Hierarchical Model-Based Motion Estimation
Published 1 January 1993
P. Anandan, James R. Bergen, K. Hanna, R. Hingorani
Citations185
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.
Abstract
A large body of work in image processing and computer vision over the last 10 or 15 years has been concerned with the estimation of motion of pixels between pairs of images. As can be seen from the contents of this book, the motivation of this work is actually quite diverse, with intended applications ranging from data compression to registration of remotely sensed data to robotics and vehicle navigation. In tandem with this diversity of motivation is a diversity of representation of motion information: from optical flow, to affine or other parametric transformations, to 3-D egomotion plus range or other structure. The purpose of this chapter is to describe a common framework within which all of these computations can be represented.
Keywords
Computer Science
HAL (Le Centre pour la Communication Scientifique Directe)An Iterative Image Registration Technique with an Application to Stereo Vision
11,614 Citations1981Bruce D. Lucas, Takeo Kanade
This work presents a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton-Raphson iteration, and can be generalized to handle rotation, scaling and shearing.
Artificial IntelligenceDetermining optical flow
9,940 Citations1981Berthold K. P. Horn, Brian G. Schunck
IRE Transactions on Communications SystemsThe Laplacian Pyramid as a Compact Image Code
5,994 Citations1983P.M.S. Burt, Edward H. Adelson
A technique for image encoding in which local operators of many scales but identical shape serve as the basis functions, which tends to enhance salient image features and is well suited for many image analysis tasks as well as for image compression.
International Journal of Computer VisionA computational framework and an algorithm for the measurement of visual motion
1,059 Citations1989P. Anandan
This paper describes a hierarchical computational framework for the determination of dense displacement fields from a pair of images, and an algorithm consistent with that framework, based on a scale-based separation of the image intensity information and the process of measuring motion.
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.
Computer Vision Graphics and Image ProcessingDisplacement vectors derived from second-order intensity variations in image sequences
424 Citations1983Hans-Hellmut Nagel
A local approach by minimization of the squared differences between a second-order Taylor expansion of gray values from one frame and the observed gray values within the same window from the next frame appears to be an interesting model for the local computation of optical flow.
International Journal of Computer VisionDirect methods for recovering motion
384 Citations1988Berthold K. P. Horn, Edward Weldon
Direct methods for recovering the motion of an observer in a static environment in the case of pure rotation, pure translation, and arbitrary motion when the rotation is known are developed.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDirect Passive Navigation
238 Citations1987S. Negahdaripour, Berthold K. P. Horn
This correspondence presents two iterative schemes for solving nine nonlinear equations in terms of the motion and surface parameters that are derived from a least-squares fomulation.
Computer Vision Graphics and Image ProcessingInvestigations of multigrid algorithms for the estimation of optical flow fields in image sequences
214 Citations1988W. Enkelmann
A modified formulation of this “oriented smoothness constraint” will be compared to an earlier one, and the iterative solution approach could be improved significantly using multigrid methods.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImage flow segmentation and estimation by constraint line clustering
164 Citations1989Brian G. Schunck
The constraint line clustering algorithm uses a statistical test to estimate the image flow velocity field in the presence of step discontinuities in the image irradiance or velocity field, with particular emphasis on motion estimation and segmentation in situations where motion is the only cue to segmentation.
Object tracking with a moving camera
162 Citations2003Peter J. Burt, James R. Bergen +6 more
The authors describe the implementation of the local and focal levels of a dynamic-motion-analysis framework and concludes that the dynamic approach to motion analysis holds the promise of performing real-time processing to obtain precise, robust results, using practical hardware.
The International Journal of Robotics ResearchContour Evolution, Neighborhood Deformation, and Global Image Flow: Planar Surfaces in Motion
162 Citations1985Allen M. Waxman, Kwangyoen Wohn
Methods for extracting deformation parameters from evolving contours in an image sequence, the image contours being manifestations of surface texture seen in perspective projection, and a second-order polyno mial approximation to the image flow in the neighborhood of a contour are developed.
An estimation-theoretic framework for image-flow computation
135 Citations2002Ajit Singh
The estimation-theoretic nature of the framework and its ability to provide covariance matrices make it very useful in the context of applications such as incremental estimation of scene-depth using techniques based on Kalman filtering.
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.
Direct multi-resolution estimation of ego-motion and structure from motion
84 Citations2002K. Hanna
An iterative algorithm that estimates the motion of a camera through an environment directly from brightness derivatives of an image pair and how the ego-motion constraint can help resolve local motion ambiguities that arise from the aperture problem is described.
Mechanisms for isolating component patterns in the sequential analysis of multiple motion
64 Citations2002Peter J. Burt, R. Hingorani +1 more
The authors determine the conditions for component selection and results can provide important guidance in practical applications of motion analysis.
DSpace@MIT (Massachusetts Institute of Technology)Direct Estimation of Structure and Motion from Multiple Frames
55 Citations1990Joachim Heel
The method combines the ``direct motion vision approach with the theory of recursive estimation'' and processes image sequences of arbitrary length and exploits the redundancy for a significant reduction in error over time.
Annual Meeting Optical Society of AmericaHierarchical, computationally efficient motion estimation algorithm
41 Citations1987James R. Bergen, Edward H. Adelson
This work has developed a low-level intensity based algorithm for computing optical flow that proceeds in a coarse-to-fine manner within an image pyramid representation.
Local motion estimation with the Dynamic Pyramid
18 Citations1986J. Dengler
The Dynamic Pyramid is a tool for analyzing monocular moving image sequences based on the physical model of the elastic membrane, where the cost function consisting of the similarity between the frames and the deformation of the transformation vector field is minimized.