Results 1  10
of
14
Computing Optical Flow with Physical Models of Brightness Variation
"... This paper exploits physical models of timevarying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with generalized brightness constancy constraints that ..."
Abstract

Cited by 80 (1 self)
 Add to MetaCart
This paper exploits physical models of timevarying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with generalized brightness constancy constraints that allow generic types of contrast and illumination changes. Here, we consider models of brightness variation that have timedependent physical causes, namely, changing surface orientation with respect to a directional illuminant, motion of the illuminant, and physical models of heat transport in infrared images. We simultaneously estimate the optical flow and the relevant physical parameters. The estimation problem is formulated using total least squares (TLS), with confidence bounds on the parameters.
The Topological Structure of ScaleSpace Images
, 1998
"... We investigate the "deep structure" of a scalespace image. The emphasis is on topology, i.e. we concentrate on critical pointspoints with vanishing gradientand toppointscritical points with degenerate Hessianand monitor their displacements, respectively generic morsifications in scales ..."
Abstract

Cited by 37 (19 self)
 Add to MetaCart
We investigate the "deep structure" of a scalespace image. The emphasis is on topology, i.e. we concentrate on critical pointspoints with vanishing gradientand toppointscritical points with degenerate Hessianand monitor their displacements, respectively generic morsifications in scalespace. Relevant parts of catastrophe theory in the context of the scalespace paradigm are briefly reviewed, and subsequently rewritten into coordinate independent form. This enables one to implement topological descriptors using a conveniently defined, global coordinate system. 1 Introduction 1.1 Historical Background A fairly well understood way to endow an image with a topology is to embed it into a oneparameter family of images known as a "scalespace image". The parameter encodes "scale" or "resolution" (coarse/fine scale means low/high resolution, respectively). Among the simplest is the linear or Gaussian scalespace model. Proposed by Iijima [13] in the context of pattern recogniti...
The Structure of the Optic Flow Field
, 1998
"... . The optic flow field is defined as preserving the intensity along flowlines. Due to singularities in the image at fixed time, poles are created in the optic flow field. In this paper we describe the generic types of flow singularities and their generic interaction over time. In a general analytic ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
. The optic flow field is defined as preserving the intensity along flowlines. Due to singularities in the image at fixed time, poles are created in the optic flow field. In this paper we describe the generic types of flow singularities and their generic interaction over time. In a general analytic flow field, normally the topology is characterised by the points where the flow vanish again subdivided into repellers, attractors, whirls, and combinations hereof. We point out the resemblance, but also the important differences in the structure of a general analytic flow field, and the structure of the optic flow field expressed through its normal flow. Finally, we show examples of detection of these singularities and events detected from nonlinear combinations of linear filter outputs. Keywords: optic flow, scalespace, singularities, catastrophe theory, equivalence under deformation, transversality, flow structure, flow topology, turbulence, attention. 1 Introduction Most work on opt...
VelocityAdaptation of SpatioTemporal Receptive Fields for Direct Recognition of Activities: An experimental study
 IVC
, 2002
"... This article presents an experimental study of the influence of velocity adaptation when recognizing spatiotemporal patterns using a histogrambased statistical framework. The basic idea consists of adapting the shapes of the filter kernels to the local direction of motion, so as to allow the compu ..."
Abstract

Cited by 8 (7 self)
 Add to MetaCart
This article presents an experimental study of the influence of velocity adaptation when recognizing spatiotemporal patterns using a histogrambased statistical framework. The basic idea consists of adapting the shapes of the filter kernels to the local direction of motion, so as to allow the computation of image descriptors that are invariant to the relative motion in the image plane between the camera and the objects or events that are studied. Based on a framework of recursive spatiotemporal scalespace, we first outline how a straightforward mechanism for local velocity adaptation can be expressed. Then, for a test problem of recognizing activities, we present an experimental evaluation, which shows the advantages of using velocityadapted spatiotemporal receptive fields, compared to directional derivatives or regular partial derivatives for which the filter kernels have not been adapted to the local image motion.
A Total Least Squares Framework for LowLevel Analysis of Dynamic Scenes and Processes
, 1999
"... We present a new method to simultaneously estimate optical flow fields and parameters of dynamic processes, violating the standard brightness change constraint equation. This technique constitutes a straightforward generalization of the standard brightness constancy assumption. Using TLS estimation ..."
Abstract

Cited by 7 (6 self)
 Add to MetaCart
We present a new method to simultaneously estimate optical flow fields and parameters of dynamic processes, violating the standard brightness change constraint equation. This technique constitutes a straightforward generalization of the standard brightness constancy assumption. Using TLS estimation the spatiotemporal brightness structure is analyzed in an entirely symmetric way with respect to the spatial and temporal coordinates. We directly incorporate nonlinear brightness changes based upon differential equations of the underlying processes.
TimeRecursive VelocityAdapted SpatioTemporal ScaleSpace Filters
 In Proc. ECCV, volume 2350 of LNCS
, 2002
"... This paper presents a theory for constructing and computing velocityadapted scalespace filters for spariotemporal image data. ..."
Abstract

Cited by 6 (6 self)
 Add to MetaCart
This paper presents a theory for constructing and computing velocityadapted scalespace filters for spariotemporal image data.
Computing Optic Flow by ScaleSpace Integration of Normal Flow
 in `Proc. ScaleSpace'01
, 2001
"... In this paper we will present a least committed multiscale method for computation of optic flow fields. We extract optic flow fields from normal flow, by fitting the normal components of a local polynomial model of the optic flow to the normal flow. This fitting is based on an analytically solvable ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
In this paper we will present a least committed multiscale method for computation of optic flow fields. We extract optic flow fields from normal flow, by fitting the normal components of a local polynomial model of the optic flow to the normal flow. This fitting is based on an analytically solvable optimization problem, in which an integration scalespace over the normal flow field regularizes the solution. An automatic local scale selection mechanism is used in order to adapt to the local structure of the flow field. The performance profile of the method is compared with that of existing optic flow techniques and we show that the proposed method performs at least as well as the leading algorithms on the benchmark image sequences proposed by Barron et al. [3]. We also do a performance comparison on a synthetic fire particle sequence and apply our method to a real sequence of smoke circulation in a pigsty. Both consist of highly complex nonrigid motion.
Optic flow computation from cardiac MR tagging using a multiscale differential methoda comparative study with velocityencoded MRI
 In Proc. MICCAI 2003
, 2003
"... Abstract. The computation of an optic flow field to reconstruct a dense velocity field from a sequence of tagged MR images faces a major difficulty: a nonconstant pixel intensity. In this paper, we resolved this problem by regarding the MRI sequence as density images, which adhere to a principle of ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
Abstract. The computation of an optic flow field to reconstruct a dense velocity field from a sequence of tagged MR images faces a major difficulty: a nonconstant pixel intensity. In this paper, we resolved this problem by regarding the MRI sequence as density images, which adhere to a principle of conservation of intensity. Based on this principle, optic flow equations are developed based on Gaussian derivatives as differential operators. The multiscale optic flow method is applied to cardiac tagged MRI. A quantitative analysis is presented comparing the reconstructed dense velocity field with a directly acquired velocity field using the velocityencoded (VEC) MRI. 1
Duality Principles in Image Processing and Analysis
 IVCNZ
, 1998
"... Duality is a wellestablished concept in quantum physics. It formalises the fact that what one observes is not nature in itself, butin Heisenberg's words"nature exposed to our method of questioning". In the context of image analysis "question" pertains to some task while "nature" (empirical fa ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Duality is a wellestablished concept in quantum physics. It formalises the fact that what one observes is not nature in itself, butin Heisenberg's words"nature exposed to our method of questioning". In the context of image analysis "question" pertains to some task while "nature" (empirical facts and natural laws) could be taken as the totality of image data supplemented with relevant external factors (knowledge or hypotheses). However, the analogy with quantum physics falls short in at least one fundamental aspect. Whereas the physicist studies nature for nature's sake, endeavouring to reveal natural laws, the image scientist pursues a certain task. This implies a shift of paradigm from the retrospect to the prospect. It will be argued that this leads to a subtle but important difference in the role duality plays in image processing and analysis as compared to the technically similar "bracket" formalism in quantum physics. Duality in the context of image processing and analysis ...
On the Behaviour of Critical Points under Gaussian Blurring
, 1999
"... The level of detail of an image can be expressed in terms of its topology, i.e. the distribution of Morse critical points and their types, which in turn is governed by resolution. We study the behaviour of critical points as a function of resolution for Gaussian scalespace images using catastrophe ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
The level of detail of an image can be expressed in terms of its topology, i.e. the distribution of Morse critical points and their types, which in turn is governed by resolution. We study the behaviour of critical points as a function of resolution for Gaussian scalespace images using catastrophe theory. Unlike existing literature, in which one employs local, socalled canonical coordinates for theoretical convenience, we state results in terms of a global, userdefined Cartesian coordinate system. This enables a fairly straightforward implementation of these results in practice. 1 Introduction A fairly well understood way to endow an image with a topology is to embed it into a oneparameter family of images known as a "scalespace image". The parameter encodes "scale" or "resolution" (coarse/fine scale means low/high resolution, respectively). Among the simplest is the linear or Gaussian scalespace model. Proposed by Iijima [10] in the context of pattern recognition it went largel...