Multiframe Motion Segmentation with Missing Data Using PowerFactorization and GPCA
International Journal of Computer VisionPublished 26 November 2007Open access
René Vidal, Roberto Tron, Richard Hartley
Citations224
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This algorithm involves projecting all point trajectories onto a 5-dimensional subspace using the SVD, the PowerFactorization method, or RANSAC, and fitting multiple linear subspaces representing different rigid-body motions to the points in ℝ5 using GPCA.
Abstract
We consider the problem of segmenting multiple rigid-body motions from point correspondences in multiple affine views. We cast this problem as a subspace clustering problem in which point trajectories associated with each motion live in a linear subspace
Keywords
Computer ScienceEngineering
Communications of the ACMRandom sample consensus
25,463 Citations1981Martin A. Fischler, Robert C. Bolles
New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
On Spectral Clustering: Analysis and an algorithm
7,751 Citations2001Andrew Y. Ng, Michael I. Jordan +1 more
A simple spectral clustering algorithm that can be implemented using a few lines of Matlab is presented, and tools from matrix perturbation theory are used to analyze the algorithm, and give conditions under which it can be expected to do well.
International Journal of Computer VisionShape and motion from image streams under orthography: a factorization method
2,884 Citations1992Carlo Tomasi, Takeo Kanade
A factorization method is developed that can overcome the difficulty by recovering shape and motion under orthography without computing depth as an intermediate step, and gives accurate results.
IEEE Transactions on Pattern Analysis and Machine IntelligenceGeneralized principal component analysis (GPCA)
1,055 Citations2005Renè Vidal, Yi Ma +1 more
An algebro-geometric solution to the problem of segmenting an unknown number of subspaces of unknown and varying dimensions from sample data points and applications of GPCA to computer vision problems such as face clustering, temporal video segmentation, and 3D motion segmentation from point correspondences in multiple affine views are presented.
Segmentation using eigenvectors: a unifying view
722 Citations1999Yaakov Weiss
A unified treatment of eigenvectors of block matrices based on eigendecompositions in the context of segmentation is given, and close connections between them are shown while highlighting their distinguishing features.
International Journal of Computer VisionA Multibody Factorization Method for Independently Moving Objects
688 Citations1998João Paulo Costeira, Takeo Kanade
A new method for separating and recovering the motion and shape of multiple independently moving objects in a sequence of images by introducing a mathematical construct of object shapes, called the shape interaction matrix, which is invariant to both the object motions and the selection of coordinate systems.
A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms
679 Citations2007Roberto Tron, René Víctor Valqui Vidal
This paper compares four 3D motion segmentation algorithms for affine cameras on a benchmark of 155 motion sequences of checkerboard, traffic, and articulated scenes.
Lecture notes in computer scienceA General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate
506 Citations2006Jingyu Yan, Marc Pollefeys
This work proposes a general framework for motion segmentation under affine projections which utilizes two properties of trajectory data: geometric constraint and locality, and estimates a number of linear manifolds, whose dimensions are unknown beforehand.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA paraperspective factorization method for shape and motion recovery
467 Citations1997Conrad J. Poelman, Takeo Kanade
This work has shown that the paraperspective factorization method can be applied to a much wider range of motion scenarios, including image sequences containing motion toward the camera and aerial image sequences of terrain taken from a low-altitude airplane.
Robust principal component analysis for computer vision
391 Citations2002Fernando De la Torre, M.J. Black
The theory of Robust Principal Component Analysis is developed and a robust M-estimation algorithm is described for learning linear multi-variate representations of high dimensional data such as images, which illustrates the benefits of RPCA when outliers are present.
Motion segmentation by subspace separation and model selection
353 Citations2002Kenichi Kanatani
A robust segmentation algorithm by incorporating such techniques as dimension correction, model selection using the geometric AIC, and least-median fitting is presented, demonstrating that oar algorithm dramatically outperforms existing methods.
Damped Newton Algorithms for Matrix Factorization with Missing Data
301 Citations2005Aeron Morgan Buchanan, Andrew Fitzgibbon
A comprehensive comparison of the two strategies for low-rank matrix factorization in the presence of missing data concludes that, although alternation approaches can be very quick, their propensity to glacial convergence in narrow valleys of the cost function means that average-case performance is worse than second-order strategies.
Multibody factorization with uncertainty and missing data using the EM algorithm
206 Citations2004Amit Gruber, Yaakov Weiss
This paper presents a multibody factorization algorithm that can handle arbitrary noise covariance for each feature as well as missing data and derive an expectation-maximization based maximum-likelihood algorithm.
IEEE Transactions on Pattern Analysis and Machine IntelligencePrincipal component analysis with missing data and its application to polyhedral object modeling
189 Citations1995Heung‐Yeung Shum, Katsushi Ikeuchi +1 more
A weighted least-squares (WLS) approach which simultaneously recovers object shape and transformation among different views without recovering interframe motion is developed and is robust against noise and mismatching and generates accurate polyhedral object models.
Motion segmentation with missing data using powerfactorization and GPCA
179 Citations2004Renè Vidal, Richard Hartley
International Journal of Computer VisionMultibody Grouping from Motion Images
166 Citations1998C. W. Gear
A statistical approach is used to estimate the grouping of points to subspaces in the presence of noise by computing which partition has the maximum likelihood.
Factorization-based segmentation of motions
159 Citations2002Terrance E. Boult, Lisa Gottesfeld Brown
International Journal of Computer VisionTwo-View Multibody Structure from Motion
147 Citations2006René Vidal, Yi Ma +2 more
An algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views that exploits the algebraic and geometric properties of the so-called multibody epipolar constraint and its associatedMultibody fundamental matrix.
Degeneracies, dependencies and their implications in multi-body and multi-sequence factorizations
99 Citations2003Lihi Zelnik‐Manor, M. Irani
It is shown that in many cases objects moving with different 3D motions will be captured as a single object using these approaches and that in the case of multiple sequences linear dependencies can supply information for temporal synchronization of sequences and for spatial matching of points across sequences.
PowerFactorization : 3D reconstruction with missing or uncertain data
98 Citations2003Richard Hartley, Frederik Schaffalitzky
The method for incomplete data is applied to several problems of 3D reconstruction, generalizing the Tomasi-Kanade method for orthographic cameras and the Sturm-Triggs method for projective cameras to missing and uncertain data.
Lecture notes in computer scienceGeometric Structure of Degeneracy for Multi-body Motion Segmentation
88 Citations2004Yasuyuki Sugaya, Kenichi Kanatani
This paper analyzes the geometric structure of the degeneracy of the motion model to lead to a new segmentation algorithm: a multi-stage unsupervised learning scheme first using the degenerate motion model and then using the general 3-D motion model.
Motion segmentation based on factorization method and discriminant criterion
57 Citations1999N. Ichimura
A motion segmentation algorithm based on factorization method and discriminant criterion and it is proposed that this grouping is robust against noise and outliers because features with no useful information are automatically rejected.
Multibody grouping via orthogonal subspace decomposition
54 Citations2005Ying Wu, Zhengyou Zhang +2 more
An orthogonal subspace decomposition and grouping technique to approachMultibody structure from motion using the shape signal subspace distance matrix for shape space grouping and the robustness of the proposed approach lies in the fact that the shape space decomposition alleviates the influence of noise.
A Factorization-Based Approach to Articulated Motion Recovery
44 Citations2005Jingyu Yan, Marc Pollefeys
The rank constraint of the global motion subspace of an articulated object is described; an algorithm is given to recover the image motion of a link, either a joint or an axis; and a novel but simple approach is proposed, which is based on subspace clustering, to recover articulated shape and motion from a single-view image sequence.
Estimating the number of independent motions for multibody motion segmentation
36 Citations2002Kenichi Kanatani, Chikara Matsunaga
The mathematical structure of the problem is elucidated, an estimation method using model selection by the geometric AIC, the geometric MDL, and the OIC is presented and techniques for evaluating the reliability of segmentation a posteriori are presented.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMultibody grouping by inference of multiple subspaces from high-dimensional data using oriented-frames
27 Citations2006Zhimin Fan, Jie Zhou +1 more
A novel and robust algorithm is proposed to capture the configuration of the multiple subspace structure and to find the segmentation of objects by clustering the feature points into these inferred subspaces, no matter whether they are independent or correlated.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFast and accurate algorithms for projective multi-image structure from motion
20 Citations2001J. Oliensis, Yakup Genç
The nature of dominant-plane compensation can be considered a small-translation approximation rather than an approximation that the scene is planar, and it is shown that projective algorithms accurately recover the inverse depths and homographies despite the possibility of transforming the structure and motion by a projective transformation.
Lecture notes in computer scienceStructure from Planar Motions with Small Baselines
19 Citations2002Renè Vidal, J. Oliensis
This paper shows how to linearly solve the multi-frame structure from motion problem when the camera translates on a plane with small baselines and arbitrary rotations, while preserving the accuracy, speed and convergence properties of the non-planar algorithm.