Results 1  10
of
20
An affine invariant interest point detector
 In Proceedings of the 7th European Conference on Computer Vision
, 2002
"... Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of ..."
Abstract

Cited by 1467 (55 self)
 Add to MetaCart
Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighbourhood of an interest point. Our approach allows to solve for these problems simultaneously. It is based on three key ideas: 1) The second moment matrix computed in a point can be used to normalize a region in an affine invariant way (skew and stretch). 2) The scale of the local structure is indicated by local extrema of normalized derivatives over scale. 3) An affineadapted Harris detector determines the location of interest points. A multiscale version of this detector is used for initialization. An iterative algorithm then modifies location, scale and neighbourhood of each point and converges to affine invariant points. For matching and recognition, the image is characterized by a set of affine invariant points; the affine transformation associated with each point allows the computation of an affine invariant descriptor which is also invariant to affine illumination changes. A quantitative comparison of our detector with existing ones shows a significant improvement in the presence of large affine deformations. Experimental results for wide baseline matching show an excellent performance in the presence of large perspective transformations including significant scale changes. Results for recognition are very good for a database with more than 5000 images.
Learning epipolar geometry from image sequences
 in IEEE Conf. on Computer Vision and Pattern Recognition
, 2003
"... ..."
(Show Context)
Covariance Propagation for Guided Matching
"... Abstract. We present a general approach and analytical method for determining a search region for use in guided matching under projective mappings. Our approach is based on the propagation of covariance through a firstorder approximation of the error model to define the boundary of the search regio ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
(Show Context)
Abstract. We present a general approach and analytical method for determining a search region for use in guided matching under projective mappings. Our approach is based on the propagation of covariance through a firstorder approximation of the error model to define the boundary of the search region for a specified probability and we provide an analytical expression for the Jacobian matrix used in the covariance propagation calculation. The resulting closedform expression is easy to implement and generalizes to n dimensions. We apply our method to pointtopoint mapping under a planar homography, pointtoline mapping under a fundamental matrix, and mosaic construction from video in the case of the video looping back on itself. 1
Guided sampling via weak motion models and outlier sample generation for epipolar geometry estimation
 In Proceedings of the CVPR
, 2005
"... The problem of automatic robust estimation of the epipolar geometry in cases where the correspondences are contaminated with a high percentage of outliers is addressed. This situation often occurs when the images have undergone a significant deformation, either due to large rotation or wide baseline ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
(Show Context)
The problem of automatic robust estimation of the epipolar geometry in cases where the correspondences are contaminated with a high percentage of outliers is addressed. This situation often occurs when the images have undergone a significant deformation, either due to large rotation or wide baseline of the cameras. An accelerated algorithm for the identification of the false matches between the views is presented. The algorithm generates a set of weak motion models (WMMs). Each WMM roughly approximates the motion of correspondences from one image to the other. The algorithm represents the distribution of the median of the geometric distances of a correspondence to the WMMs as a mixture model of outlier correspondences and inlier correspondences. The algorithm generates a sample of outlier correspondences from the data. This sample is used to estimate the outlier rate and to estimate the outlier pdf. Using these two pdfs the probability that each correspondence is an inlier is estimated. These probabilities enable guided sampling. In the RANSAC process this guided sampling accelerates the search process. The resulting algorithm when tested on real images achieves a speedup of between one or two orders of magnitude. 1.
Blogs: Balanced local and global search for nondegenerate two view epipolar geometry
, 2009
"... ..."
(Show Context)
Alternatives for optical tracking
, 2001
"... One of the main goals for the UbiCom position tracking system is an accuracy in the centimeter range and a latency of 2 ms. We planned to use inertial tracking to reach the latency requirements, but inertial trackers have drift. The main job of the additional tracking system is to resolve this drift ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
One of the main goals for the UbiCom position tracking system is an accuracy in the centimeter range and a latency of 2 ms. We planned to use inertial tracking to reach the latency requirements, but inertial trackers have drift. The main job of the additional tracking system is to resolve this drift problem. We chose to use a camerabased
15+ MILLION TOP 1% MOST CITED SCIENTIST 12.2% AUTHORS AND EDITORS FROM TOP 500 UNIVERSITIES Maternal Depression, Mothering and Child Development
"... ..."
(Show Context)
Mathematiques, Sciences et technologies de l'information, Informatique
, 2011
"... of local features invariant to affines transformations ..."
(Show Context)