Results 1  10
of
59
Spacetime Interest Points
 IN ICCV
, 2003
"... Local image features or interest points provide compact and abstract representations of patterns in an image. In this paper, we propose to extend the notion of spatial interest points into the spatiotemporal domain and show how the resulting features often reflect interesting events that can be use ..."
Abstract

Cited by 794 (22 self)
 Add to MetaCart
Local image features or interest points provide compact and abstract representations of patterns in an image. In this paper, we propose to extend the notion of spatial interest points into the spatiotemporal domain and show how the resulting features often reflect interesting events that can be used for a compact representation of video data as well as for its interpretation.. To detect
Reliable Estimation of Dense Optical Flow Fields with Large Displacements
, 2001
"... In this paper we show that a classic optical ow technique by Nagel and Enkelmann (1986) can be regarded as an early anisotropic diusion method with a diusion tensor. We introduce three improvements into the model formulation that (i) avoid inconsistencies caused by centering the brightness term and ..."
Abstract

Cited by 122 (14 self)
 Add to MetaCart
(Show Context)
In this paper we show that a classic optical ow technique by Nagel and Enkelmann (1986) can be regarded as an early anisotropic diusion method with a diusion tensor. We introduce three improvements into the model formulation that (i) avoid inconsistencies caused by centering the brightness term and the smoothness term in dierent images, (ii) use a linear scalespace focusing strategy from coarse to ne scales for avoiding convergence to physically irrelevant local minima, and (iii) create an energy functional that is invariant under linear brightness changes. Applying a gradient descent method to the resulting energy functional leads to a system of diusion{reaction equations. We prove that this system has a unique solution under realistic assumptions on the initial data, and we present an ecient linear implicit numerical scheme in detail. Our method creates ow elds with 100 % density over the entire image domain, it is robust under a large range of parameter variations, and it c...
Dense Disparity Map Estimation Respecting Image Discontinuities: A PDE and ScaleSpace Based Approach
 JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
, 2000
"... We present an energy based approach to estimate a dense disparity map between two images while preserving its discontinuities resulting from image boundaries. We first derive a simplied expression for the disparity that allows us to easily estimate it from a stereo pair of images using an energy min ..."
Abstract

Cited by 85 (11 self)
 Add to MetaCart
We present an energy based approach to estimate a dense disparity map between two images while preserving its discontinuities resulting from image boundaries. We first derive a simplied expression for the disparity that allows us to easily estimate it from a stereo pair of images using an energy minimization approach. We assume that the epipolar geometry is known, and we include this information in the energy model. Discontinuities are preserved by means of a regularization term based on the NagelEnkelmann operator. We investigate the associated EulerLagrange equation of the energy functional, and we approach the solution of the underlying partial differential equation (PDE) using a gradient descent method. In order to reduce the risk to be trapped within some irrelevant local minima during the iterations, we use a focusing strategy based on a linear scalespace. We prove the existence and uniqueness of the underlying parabolic partial differential equation. Experimental results on bot...
The Structure of Locally Orderless Images
, 1998
"... We propose a representation of images in which a global, but not a local topology is defined. The topology is restricted to resolutions up to the extent of the local region of interest (ROI). Although the ROI's may contain many pixels, there is no spatial order on the pixels within the ROI, the ..."
Abstract

Cited by 75 (0 self)
 Add to MetaCart
We propose a representation of images in which a global, but not a local topology is defined. The topology is restricted to resolutions up to the extent of the local region of interest (ROI). Although the ROI's may contain many pixels, there is no spatial order on the pixels within the ROI, the only information preserved is the histogram of pixel values within the ROI's. This can be considered as an extreme case of a textel (texture element) image: The histogram is the limit of texture where the spatial order has been completely disregarded. We argue that locally orderless images are ubiquitous in perception and the visual arts. Formally, the orderless images are most aptly described by three mutually intertwined scale spaces. The scale parameters correspond to the pixellation ("inner scale"), the extent of the ROI's ("outer scale") and the resolution in the histogram ("tonal scale"). We describe how to construct locally orderless images, how to render them, and how to use them in a variety of local and global image processing operations.
Linear ScaleSpace has First been Proposed in Japan
, 1999
"... Linear scalespace is considered to be a modern bottomup tool in computer vision. The American and European vision community, however, is unaware of the fact that it has already been axiomatically derived in 1959 in a Japanese paper by Taizo Iijima. This result formed the starting point of vast li ..."
Abstract

Cited by 42 (5 self)
 Add to MetaCart
Linear scalespace is considered to be a modern bottomup tool in computer vision. The American and European vision community, however, is unaware of the fact that it has already been axiomatically derived in 1959 in a Japanese paper by Taizo Iijima. This result formed the starting point of vast linear scalespace research in Japan ranging from various axiomatic derivations over deep structure analysis to applications to optical character recognition. Since the outcomes of these activities are unknown to western scalespace researchers, we give an overview of the contribution to the development of linear scalespace theories and analyses. In particular, we review four Japanese axiomatic approaches that substantiate linear scalespace theories proposed between 1959 and 1981. By juxtaposing them to ten American or European axiomatics, we present an overview of the stateoftheart in Gaussian scalespace axiomatics. Furthermore, we show that many techniques for analysing linear scalespace have also been pioneered by Japanese researchers.
RealTime Scale Selection in Hybrid MultiScale Representations
, 2003
"... Local scale information extracted from visual data in a bottom up manner constitutes an important cue for a large number of visual tasks. This article presents a framework for how the computation of such scale descriptors can be performed in real time on a standard computer. ..."
Abstract

Cited by 29 (6 self)
 Add to MetaCart
Local scale information extracted from visual data in a bottom up manner constitutes an important cue for a large number of visual tasks. This article presents a framework for how the computation of such scale descriptors can be performed in real time on a standard computer.
Linear SpatioTemporal ScaleSpace
 In Proc. ScaleSpace’97, Springer LNCS 1252
, 1997
"... This article presents a scalespace theory for spatiotemporal data. Starting from the main assumptions that (i) the scalespace should be generated by convolution with a semigroup of filter kernels and that (ii) local extrema must not be enhanced when the scale parameter increases, a complete taxo ..."
Abstract

Cited by 12 (5 self)
 Add to MetaCart
(Show Context)
This article presents a scalespace theory for spatiotemporal data. Starting from the main assumptions that (i) the scalespace should be generated by convolution with a semigroup of filter kernels and that (ii) local extrema must not be enhanced when the scale parameter increases, a complete taxonomy is given of the linear scalespace concepts that satisfy these conditions on spatial, temporal and spatiotemporal domains, including the cases with continuous as well as discrete data.
ScaleSpace Properties of Regularization Methods
 ScaleSpace Theories in Computer Vision. Second International Conference, ScaleSpace ’99, Corfu
"... . In this paper we show that regularization methods form a scalespace where the regularization parameter serves as scale. In analogy to nonlinear diffusion filtering we establish continuity with respect to scale, causality in terms of a maximumminimum principle, simplification properties by means ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
(Show Context)
. In this paper we show that regularization methods form a scalespace where the regularization parameter serves as scale. In analogy to nonlinear diffusion filtering we establish continuity with respect to scale, causality in terms of a maximumminimum principle, simplification properties by means of Lyapunov functionals and convergence to a constant steadystate. We identify nonlinear regularization with a single implicit time step of a diffusion process. This implies that iterated regularization with small regularization parameters is a numerical realization of a diffusion filter. We present numerical experiments in two and three space dimensions illustrating the scalespace behaviour of regularization methods. 1 Introduction There has often been a fruitful interaction between linear scalespace techniques and regularization methods. Torre and Poggio [29] emphasized that differentiation is illposed in the sense of Hadamard, and applying suitable regularization strategies approxim...
An automatic assessment scheme for steel quality inspection
, 1998
"... An automatic assessment scheme for steel quality inspection ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
An automatic assessment scheme for steel quality inspection
Interest point detection and scale selection in spacetime
 of Lecture Notes in Computer Science
, 2003
"... Abstract. Several types of interest point detectors have been proposed for spatial images. This paper investigates how this notion can be generalised to the detection of interesting events in spacetime data. Moreover, we develop a mechanism for spatiotemporal scale selection and detect events at s ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Several types of interest point detectors have been proposed for spatial images. This paper investigates how this notion can be generalised to the detection of interesting events in spacetime data. Moreover, we develop a mechanism for spatiotemporal scale selection and detect events at scales corresponding to their extent in both space and time. To detect spatiotemporal events, we build on the idea of the Harris and Förstner interest point operators and detect regions in spacetime where the image structures have significant local variations in both space and time. In this way, events that correspond to curved spacetime structures are emphasised, while structures with locally constant motion are disregarded. To construct this operator, we start from a multiscale windowed second moment matrix in spacetime, and combine the determinant and the trace in a similar way as for the spatial Harris operator. All spacetime maxima of this operator are then adapted to characteristic scales by maximising a scalenormalised spacetime Laplacian operator over both spatial scales and temporal scales. The motivation for performing temporal scale selection as a complement to previous approaches of spatial scale selection is to be able to robustly capture spatiotemporal events of different temporal extent. It is shown that the resulting approach is truly scale invariant with respect to both spatial scales and temporal scales. The proposed concept is tested on synthetic and real image sequences. It is shown that the operator responds to distinct and stable points in spacetime that often correspond to interesting events. The potential applications of the method are discussed. 1