Results 1  10
of
19
The Computation of Optical Flow
, 1995
"... Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image dis ..."
Abstract

Cited by 295 (10 self)
 Add to MetaCart
(Show Context)
Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image displacements. These are usually called the optical flow field or the image velocity field. Provided that optical flow is a reliable approximation to twodimensional image motion, it may then be used to recover the threedimensional motion of the visual sensor (to within a scale factor) and the threedimensional surface structure (shape or relative depth) through assumptions concerning the structure of the optical flow field, the threedimensional environment and the motion of the sensor. Optical flow may also be used to perform motion detection, object segmentation, timetocollision and focus of expansion calculations, motion compensated encoding and stereo disparity measurement. We investiga...
Multiresolution markov models for signal and image processing
 Proceedings of the IEEE
, 2002
"... This paper reviews a significant component of the rich field of statistical multiresolution (MR) modeling and processing. These MR methods have found application and permeated the literature of a widely scattered set of disciplines, and one of our principal objectives is to present a single, coheren ..."
Abstract

Cited by 153 (17 self)
 Add to MetaCart
This paper reviews a significant component of the rich field of statistical multiresolution (MR) modeling and processing. These MR methods have found application and permeated the literature of a widely scattered set of disciplines, and one of our principal objectives is to present a single, coherent picture of this framework. A second goal is to describe how this topic fits into the even larger field of MR methods and concepts–in particular making ties to topics such as wavelets and multigrid methods. A third is to provide several alternate viewpoints for this body of work, as the methods and concepts we describe intersect with a number of other fields. The principle focus of our presentation is the class of MR Markov processes defined on pyramidally organized trees. The attractiveness of these models stems from both the very efficient algorithms they admit and their expressive power and broad applicability. We show how a variety of methods and models relate to this framework including models for selfsimilar and 1/f processes. We also illustrate how these methods have been used in practice. We discuss the construction of MR models on trees and show how questions that arise in this context make contact with wavelets, state space modeling of time series, system and parameter identification, and hidden
On the Design of Optimal Filters for GradientBased Motion Estimation
 In: Proc. Intern. Conf. on Computer Vision
, 2002
"... Gradient based approaches for motion estimation (OpticalFlow) refer to those techniques that estimate the motion of an image sequence based on local changes in the image intensities. ..."
Abstract

Cited by 27 (0 self)
 Add to MetaCart
Gradient based approaches for motion estimation (OpticalFlow) refer to those techniques that estimate the motion of an image sequence based on local changes in the image intensities.
Probabilistic motion estimation based on temporal coherence
 Neural Computation
, 2000
"... ∗To whom correspondence should be addressed. ..."
(Show Context)
Computationally Efficient Multiscale Estimation of LargeScale Dynamic Systems
 In Proceedings of International Conference on Image Processing
, 1998
"... ..."
Multiscale Modeling and Estimation of LargeScale Dynamic Systems
, 1998
"... Statistical modeling and estimation of largescale dynamic systems is important in a wide range of scientific applications. Conventional optimal estimation methods, however, are impractical due to their computational complexity. In this thesis, we consider an alternative multiscale modeling framewor ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Statistical modeling and estimation of largescale dynamic systems is important in a wide range of scientific applications. Conventional optimal estimation methods, however, are impractical due to their computational complexity. In this thesis, we consider an alternative multiscale modeling framework first developed by Basseville, Willsky, et al. [6, 18]. This multiscale estimation methodology has been successfully applied to a number of largescale static estimation problems, one of which is the application of the socalled 1=f multiscale models to the mapping of ocean surface height from satellite altimetric measurements. A modified 1=f model is used in this thesis to jointly estimate the surface height of the Mediterranean Sea and the correlated component of the measurement noise in order to remove the artifacts apparent in maps generated with the more simplistic assumption that the measurement noise is white. The main
LETTER Communicated by Steven Nowlan Probabilistic Motion Estimation Based on Temporal Coherence
"... We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate the motion �ows in the image sequence. This temporal grouping can be considered a generalization of t ..."
Abstract
 Add to MetaCart
(Show Context)
We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate the motion �ows in the image sequence. This temporal grouping can be considered a generalization of the data association techniques that engineers use to study motion sequences. Our temporal grouping theory is expressed in terms of the Bayesian generalization of standard Kalman �ltering. To implement the theory, we derive a parallel network that shares some properties of cortical networks. Computer simulations of this network demonstrate that our theory qualitatively accounts for psychophysical experiments on motion occlusion and motion outliers. In deriving our theory, we assumed spatial factorizability of the probability distributions and made the approximation of updating the marginal distributions of velocity at each point. This allowed us to perform local computations and simpli�ed our implementation. We argue that these approximations are suitable for the stimuli we are considering (for which spatial coherence effects are negligible). 1
Vision and
"... Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. In this paper, we will present a novel parametrization for multiframe optical flow computation that naturally enables us t ..."
Abstract
 Add to MetaCart
(Show Context)
Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. In this paper, we will present a novel parametrization for multiframe optical flow computation that naturally enables us to embed the assumption of a temporally coherent spatial flow structure, as well as the assumption that the optical flow is smooth along motion trajectories. While the first assumption is realized by expanding spatial regularization over multiple frames, the second assumption is imposed by two novel first and secondorder trajectorial smoothness terms. With respect to the latter, we investigate an adaptive decision scheme that makes a local (per pixel) or global (per sequence) selection of the most appropriate model possible. Experiments show the clear superiority of our approach when compared to existing strategies for imposing temporal coherence. Moreover, we demonstrate the stateoftheart performance of our method by achieving Top 3 results at the widely used Middlebury benchmark. 1.
LongRange Video Motion . . .
, 2006
"... This thesis describes a new approach to video motion estimation, in which motion is represented using a set of particles. Each particle is an image point sample with a longduration trajectory and other properties. To optimize these particles, we measure pointbased matching along the particle traje ..."
Abstract
 Add to MetaCart
(Show Context)
This thesis describes a new approach to video motion estimation, in which motion is represented using a set of particles. Each particle is an image point sample with a longduration trajectory and other properties. To optimize these particles, we measure pointbased matching along the particle trajectories and distortion between the particles. The resulting motion representation is useful for a variety of applications and differs from optical flow, feature tracking, and parametric or layerbased models. We demonstrate the algorithm on challenging realworld videos that include complex scene geometry, multiple types of occlusion, regions with low texture, and nonrigid deformation.