Skin and bones: multi-layer, locally affine, optical flow and regularization with transparency
Published 1 January 1996
S.X. Ju, M.J. Black, Allan D. Jepson
Citations130
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
A new method for estimating optical flow that strikes a balance between the flexibility of local dense computations and the robustness and accuracy of global parameterized flow models is described.
Abstract
This paper describes a new methodfor estimuting op-tical jlow that strikes a balance between the jlexibil-ity of local dense compututions and the robustness and accuracy of global parameterized jlow models. An affine model of image motion is used within locul im-age patches while a spatial smoothness constraint on the afine$ow purameters of neighboring patches en-forces continuity of the motion. We refer to this as a “Skin and Bones ” model in which the affine patches cun he thought ofus rigid “bones ” connected by aJEex-ible “skin ”. Since local image putches may coiztuin multiple motions we use a layered representation fir the affine bones. To regularize this luyered motion rep-resentation we develop a new framework for regular-ization with transparency. 1
Keywords
Computer Science
International Journal of Computer VisionPerformance of optical flow techniques
4,271 Citations1994John A. Barron, David J. Fleet +1 more
These comparisons are primarily empirical, and concentrate on the accuracy, reliability, and density of the velocity measurements; they show that performance can differ significantly among the techniques the authors implemented.
Queensland's institutional digital repository (The University of Queensland)Mixture models : inference and applications to clustering
2,074 Citations1988Geoffrey J. McLachlan, K. E. Basford
Computer Vision and Image UnderstandingThe Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
1,563 Citations1996Michael J. Black, P. Anandan
A framework based on robust estimation is presented that addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions of optical flow, and is applied to standard formulations of the optical flow problem thus reducing their sensitivity to violations of their underlying assumptions.
Lecture notes in computer scienceHierarchical model-based motion estimation
1,155 Citations1992James R. Bergen, P. Anandan +2 more
This paper describes a hierarchical estimation framework for the computation of diverse representations of motion information that constrains the overall structure of the motion estimated, a local model that is used in the estimation process, and a coarse-fine refinement strategy.
IEEE Transactions on Image ProcessingRepresenting moving images with layers
1,098 Citations1994J.Y.A. Wang, Edward H. Adelson
A system for representing moving images with sets of overlapping layers that is more flexible than standard image transforms and can capture many important properties of natural image sequences.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDetermining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects
794 Citations1985Gilad Adiv
A new approach for the interpretation of optical flow fields is presented, where the flow field is partitioned into connected segments of flow vectors, where each segment is consistent with a rigid motion of a roughly planar surface.
A framework for the robust estimation of optical flow
446 Citations2002Michael J. Black, P. Anandan
The authors consider the problem of robustly estimating optical flow from a pair of images using a new framework based on robust estimation which addresses violations of the brightness constancy and spatial smoothness assumptions and presents a graduated non-convexity algorithm for recovering optical flow and motion discontinuities.
Journal of the Royal Statistical Society Series C (Applied Statistics)Mixture Models: Inference and Applications to Clustering.
386 Citations1989David J. Hand, Geoffrey J. McLachlan +1 more
Surface modeling with oriented particle systems
295 Citations1992Richard Szeliski, David Tonnesen
A new model of elastic surfaces based on interacting particle systems, which, unlike previous techniques, can be used to join, or extend surfaces without the need for manual intervention.
Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding
254 Citations2002Steven K. Ayer, Harpreet Sawhney
This paper presents one such formulation based on maximum likelihood estimation (MLE) of mixture models and the minimum description length (MDL) encoding principle of layered motion representation, and examines how many motion models adequately describe image motion.
Mixture models for optical flow computation
223 Citations2002Allan Jepson, Michael J. Black
ACM SIGGRAPH Computer GraphicsSurface modeling with oriented particle systems
159 Citations1992Richard Szeliski, David Tonnesen
Robust estimation of a multi-layered motion representation
135 Citations2002Trevor Darrell, Alex Pentland
A layered model of scene segmentation based on explicitly representing the support of a homogeneous region is introduced, which employs parallel robust estimation techniques, and uses a minimal-covering optimization to estimate the number of objects in the scene.
Computing two motions from three frames
94 Citations2002James R. Bergen, Peter J. Burt +2 more
The authors propose an alternative formulation of optical-flow algorithms in which there may be two distinct patterns undergoing coherent motion within a given local analysis region, and present an algorithm for the analysis of two-component motion.
Lecture notes in computer scienceRecursive non-linear estimation of discontinuous flow fields
62 Citations1994Michael J. Black
An incremental continuation method for recursive non-linear estimation that robustly and adaptively recovers optical flow with motion discontinuities over an image sequence is described.
Robust computation of optical flow in a multi-scale differential framework
61 Citations2002Joseph Weber, Jitendra Malik
Motion estimation with quadtree splines
20 Citations2002Richard Szeliski, Heung‐Yeung Shum
This paper presents a motion estimation algorithm based on a new multiresolution representation, the quadtree spline, which combines the advantages of adaptively-sized correlation windows with the speedups obtained with hierarchical basis preconditioners.
Estimating multiple independent motions in segmented images using parametric models with local deformations
16 Citations2002Richard J. Black, Allan Jepson
This paper presents a new model for optical flow based on the motion of planar regions plus local deformations that exploits the strong constraints of parametric approaches while retaining the adaptive nature of regularization approaches.
Multi-layer surface segmentation using energy minimization
10 Citations2002Suthep Madarasmi, Daniel Kersten +1 more
A multilayer, depth planes approach to image segmentation is proposed, where pixels may have arisen from a single smooth surface in the scene are represented in a common layer.