Computation and analysis of image motion: A synopsis of current problems and methods
International Journal of Computer VisionPublished 1 July 1996
Amar Mitiche, Patrick Bouthémy
Citations250
SJR quartileQ1
SJR score3.14
SNIP5.15
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 structured synopsis of the problems in image motion computation and analysis, and of the methods proposed, exposing the underlying models and supporting assumptions are offered.
Abstract
The goal of this paper is to offer a structured synopsis of the problems in image motion computation and analysis, and of the methods proposed, exposing the underlying models and supporting assumptions. A sufficient number of pointers to the literature will be given, concentrating mostly on recent contributions. Emphasis will be on the detection, measurement and segmentation of image motion. Tracking, and deformable motion issues will be also addressed. Finally, a number of related questions which could require more investigations will be presented.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceStochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
17,980 Citations1984Stuart Geman, Donald Geman
The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
International Journal of Computer VisionSnakes: Active contour models
16,951 Citations1988Michael Kass, Andrew Witkin +1 more
This work uses snakes for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest, and uses scale-space continuation to enlarge the capture region surrounding a feature.
Artificial IntelligenceDetermining optical flow
9,940 Citations1981Berthold K. P. Horn, Brian G. Schunck
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Determining Optical Flow</title>
7,496 Citations1981Berthold K. P. Horn, Brian G. Schunck
An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences and is robust in that it can handle image sequences that are quantized rather coarsely in space and time.
Computer Vision and Image UnderstandingActive Shape Models-Their Training and Application
7,187 Citations1995T.F. Cootes, Chris Taylor +2 more
This work describes a method for building models by learning patterns of variability from a training set of correctly annotated images that can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes).
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.
ACM Computing SurveysA survey of image registration techniques
4,042 Citations1992Lisa Gottesfeld Brown
This paper organizes this material by establishing the relationship between the variations in the images and the type of registration techniques which can most appropriately be applied, and establishing a framework for understanding the merits and relationships between the wide variety of existing techniques.
Robot Vision
3,632 Citations1986Berthold K. P. Horn
This book presents a coherent approach to the fast-moving field of computer vision, using a consistent notation based on a detailed understanding of the image formation process, and will provide a useful and current reference for professionals working in the fields of machine vision, image processing, and pattern recognition.
Journal of the Optical Society of America ASpatiotemporal energy models for the perception of motion
3,515 Citations1985Edward H. Adelson, James R. Bergen
A class of models for human motion mechanisms in which the first stage consists of linear filters that are oriented in space-time and tuned in spatial frequency that permit a qualitative understanding of a variety of motion phenomena.
IEEE Transactions on Automatic ControlAn algorithm for tracking multiple targets
2,992 Citations1979D. Reid
CVGIP Image UnderstandingOn active contour models and balloons
2,138 Citations1991Laurent D. Cohen
A model of deformation which solves some of the problems encountered with the original method of energy-minimizing curves and makes the curve behave like a balloon which is inflated by an additional force.
International Journal of Computer VisionFeature extraction from faces using deformable templates
1,368 Citations1992Alan Yuille, Peter W. Hallinan +1 more
De deformable templates are illustrated by showing their ability for tracking features and altering parameter values to minimize the energy function, thereby deforming itself to find the best fit.
Lecture notes in computer scienceA new approach to visual servoing in robotics
1,356 Citations1993Bernard Espiau, François Chaumette +1 more
Vision-based control in robotics based on considering a vision system as a specific sensor dedicated to a task and included in a control servo loop is described, and stability and robustness questions arise.
IEEE Transactions on Robotics and AutomationA new approach to visual servoing in robotics
1,327 Citations1992Bernard Espiau, François Chaumette +1 more
IEEE Transactions on Aerospace and Electronic SystemsEstimating Optimal Tracking Filter Performance for Manned Maneuvering Targets
1,222 Citations1970Robert A. Singer
Journal of the Optical Society of America AModel of human visual-motion sensing
1,184 Citations1985Andrew B. Watson, Albert J. Ahumada
A model of how humans sense the velocity of moving images, using a set of spatial-frequency-tuned, direction-selective linear sensors, agrees qualitatively with human perception.
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.
Digital video processing
1,151 Citations2012
Digital Video Processing, Second Edition, reflects important advances in image processing, computer vision, and video compression, including new applications such as digital cinema, ultra-high-resolution video, and 3D video.
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.
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.
Journal of the Royal Statistical Society Series A (Statistics in Society)Testing Statistical Hypotheses.
976 Citations1988J. D. Biggins, E. L. Lehmann
Active perception
976 Citations1988Růžena Bajcsy
Image and Vision ComputingUse of active shape models for locating structures in medical images
915 Citations1994T.F. Cootes, Andrew Hill +2 more
This paper describes a technique for building compact models of the shape and appearance of flexible objects seen in 2D images, derived from the statistics of labelled images containing examples of the objects.
International Journal of Computer VisionActive vision
832 Citations1988John Aloimonos, Ittay Weiss +1 more
It is proved that an active observer can solve basic vision problems in a much more efficient way than a passive one, and a general methodology is introduced, a general framework in which low-level vision problems should be addressed.
IEEE Journal on Robotics and AutomationDynamic sensor-based control of robots with visual feedback
822 Citations1987L.E. Weiss, Arthur C. Sanderson +1 more
Simulation studies of two- and three-degree-of-freedom systems show the application of an adaptive control algorithm to overcome unknown and nonlinear relations in the feature to world space mapping.
AutomaticaDetecting changes in signals and systems—A survey
797 Citations1988Michèle Basseville
A tentative general framework for change detection in signals and systems is presented, based upon a non-exhaustive survey of available methods, which are presented according to the increasing order of complexity of the change problem.
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.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDisparity Analysis of Images
790 Citations1980Stephen T. Barnard, William B. Thompson
IEEE Transactions on Pattern Analysis and Machine IntelligenceDynamic 3D models with local and global deformations: deformable superquadrics
787 Citations1991Demetri Terzopoulos, Dimitris Metaxas
Proceedings of the IEEEActive perception
787 Citations1988R. Bajcsy
Active perception (active vision specifically) is defined as a study of modeling and control strategies for perception as the existence proof of the proposed theory on obtaining range from focus and stereo/vergence on 2-D segmentation of an image and 3-D shape parameterization.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAn Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences
766 Citations1986Hans-Hellmut Nagel, W. Enkelmann
Results are reported of an investigation about how an ``oriented smoothness'' constraint may be formulated and evaluated about how variations of the displacement vector field only in directions with small or no variation of gray values are restricted.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBoundary finding with parametrically deformable models
754 Citations1992Lawrence H. Staib, James S. Duncan
The authors apply flexible constraints, in the form of a probabilistic deformable model, to the problem of segmenting natural 2-D objects whose diversity and irregularity of shape make them poorly represented in terms of fixed features or form.
Proceedings of the IEEEIll-posed problems in early vision
729 Citations1988M. Bertero, Tomaso Poggio +1 more
Journal of the American Statistical AssociationProbabilistic Solution of Ill-Posed Problems in Computational Vision
698 Citations1987José L. Marroquín, Sanjoy K. Mitter +1 more
This work derives efficient algorithms and describes parallel implementations on digital parallel SIMD architectures, as well as a new class of parallel hybrid computers that mix digital with analog components.
Proceedings of the IEEEOn the computation of motion from sequences of images-A review
646 Citations1988J.K. Aggarwal, N. Nandhakumar
Two distinct paradigms are highlighted: (i) the feature- based approach and (ii) the optical-flow-based approach: the comparative merits/demerits of these approaches are discussed.
International Journal of Computer VisionRobust regression methods for computer vision: A review
638 Citations1991Peter Meer, Doron Mintz +2 more
The least-median-of-squares (LMedS) method, which yields the correct result even when half of the data is severely corrupted, is described and compared with the class of robust M-estimators.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRegistration of Translated and Rotated Images Using Finite Fourier Transforms
596 Citations1987Ercole De Castro, C. Morandi
This correspondence discusses an extension of the method to cover both translational and rotational movements, characterized by an outstanding robustness against correlated noise and disturbances, such as those encountered with nonuniform, time varying illumination.
Journal of the Optical Society of America AModel for the extraction of image flow
569 Citations1987David J. Heeger
The model appears to deal with the aperture problem as well as the human visual system since it extracts the correct velocity for patterns that have large differences in contrast at different spatial orientations, and it simulates psychophysical data on the coherence of sine-grating plaid patterns.
International Journal of Computer VisionOptical flow using spatiotemporal filters
531 Citations1988David J. Heeger
A model is presented that combines the outputs of a set of spatiotemporal motion-energy filters to estimate image velocity and a measure of image-flow uncertainty is formulated; preliminary results indicate that this uncertainty measure may be used to recognize ambiguity due to the aperture problem.
Journal of Visual Communication and Image RepresentationRobust Multiresolution Estimation of Parametric Motion Models
527 Citations1995Jean‐Marc Odobez, P. Bouthemy
Numerical results support this approach, as validated by the use of these algorithms on complex sequences, and two robust estimators in a multi-resolution framework are developed.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBoundary detection by constrained optimization
481 Citations1990Donald Geman, Stuart Geman +2 more
A statistical framework is used for finding boundaries and for partitioning scenes into homogeneous regions and incorporates a measure of disparity between certain spatial features of block pairs of pixel gray levels, using the Kolmogorov-Smirnov nonparametric measures of difference between the distributions of these features.
IEEE Transactions on Pattern Analysis and Machine IntelligenceClosed-form solutions for physically based shape modeling and recognition
466 Citations1991Alex Pentland, Stan Sclaroff
The authors present a closed-form, physically based solution for recovering a three-dimensional (3-D) solid model from collections of 3-D surface measurements that is overconstrained and unique except for rotational symmetries.
Proceedings of the IEEEMotion and structure from feature correspondences: a review
464 Citations1994Thomas S. Huang, Arun N. Netravali
Some of the mathematical techniques borrowed from algebraic geometry, projective geometry, and homotopy theory that are required to solve three-dimensional (3D) motion and structure of rigid objects when their corresponding features are known at different times or are viewed by different cameras are mentioned.
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.
Artificial IntelligenceOn the estimation of optical flow: Relations between different approaches and some new results
425 Citations1987Hans-Hellmut Nagel
An exact solution for the system of partial differential equations proposed by Horn and Schunck (1981) is given at gray value corners and extrema and results in a modification of the “oriented smoothness” approach of Nagel (1983) which thereby becomes considerably simpler.
Journal of Applied StatisticsRandom field models in image analysis
419 Citations1989Richard C. Dubes, Anil K. Jain
This review paper explains how Gibbs and Markov random field models provide a unifying theme for many contemporary problems in image analysis and allows the introduction of spatial context into pixel labeling problems, such as segmentation and restoration.
PerceptionOptical Velocity Patterns, Velocity-Sensitive Neurons, and Space Perception: A Hypothesis
412 Citations1974Kazuhisa Nakayama, Jack M. Loomis
A hypothesis is put forward of how global patterns of optical flow, as discussed by Gibson, Johansson, and others, could be processed by relatively simple physiological mechanisms and it is shown that the convexity cell is insensitive to rotations and in consequence responds in an invariant fashion to aspects of the optical flow which are related to the surrounding environment.
Optica Acta International Journal of OpticsInvariant Properties of the Motion Parallax Field Due to the Movement of Rigid Bodies Relative to an Observer
388 Citations1975
International Journal of Computer VisionA framework for spatiotemporal control in the tracking of visual contours
383 Citations1993Andrew Blake, R. Curwen +1 more
This article combines themes from tracking theory—elastic models and stochastic filtering—with the notion of affine invariance to synthesize a substantially new and demonstrably effective framework for contour tracking.
CVGIP Image UnderstandingTowards Model-Based Recognition of Human Movements in Image Sequences
378 Citations1994Karl Rohr
A model-based approach for the recognition of pedestrians is introduced and the human body is represented by a 3D-model consisting of cylinders, whereas for modelling the movement of walking the authors use data from medical motion studies.
International Journal of Computer VisionComputing occluding and transparent motions
376 Citations1994Michal Irani, Benny Rousso +1 more
A method is presented for detecting and tracking occluding and transparent moving objects, which uses temporal integration without assuming motion constancy, to improve the segmentation of motion analysis and segmentation.
Probability distributions of optical flow
371 Citations2002Eero P. Simoncelli, Edward H. Adelson +1 more
Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImage Analysis Using Multigrid Relaxation Methods
370 Citations1986Demetri Terzopoulos
This paper develops multiresolution iterative algorithms for computing lightness, shape-from-shading, and optical flow and examines the efficiency of these algorithms using synthetic image inputs, and describes the multigrid methodology that is broadly applicable in early vision.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOptical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization
368 Citations1987Joseph K. Kearney, William B. Thompson +1 more
This paper examines the sources of errors for gradient-based techniques that locally solve for optical flow that assume that optical flow is constant in a small neighborhood and the consequence of violating this assumption.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMotion field and optical flow: qualitative properties
334 Citations1989Alessandro Verri, Tomaso Poggio
It is shown that the (smoothed) optical flow and the motion field can be interpreted as vector fields tangent to flows of planar dynamical systems, which give useful informations about the 3-D velocity field and the3-D structure of the scene.
Medical Entomology and ZoologyHands: A Pattern Theoretic Study of Biological Shapes
324 Citations1990Ulf Grenander, Y. K. Chow +1 more
The text develops a global shape model and applies it to the analysis of real pictures acquired with a visible light camera under varying conditions of optical degradation to develop methods for image understanding based on structured restoration, for example automatic detection of abnormalities.
Journal of the American Statistical AssociationStructural Image Restoration through Deformable Templates
321 Citations1991Yali Amit, Ulf Grenander +1 more
This work presents simulations of the posterior distribution that lead to structural reconstructions of the true image in the sense that it enables us to determine landmarks and other characteristic features of the image, as well as to spot pathologies in it.
IEEE Transactions on Automatic ControlTracking methods in a multitarget environment
319 Citations1978Yaakov Bar‐Shalom
This compact and unified presentation of the state-of-art in multitarget tracking was motivated by the recent surge of interest in this problem and is hoped to be useful in view of the need to adapt and modify existing techniques before using them for specific problems.
IEEE Transactions on Pattern Analysis and Machine IntelligenceStereo correspondence through feature grouping and maximal cliques
314 Citations1989Radu Horaud, Thomas Skordas
The authors propose a method for solving the stereo correspondence problem by extracting local image structures and matching similar such structures between two images using a benefit function.
IEEE Transactions on Pattern Analysis and Machine IntelligenceScene Segmentation from Visual Motion Using Global Optimization
300 Citations1987David W. Murray, Bernard F. Buxton
To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used and the search for the globally optimal segmentation is performed using simulated annealing.
Artificial IntelligenceComputations underlying the measurement of visual motion
300 Citations1984Ellen C. Hildreth
A theoretical analysis of the conditions under which this computation of an instantaneous two-dimensional velocity field yields the correct velocity field suggests that the solution is physically plausible; empirical studies show the results to be consistent with human motion perception.
ComputerComputing motion using analog and binary resistive networks
295 Citations1988James Hutchinson, Christof Koch +2 more
The authors describe recent developments in the theory of early vision that led from the formulation of the motion problem as an ill-posed one to its solution by minimizing certain 'cost' functions by mapping onto simple analog and digital resistive networks.
Signal ProcessingStatistical model-based change detection in moving video
290 Citations1993Til Aach, André Kaup +1 more
This method serves three purposes: it accurately locates boundaries between changed and unchanged areas, it brings to bear a regularizing effect on these boundaries in order to smooth them, and it eliminates small regions if the original data permits this.
Purposive and qualitative active vision
289 Citations2002John Aloimonos
The traditional view of the problem of computer vision as a recovery problem is questioned, and the paradigm of purposive-qualitative vision is offered as an alternative and the design of the Medusa of CVL is described.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBayesian estimation of motion vector fields
286 Citations1992Janusz Konrad, Éric Dubois
A stochastic approach to the estimation of 2D motion vector fields from time-varying images is presented and the maximum a posteriori probability (MAP) estimation is incorporated into a hierarchical environment to deal efficiently with large displacements.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMultimodal estimation of discontinuous optical flow using Markov random fields
255 Citations1993Fabrice Heitz, Patrick Bouthémy
It is shown that multiple constraints can provide more accurate flow estimation in a wide range of circumstances and is presented a multimodal approach to the problem of motion estimation in which the computation of visual motion is based on several complementary constraints.
Image and Vision ComputingTracking line segments
250 Citations1990Rachid Deriche, Olivier Faugeras
The development and implementation of a line segment-based token tracker that combines prediction and matching steps and is illustrated in several experiments that have been carried out considering noisy synthetic data and real scenes obtained from the INRIA mobile robot.
Robust dynamic motion estimation over time
241 Citations2002Michael J. Black, P. Anandan
A highly parallel incremental stochastic minimization algorithm is presented which has a number of advantages over previous approaches and the incremental nature of the scheme makes it dynamic and permits the detection of occlusion and disocclusion boundaries.
International Journal of Computer VisionAutomatic extraction of deformable part models
232 Citations1990Alex Pentland
A system that first segments an image into parts, and then fits deformable models to range data associated with the image, which significantly improves the computational complexity of both model recovery and subsequent processing.
International Journal of Computer VisionMotion segmentation and qualitative dynamic scene analysis from an image sequence
228 Citations1993Patrick Bouthémy, Édouard François
This article presents a motion-based segmentation method relying on 2-D affine motion models and a statistical regularization approach which ensures stable motion- based partitions and results obtained on several real-image sequences corresponding to complex outdoor situations are reported.
International Journal of Computer VisionRobust computation of optical flow in a multi-scale differential framework
226 Citations1995Joseph Weber, Jitendra Malik
A new algorithm for computing optical flow in a differential framework based on a robust version of total least squares is developed, incorporating only past time frames.
IEEE Transactions on Pattern Analysis and Machine IntelligenceObstacle avoidance using flow field divergence
222 Citations1989Randal C. Nelson, John Aloimonos
It is shown that a quantity termed the directional divergence of the 2-D motion field can be used as a reliable indicator of the presence of obstacles in the visual field of an observer undergoing generalized rotational and translational motion.
International Journal of Computer VisionDetecting moving objects
218 Citations1990William B. Thompson, Ting-Chuen Pong
It is concluded that in realistic situations, detection using visual information alone is quite difficult, particularly when the camera may also beMoving object detection based primarily on optical flow is concluded.
PerceptionNeural Mechanisms of Visual Perception
214 Citations1997Tat'yana Grigor'yevna Wiesel
The processing of visual information at the level of the striate cortex in the cat and monkey is discussed, and technical advances that have greatly facilitated the analysis of the neural mechanisms of visual perception are described.
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 Signal ProcessingDetecting small, moving objects in image sequences using sequential hypothesis testing
208 Citations1991Steven D. Blostein, Thomas S. Huang
An algorithm is proposed for the solution of the class of multidimensional detection problems concerning the detection of small, barely discernible, moving objects of unknown position and velocity in a sequence of digital images, modeled as GWN.
IEEE Transactions on Image ProcessingA computational vision approach to image registration
195 Citations1993Qian Zheng, Rama Chellappa
International Journal of Computer VisionA mathematical analysis of the motion coherence theory
194 Citations1989Alan Yuille, Norberto M. Grzywacz
A detailed theoretical analysis of the motion coherence theory is provided, which places short-range and long-range motion in the same computational framework and provides a way to define interactions between the two processes.
Lecture notes in computer scienceTracking points on deformable objects using curvature information
194 Citations1992Isaac Cohen, Nicholas Ayache +1 more
A significant improvement is presented to the approach of Duncan et al. to analyze the deformations of curves in sequences of 2D images based on the paradigm that high curvature points usually possess an anatomical meaning, and are therefore good landmarks to guide the matching process.
Computer Vision Graphics and Image ProcessingIllumination independent change detection for real world image sequences
185 Citations1989Kurt D. Skifstad, Ramesh Jain
Two techniques for change detection are presented that have been developed to deal with the more general scenario where illuination is not assumed to be constant, and results are presented for applying each of the techniques discussed to various image pairs.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBinocular Image Flows: Steps Toward Stereo-Motion Fusion
184 Citations1986Allen M. Waxman, James H. Duncan
A new module is described here which unifies stereo and motion analysis in a manner in which each helps to overcome the other's short-comings and points to the importance of the ratio, rate of change of disparity, and its possible role in establishing stereo correspondence.
IEEE Transactions on Pattern Analysis and Machine IntelligenceComputerized flow field analysis: oriented texture fields
182 Citations1992A. Ravishankar Rao, Ramesh Jain
The authors use the geometric theory of differential equations to derive a symbol set based on the visual appearance of phase portraits which are a geometric representation of the solution curves of a system of differential equation.
Lecture notes in computer scienceDetecting and tracking multiple moving objects using temporal integration
179 Citations1992Michal Irani, Benny Rousso +1 more
This work tracks multiple moving objects in image sequences using a combination of motion detection and segmentation, which can become complicated as image motion may change significantly between frames, like with camera vibrations.
Computer Vision Graphics and Image ProcessingNew likelihood test methods for change detection in image sequences
173 Citations1984Yun-Hsiang Hsu, Hans-Hellmut Nagel +1 more
Results encouraged investigations into modeling the picture as a mosaic of patches where the gray-value function within each patch is described as a second-order bivariate polynomial of the pixel coordinates, facilitating the determination of threshold values related to a priori confidence limits.
Image and Vision ComputingFrom image sequences towards conceptual descriptions
172 Citations1988Hans-Hellmut Nagel
It is suggested to introduce a ‘generically describable situation’ as a new conceptual unit for the computer-internal representation of more complex discourse worlds.
Lecture notes in computer scienceSurface orientation and time to contact from image divergence and deformation
165 Citations1992Roberto Cipolla, Andrew Blake
A novel method to measure the differential invariants of the image velocity field robustly by computing average values from the integral of normal image velocities around image contours, equivalent to measuring the temporal changes in the area of a closed contour.
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.
Motion Analysis and Image Sequence Processing
160 Citations1993M. Ibrahim Sezan, Reginald L. Lagendijk
This paper presents an Estimation Theoretic Perspective on Image Processing and the Calculation of Optical Flow from a Hierarchical Model-Based Motion Estimation perspective, and discusses 3-D Median Structures for Image Sequence Filtering and Coding and Human Facial Motion Analysis and Synthesis with Applications to Model-based Coding.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDynamic Occlusion Analysis in Optical Flow Fields
156 Citations1985William B. Thompson, Kathleen M. Mutch +1 more
An edge detection algorithm sensitive to changes in flow fields likely to be associated with occlusion, patterned after the Marr-Hildreth zero-crossing detectors currently used to locate boundaries in scalar fields is derived.
CVGIP Image UnderstandingQualitative recognition of motion using temporal texture
155 Citations1992Randal C. Nelson, Ramprasad Polana
It is shown that certain statistical spatial and temporal features that can be derived from approximations to the motion field have invariant properties, and can be used to classify regional activities such as windblown trees, ripples on water, or chaotic fluid flow, that are characterized by complex, nonrigid motion.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA maximum likelihood framework for determining moving edges
152 Citations1989Patrick Bouthémy
This method can be of interest for motion-analysis schemes, not only for supplying spatiotemporal segmentation, but also for extracting local motion information, as it can cope with occlusion contours and important displacement magnitude.
Signal Processing Image CommunicationMotion compensating interpolation considering covered and uncovered background
151 Citations1989Robert Thoma, Matthias Bierling
An improved algorithm for motion compensating interpolation of images in digital television sequences provides a remarkably improved rendition of motion, even if video sequences are strongly distorted with coding noise caused by a low bit rate coding process.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMatching Images Using Linear Features
144 Citations1984Gérard Medioni, Ramakant Nevatia
This work gives results on complex aerial images which contain many image differences, caused by varying sun position, different seasons, and imaging environments, and also structural changes caused by man-made alterations such as new construction.
CVGIP Image UnderstandingRegion-Based Tracking Using Affine Motion Models in Long Image Sequences
142 Citations1994François G. Meyer, Patrick Bouthémy
A pursuit algorithm has been designed that directly tracks the region representing the projection of a moving object in the image, rather than relying on the set of trajectories of individual points or segments, which makes it possible to predict the position of the target in the next frame.
International Journal of Computer VisionGeneralizing Epipolar-Plane Image Analysis on the spatiotemporal surface
139 Citations1989H. Harlyn Baker, Robert C. Bolles
A generalization of this analysis is developed that enables varying view direction, including variation over time, and provides three-dimensional connectivity information for building coherent spatial descriptions of observed objects; and operates sequentially, allowing initiation and refinement of scene feature estimates while the sensor is in motion.
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.
…