006.

[2]  Hongdong Li,et al.  A practical algorithm for L triangulation with outliers , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jiri Matas,et al.  Fixing the Locally Optimized RANSAC , 2012, BMVC.

[4]  Hongdong Li.  Efficient reduction of L-infinity geometry problems , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Anders P. Eriksson,et al.  Guaranteed Outlier Removal with Mixed Integer Linear Programs , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  J. Matoušek,et al.  On geometric optimization with few violated constraints , 1994, SCG '94.

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

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

[9]  Anders P. Eriksson,et al.  Outlier removal using duality , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Masatoshi Okutomi,et al.  Deterministically maximizing feasible subsystem for robust model fitting with unit norm constraint , 2011, CVPR 2011.

[11]  Anton van den Hengel,et al.  RATSAC: An Adaptive Method for Accelerated Robust Estimation and its Application to Video Synchronisation , 2007, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007).

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

[13]  Takeo Kanade,et al.  Quasiconvex Optimization for Robust Geometric Reconstruction , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[15]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[16]  E. Cheney.  Introduction to approximation theory , 1966 .

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

[18]  Carl Olsson,et al.  A polynomial-time bound for matching and registration with outliers , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[20]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[21]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[22]  David Eppstein,et al.  Quasiconvex Programming , 2004, ArXiv.

[23]  Anders P. Eriksson,et al.  Efficient Globally Optimal Consensus Maximisation with Tree Search , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[25]  Hongdong Li,et al.  Consensus set maximization with guaranteed global optimality for robust geometry estimation , 2009, 2009 IEEE 12th International Conference on Computer Vision.