1 Hierarchical Image-Motion Segmentation using Swendsen-Wang Cuts Adrian Barbu Siemens Corporate Research Princeton, NJ Acknowledgements: S.C. Zhu, Y.N.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

HOPS: Efficient Region Labeling using Higher Order Proxy Neighborhoods Albert Y. C. Chen 1, Jason J. Corso 1, and Le Wang 2 1 Dept. of Computer Science.
A Hierarchical Multiple Target Tracking Algorithm for Sensor Networks Songhwai Oh and Shankar Sastry EECS, Berkeley Nest Retreat, Jan
I Images as graphs Fully-connected graph – node for every pixel – link between every pair of pixels, p,q – similarity w ij for each link j w ij c Source:
Markov-Chain Monte Carlo
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
EE462 MLCV Lecture Introduction of Graphical Models Markov Random Fields Segmentation Tae-Kyun Kim 1.
Image Parsing: Unifying Segmentation and Detection Z. Tu, X. Chen, A.L. Yuille and S-C. Hz ICCV 2003 (Marr Prize) & IJCV 2005 Sanketh Shetty.
Jun Zhu Dept. of Comp. Sci. & Tech., Tsinghua University This work was done when I was a visiting researcher at CMU. Joint.
Hidden Markov Model based 2D Shape Classification Ninad Thakoor 1 and Jean Gao 2 1 Electrical Engineering, University of Texas at Arlington, TX-76013,
Bayesian statistics – MCMC techniques
Self-Validated Labeling of MRFs for Image Segmentation Wei Feng 1,2, Jiaya Jia 2 and Zhi-Qiang Liu 1 1. School of Creative Media, City University of Hong.
CS774. Markov Random Field : Theory and Application Lecture 16 Kyomin Jung KAIST Nov
Lecture 6 Image Segmentation
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
Segmentation. Terminology Segmentation, grouping, perceptual organization: gathering features that belong together Fitting: associating a model with observed.
Hierarchical Region-Based Segmentation by Ratio-Contour Jun Wang April 28, 2004 Course Project of CSCE 790.
CS 376b Introduction to Computer Vision 04 / 08 / 2008 Instructor: Michael Eckmann.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
A Study of Approaches for Object Recognition
Primal Sketch Integrating Structure and Texture Ying Nian Wu UCLA Department of Statistics Keck Meeting April 28, 2006 Guo, Zhu, Wu (ICCV, 2003; GMBV,
Particle filters (continued…). Recall Particle filters –Track state sequence x i given the measurements ( y 0, y 1, …., y i ) –Non-linear dynamics –Non-linear.
Today Introduction to MCMC Particle filters and MCMC
Measuring Uncertainty in Graph Cut Solutions Pushmeet Kohli Philip H.S. Torr Department of Computing Oxford Brookes University.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Computer Vision Segmentation Marc Pollefeys COMP 256 Some slides and illustrations from D. Forsyth, T. Darrel,...
Data-Driven Markov Chain Monte Carlo Presented by Tomasz MalisiewiczTomasz Malisiewicz for Advanced PerceptionAdvanced Perception 3/1/2006.
Graph-based Segmentation
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.
Computer Vision James Hays, Brown
Inference Algorithms: A Tutorial Yuanlu Xu, SYSU, China
Learning Based Hierarchical Vessel Segmentation
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
Introduction to MCMC and BUGS. Computational problems More parameters -> even more parameter combinations Exact computation and grid approximation become.
Image Segmentation Seminar III Xiaofeng Fan. Today ’ s Presentation Problem Definition Problem Definition Approach Approach Segmentation Methods Segmentation.
Hierarchical Distributed Genetic Algorithm for Image Segmentation Hanchuan Peng, Fuhui Long*, Zheru Chi, and Wanshi Siu {fhlong, phc,
City University of Hong Kong 18 th Intl. Conf. Pattern Recognition Self-Validated and Spatially Coherent Clustering with NS-MRF and Graph Cuts Wei Feng.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
Markov Random Fields Probabilistic Models for Images
1 Markov Random Fields with Efficient Approximations Yuri Boykov, Olga Veksler, Ramin Zabih Computer Science Department CORNELL UNIVERSITY.
CS654: Digital Image Analysis Lecture 30: Clustering based Segmentation Slides are adapted from:
CS654: Digital Image Analysis
Stable Multi-Target Tracking in Real-Time Surveillance Video
Face Detection Using Large Margin Classifiers Ming-Hsuan Yang Dan Roth Narendra Ahuja Presented by Kiang “Sean” Zhou Beckman Institute University of Illinois.
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Approximate Inference: Decomposition Methods with Applications to Computer Vision Kyomin Jung ( KAIST ) Joint work with Pushmeet Kohli (Microsoft Research)
Presenter : Kuang-Jui Hsu Date : 2011/3/24(Thur.).
Efficient Belief Propagation for Image Restoration Qi Zhao Mar.22,2006.
Graph Algorithms for Vision Amy Gale November 5, 2002.
Segmentation Through Optimization Pyry Matikainen.
CS Statistical Machine learning Lecture 25 Yuan (Alan) Qi Purdue CS Nov
Cell Segmentation in Microscopy Imagery Using a Bag of Local Bayesian Classifiers Zhaozheng Yin RI/CMU, Fall 2009.
Bayesian Inference and Visual Processing: Image Parsing & DDMCMC. Alan Yuille (Dept. Statistics. UCLA) Tu, Chen, Yuille & Zhu (ICCV 2003).
Motion Segmentation at Any Speed Shrinivas J. Pundlik Department of Electrical and Computer Engineering, Clemson University, Clemson, SC.
Some links between min-cuts, optimal spanning forests and watersheds Cédric Allène, Jean-Yves Audibert, Michel Couprie, Jean Cousty & Renaud Keriven ENPC.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Learning Image Statistics for Bayesian Tracking Hedvig Sidenbladh KTH, Sweden Michael Black Brown University, RI, USA
Student Gesture Recognition System in Classroom 2.0 Chiung-Yao Fang, Min-Han Kuo, Greg-C Lee, and Sei-Wang Chen Department of Computer Science and Information.
Sublinear Computational Time Modeling in Statistical Machine Learning Theory for Markov Random Fields Kazuyuki Tanaka GSIS, Tohoku University, Sendai,
Simple Instances of Swendson-Wang & RJMCMC
Markov Random Fields with Efficient Approximations
STEREO MATCHING USING POPULATION-BASED MCMC
Outline Image Segmentation by Data-Driven Markov Chain Monte Carlo
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
Image Parsing & DDMCMC. Alan Yuille (Dept. Statistics. UCLA)
Design of Hierarchical Classifiers for Efficient and Accurate Pattern Classification M N S S K Pavan Kumar Advisor : Dr. C. V. Jawahar.
Markov Random Fields Presented by: Vladan Radosavljevic.
CSSE463: Image Recognition Day 23
Presentation transcript:

1 Hierarchical Image-Motion Segmentation using Swendsen-Wang Cuts Adrian Barbu Siemens Corporate Research Princeton, NJ Acknowledgements: S.C. Zhu, Y.N. Wu, A.L. Yuille et al.

Harvard, May 14 th, of 39 Talk Outline The Swendsen-Wang Cuts algorithm The original Swendsen-Wang algorithm Generalization to arbitrary probabilities Multi-Grid and Multi-Level Swendsen-Wang Cuts Application: Hierarchical Image-Motion Segmentation Conclusions and future work

Harvard, May 14 th, of 39 Swendsen-Wang for Ising / Potts Models Swedsen-Wang (1987) is an extremely smart idea that flips a patch at a time. Each edge in the lattice e= is associated a probability q=e - . 1. If s and t have different labels at the current state, e is turned off. If s and t have the same label, e is turned off with probability q. Thus each object is broken into a number of connected components (subgraphs). 2. One or many components are chosen at random. 3. The collective label is changed randomly to any of the labels.

Harvard, May 14 th, of 39 The Swendsen-Wang Algorithm Pros Computationally efficient in sampling the Ising/Potts models Cons: Limited to Ising / Potts models and factorized distributions Not informed by data, slows down in the presence of an external field (data term) Swendsen Wang Cuts Generalizes Swendsen-Wang to arbitrary posterior probabilities Improves the clustering step by using the image data

Harvard, May 14 th, of 39 SW Cuts: the Acceptance Probability Theorem (Metropolis-Hastings) For any proposal probability q(A  B) and probability p(A), if the Markov chain moves by taking samples from q(A  B) which are accepted with probability then the Markov chain is reversible with respect to p and has stationary distribution p. Theorem (Barbu,Zhu ‘03). The acceptance probability for the Swendsen-Wang Cuts algorithm is

Harvard, May 14 th, of Initialize a graph partition 2. Repeat, for current state A= π State A The Swendsen-Wang Cuts Algorithm Swendsen-Wang Cuts: SWC Input: G o =, discriminative probabilities q e, e  E o, and generative posterior probability p(W|I). Output: Samples W~p(W|I). 7. Select a connected component V 0  CP at random 9. Accept the move with probability α(A  B). 3. Repeat for each subgraph G l =, l=1,2,...,n in A 4. For e  E l turn e=“on” with probability q e. 5. Partition G l into n l connected components: g li =, i=1,...,n l 6. Collect all the connected components in CP={V li : l=1,...,n, i=1,...,n l }. CP The initial graph G o 8. Propose to reassign V 0 to a subgraph G l’, l' follows a probability q(l'|V 0,A) State B

Harvard, May 14 th, of 39 Advantages of the SW Cuts Algorithm Our algorithm bridges the gap between the specialized and generic algorithms: Generally applicable – allows usage of complex models beyond the scope of the specialized algorithms Computationally efficient – performance comparable with the specialized algorithms Reversible and ergodic – theoretically guaranteed to eventually find the global optimum

Harvard, May 14 th, of 39 Hierarchical Image-Motion Segmentation Three-level representation: – Level 0: Pixels are grouped into atomic regions r ijk of relatively constant motion and intensity – motion parameters (u ijk,v ijk ) – intensity histogram h ijk – Level 1: Atomic regions are grouped into intensity regions R ij of coherent motion with intensity models H ij – Level 2: Intensity regions are grouped into moving objects O i with motion parameters  i

Harvard, May 14 th, of 39 Multi-Grid SWC 1. Select an attention window  ½ G. 2. Cluster the vertices within  and select a connected component R 3. Swap the label of R 4. Accept the swap with probability, using as boundary condition.

Harvard, May 14 th, of 39 Multi-Level SWC 1. Select a level s, usually in an increasing order. 2. Cluster the vertices in G (s) and select a connected component R 3. Swap the label of R 4. Accept the swap with probability, using the lower levels, denoted by X (<s), as boundary conditions.

Harvard, May 14 th, of 39 Hierarchical Image-Motion Segmentation Modeling occlusion Accreted (disoccluded) pixels Motion pixels Accreted pixels Bayesian formulation Motion pixels explained by motion Intensity segmentation factor with generative and histogram models.

Harvard, May 14 th, of 39 Hierarchical Image-Motion Segmentation The prior has factors for Smoothness of motion Main motion for each object Boundary length Number of labels

Harvard, May 14 th, of 39 Designing the Edge Weights Level 0: Pixel similarity Common motion Histogram H j Histogram H i Level 1: Motion histogram M i Motion histogram M j Level 2:

Harvard, May 14 th, of 39 Experiments Image SegmentationMotion Segmentation Input sequence Image SegmentationMotion Segmentation Input sequence

Harvard, May 14 th, of 39 Experiments Image SegmentationMotion Segmentation Input sequence Image SegmentationMotion Segmentation Input sequence

Harvard, May 14 th, of 39 Conclusion Two extensions: Swendsen-Wang Cuts Samples arbitrary probabilities on Graph Partitions Efficient by using data-driven techniques Hundreds of times faster than Gibbs sampler Marginal Space Learning Constrain search by learning in Marginal Spaces Six orders of magnitude speedup with great accuracy Robust, complex statistical model by supervised learning

Harvard, May 14 th, of 39 Future Work Algorithm Boosting Any algorithm has a success rate and an error rate Can combine algorithms into a more robust algorithm by supervised learning Proof of concept for Image Registration Hierarchical Computing Efficient representation of Top-Down and Bottom-Up communication using specialized dictionaries Robust integration of multiple MSL paths by Algorithm Boosting Applications to medical imaging 3D curve localization and tracking Brain segmentation Lymph node detection

Harvard, May 14 th, of 39 References  A. Barbu, S.C. Zhu. Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities, IEEE Trans. PAMI, August  A. Barbu, S.C. Zhu. Generalizing Swendsen-Wang for Image Analysis. To appear in J. Comp. Graph. Stat. Thank You!