Results 1  10
of
20
Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
 In Proc. BMVC
, 2000
"... `Invariant regions' are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then described by a set of invariant features, which makes it relatively easy to match them between views and under changing illuminati ..."
Abstract

Cited by 167 (5 self)
 Add to MetaCart
`Invariant regions' are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then described by a set of invariant features, which makes it relatively easy to match them between views and under changing illumination. In previous work, we have presented invariant regions that are based on a combination of corners and edges. The application discussed then was image database retrieval. Here, an alternative method for extracting (affinely) invariant regions is given, that does not depend on the presence of edges or corners in the image but is purely intensitybased. Also, we demonstrate the use of such regions for another application, which is wide baseline stereo matching. As a matter of fact, the goal is to build an opportunistic system that exploits several types of invariant regions as it sees fit. This yields more correspondences and a system that can deal with a wider range of images. To increase t...
Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing
 JOURNAL OF SCIENTIFIC COMPUTING
, 2002
"... This paper is devoted to the modeling of real textured images by functional minimization and partial differential equations. Following the ideas of Yves Meyer in a total variation minimization framework of L. Rudin, S. Osher and E. Fatemi, we decompose a given (possible textured) image f into a su ..."
Abstract

Cited by 150 (23 self)
 Add to MetaCart
This paper is devoted to the modeling of real textured images by functional minimization and partial differential equations. Following the ideas of Yves Meyer in a total variation minimization framework of L. Rudin, S. Osher and E. Fatemi, we decompose a given (possible textured) image f into a sum of two functions u + v, where u E BV is a function of bounded variation (a cartoon or sketchy approximation of f), while v is a function representing the texture or noise. To model v we use the space of oscillating functions introduced by Yves Meyer, which is in some sense the dual of the BV space. The new algorithm is very simple, making use of differential equations and is easily solved in practice. Finally, we implement the method by finite differences, and we present various numerical results on real textured images, showing the obtained decomposition u + v, but we also show how the method can be used for texture discrimination and texture segmentation.
Viewpoint Invariant Texture Matching and Wide Baseline Stereo
 In Proc. ICCV
, 2001
"... We describe and demonstrate a texture region descriptor which is invariant to affine geometric and photometric transformations, and insensitive to the shape of the texture region. It is applicable to texture patches which are locally planar and have stationary statistics. The novelty of the descript ..."
Abstract

Cited by 89 (7 self)
 Add to MetaCart
We describe and demonstrate a texture region descriptor which is invariant to affine geometric and photometric transformations, and insensitive to the shape of the texture region. It is applicable to texture patches which are locally planar and have stationary statistics. The novelty of the descriptor is that it is based on statistics aggregated over the region, resulting in richer and more stable descriptors than those computed at a point. Two texture matching applications of this descriptor are demonstrated: (1) it is used to automatically identify regions of the same type of texture, but with varying surface pose, within a single image
Evaluation of features detectors and descriptors based on 3d objects
 IJCV
, 2005
"... We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collec ..."
Abstract

Cited by 82 (0 self)
 Add to MetaCart
We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessianaffine feature finder and SIFT features is most robust to viewpoint change. Harrisaffine combined with SIFT and Hessianaffine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detectordescriptor combination performs well with viewpoint changes of more than 2530 ◦. 1
Object Recognition using Local Affine Frames on Maximally Stable Extremal Regions
"... Viewpointindependent recognition of objects is a fundamental problem in computer vision. Recently, ..."
Abstract

Cited by 37 (0 self)
 Add to MetaCart
Viewpointindependent recognition of objects is a fundamental problem in computer vision. Recently,
Image denoising and decomposition with total variation minimization and oscillatory functions
 J. Math. Imaging Vision
, 2004
"... Abstract. In this paper, we propose a new variational model for image denoising and decomposition, witch combines the total variation minimization model of Rudin, Osher and Fatemi from image restoration, with spaces of oscillatory functions, following recent ideas introduced by Meyer. The spaces int ..."
Abstract

Cited by 37 (5 self)
 Add to MetaCart
Abstract. In this paper, we propose a new variational model for image denoising and decomposition, witch combines the total variation minimization model of Rudin, Osher and Fatemi from image restoration, with spaces of oscillatory functions, following recent ideas introduced by Meyer. The spaces introduced here are appropriate to model oscillatory patterns of zero mean, such as noise or texture. Numerical results of image denoising, image decomposition and texture discrimination are presented, showing that the new models decompose better a given image, possible noisy, into cartoon and oscillatory pattern of zero mean, than the standard ones. The present paper develops further the models previously introduced by the authors in Vese and Osher (Modeling textures with total variation minimization and oscillating patterns in image processing, UCLA CAM Report 0219, May 2002, to appear in Journal of Scientific Computing, 2003). Other recent and related image decomposition models are also discussed.
Image Analysis and P.D.E.s
 IPAM GBM Tutorial
, 2001
"... It is well known that a conveniently rescaled iterated convolution of a linear positive kernel converges to a gaussian. As a consequence, all iterative linear smoothing methods of a signal or an image boil down to the application to the signal of the heat equation. This book explains how a similar a ..."
Abstract

Cited by 13 (2 self)
 Add to MetaCart
It is well known that a conveniently rescaled iterated convolution of a linear positive kernel converges to a gaussian. As a consequence, all iterative linear smoothing methods of a signal or an image boil down to the application to the signal of the heat equation. This book explains how a similar analysis can be performed for image iterative smoothing by a wide class of nonlinear operators, the contrast invariant operators. These monotone operators have a property which makes them suitable for image analysis: they commute with contrast changes of the images. Among them, the median operator which computes alocal \mean value" independent of constrast changes. We prove that all monotone and contrast invariant operators, are asymptotically equivalent (when they become more and more local) to a motion of the image by its curvature. The iteration of these lters is equivalent to the application to the image of a nonlinear heat equation. We give in parallel a classi cation of all image multiscale smoothing methods (the so called \scale space" methods in Computer Vision). It is shown that both approaches (classi cation of iterative ltering methods or of \scale spaces") yield the same, recently discovered, partial dierential equations. Experiments arepresented with both classical and new, contrast invariant and monotone numerical schemes. Figure 1: Zoom on Noise.
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 10 (5 self)
 Add to MetaCart
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.
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.
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.