A Closed Form Solution to Direct Motion Segmentation

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Motion.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Reducing Drift in Parametric Motion Tracking
On Constrained Optimization Approach To Object Segmentation Chia Han, Xun Wang, Feng Gao, Zhigang Peng, Xiaokun Li, Lei He, William Wee Artificial Intelligence.
Computer Vision Optical Flow
MASKS © 2004 Invitation to 3D vision Lecture 8 Segmentation of Dynamical Scenes.
Motion Estimation I What affects the induced image motion? Camera motion Object motion Scene structure.
Feature tracking. Identify features and track them over video –Small difference between frames –potential large difference overall Standard approach:
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Problem Sets Problem Set 3 –Distributed Tuesday, 3/18. –Due Thursday, 4/3 Problem Set 4 –Distributed Tuesday, 4/1 –Due Tuesday, 4/15. Probably a total.
Feature matching and tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on.
Computing motion between images
CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc Optical Flow & Motion The Factorization Method.
Lecture 19: Optical flow CS6670: Computer Vision Noah Snavely
Agenda The Subspace Clustering Problem Computer Vision Applications
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
KLT tracker & triangulation Class 6 Read Shi and Tomasi’s paper on good features to track
Optical Flow Digital Photography CSE558, Spring 2003 Richard Szeliski (notes cribbed from P. Anandan)
Computer Vision Optical Flow Marc Pollefeys COMP 256 Some slides and illustrations from L. Van Gool, T. Darell, B. Horn, Y. Weiss, P. Anandan, M. Black,
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Learning and Recognizing Human Dynamics in Video Sequences Christoph Bregler Alvina Goh Reading group: 07/06/06.
The Brightness Constraint
Motion Segmentation By Hadas Shahar (and John Y.A.Wang, and Edward H. Adelson, and Wikipedia and YouTube) 1.
Uses of Motion 3D shape reconstruction Segment objects based on motion cues Recognize events and activities Improve video quality Track objects Correct.
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
3D Imaging Motion.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Joint Tracking of Features and Edges STAN BIRCHFIELD AND SHRINIVAS PUNDLIK CLEMSON UNIVERSITY ABSTRACT LUCAS-KANADE AND HORN-SCHUNCK JOINT TRACKING OF.
Final Review Course web page: vision.cis.udel.edu/~cv May 21, 2003  Lecture 37.
Motion Estimation I What affects the induced image motion?
Motion / Optical Flow II Estimation of Motion Field Avneesh Sud.
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Optical flow and keypoint tracking Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Motion Segmentation at Any Speed Shrinivas J. Pundlik Department of Electrical and Computer Engineering, Clemson University, Clemson, SC.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
MOTION Model. Road Map Motion Model Non Parametric Motion Field : Algorithms 1.Optical flow field estimation. 2.Block based motion estimation. 3.Pel –recursive.
Motion Segmentation with Missing Data using PowerFactorization & GPCA
Motion and Optical Flow
Unsupervised Riemannian Clustering of Probability Density Functions
Part I 1 Title 2 Motivation 3 Problem statement 4 Brief review of PCA
Computer Vision, Robotics, Machine Learning and Control Lab
René Vidal and Xiaodong Fan Center for Imaging Science
Segmentation of Dynamic Scenes
Part II Applications of GPCA in Computer Vision
L-infinity minimization in geometric vision problems.
René Vidal Center for Imaging Science
René Vidal Time/Place: T-Th 4.30pm-6pm, Hodson 301
Segmentation of Dynamic Scenes
Robust Visual Motion Analysis: Piecewise-Smooth Optical Flow
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
Segmentation of Dynamic Scenes from Image Intensities
Optical Flow Estimation and Segmentation of Moving Dynamic Textures
Modeling and Segmentation of Dynamic Textures
Observability, Observer Design and Identification of Hybrid Systems
Dynamic Scene Reconstruction using GPCA
Generalized Principal Component Analysis CVPR 2008
Image Primitives and Correspondence
Dynamical Statistical Shape Priors for Level Set Based Tracking
Representing Moving Images with Layers
EE 290A Generalized Principal Component Analysis
Representing Moving Images with Layers
Combining Geometric- and View-Based Approaches for Articulated Pose Estimation David Demirdjian MIT Computer Science and Artificial Intelligence Laboratory.
Filtering Things to take away from this lecture An image as a function
Announcements more panorama slots available now
Segmentation of Dynamical Scenes
Coupled Horn-Schunck and Lukas-Kanade for image processing
Announcements more panorama slots available now
Optical flow and keypoint tracking
Image Registration  Mapping of Evolution
Presentation transcript:

A Closed Form Solution to Direct Motion Segmentation René Vidal and Dheeraj Singaraju Center for Imaging Science Johns Hopkins University

Direct 2-D motion segmentation problem Given the image intensities of a dynamic scene containing multiple motions, determine Number of motion models (translational, affine, etc.) Motion model: translational, or affine Segmentation: model to which each pixel belongs Copyright © JHU Vision Lab

Prior work on 2-D motion segmentation Probabilistic approaches (Jepson-Black’93, Ayer-Sawhney ’95, Darrel-Pentland’95, Weiss-Adelson’96, Weiss’97, Torr-Szeliski-Anandan ’99) Generative model: mixture of 2-D motion models Estimate model using Expectation Maximization E-step: Given motion models, segment image M-step: Given grouping, estimate motion models Local methods (Wang-Adelson ’93) Estimate one model per pixel using a data in a window Cluster models with K-means Aperture problem Motion across boundaries Global methods (Irani-Peleg ’92) Dominant motion: fit one motion model to all pixels Look for misaligned pixels & fit a new model to them Motion competition (Cremers’02) Piece-wise parametric model Minimize Mumford-Shah cost functional Copyright © JHU Vision Lab

Paper contributions Propose a global algebraic solution to direct 2-D motion segmentation Multibody Brightness Constancy Constraint (MBCC) 2-D translational motions and 2-D affine motions Algebraic solution to direct motion segmentation Fit MBCC linearly to image partial derivatives Compute optical flow as the derivative of the MBCC Compute motion model parameters from the cross products of the derivatives of the MBCC Main features Requires no feature tracking or correspondences Fits a mixture of motion models globally Can be used to initialize nonlinear/probabilistic methods Needs improvement Copyright © JHU Vision Lab

Brightness constancy constraint (BCC) Linear motion model: 2-D translational Bilinear motion model: 2-D affine Copyright © JHU Vision Lab

Multibody brightness constancy constraint Mixture of n 2-D motion models Multibody brightness constancy constraint Optical flow from derivative of MBCC Copyright © JHU Vision Lab

Segmentation of 2-D translational motions MBCC is homogeneous polynomial of degree n Linear on embedded data! Number of motions Veronese map Motion models Copyright © JHU Vision Lab

Segmentation of 2-D affine motions MBCC bi-homogeneous polynomials of degree n Lifting Embedding Bilinear on embedded data! Multibody motion matrix Copyright © JHU Vision Lab

Segmentation of 2-D affine motions Multibody motion can be computed linearly from Number of motion models can be computed from the rank of embedded data matrix Individual motion models can be computed from the derivatives of Copyright © JHU Vision Lab

Segmentation of 2-D affine motions If belongs to ith motion, partials of MBC at give linear combination of the rows of As 3rd row of is , 1st and 2nd rows can be obtained from cross product of partials Copyright © JHU Vision Lab

Calculation of number of motions Copyright © JHU Vision Lab

Segmentation of 2-D translational motions Copyright © JHU Vision Lab

Segmentation of 2-D translational motions Good segmentation (71% of frames) Bad segmentation (29% of frames) Copyright © JHU Vision Lab

Segmentation of 2-D affine motions Copyright © JHU Vision Lab

Segmentation of 2-D affine motions Good segmentation (78% of frames) Bad segmentation (22% of frames) Copyright © JHU Vision Lab

Optical flow for 2-D affine motions Copyright © JHU Vision Lab

Conclusions and open problems Algebraic solution to direct motion segmentation Multibody Brightness Constancy Constraint (MBCC) Optical flow & affine models: cross product of MBCC derivatives Main features Requires no feature tracking or correspondences Fits a mixture of motion models globally Can be used to initialize nonlinear/probabilistic methods Open problems How to deal with outliers? How to incorporate smoothing in space and time? How to incorporate multiple resolutions? How to segment motion models of different type? Copyright © JHU Vision Lab

Thanks

Optical flow for 2-D translational motions Copyright © JHU Vision Lab

Best segmentation results Copyright © JHU Vision Lab

Worst segmentation results Copyright © JHU Vision Lab

Best segmentation results Copyright © JHU Vision Lab

Worst segmentation results Copyright © JHU Vision Lab