Search For:

Displaying 1-45 out of 45 total
Robust unambiguous parametrization of the essential manifold
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raghav Subbarao, Yakup Genc, Peter Meer
Issue Date:June 2008
pp. 1-8
Analytic manifolds were recently used for motion averaging, segmentation and robust estimation. Here we consider the epipolar constraint for calibrated cameras, which is the most general motion model for calibrated cameras and is encoded by the essential m...
 
Learning on lie groups for invariant detection and tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oncel Tuzel, Fatih Porikli, Peter Meer
Issue Date:June 2008
pp. 1-8
This paper presents a novel learning based tracking model combined with object detection. The existing techniques proceed by linearizing the motion, which makes an implicit Euclidean space assumption. Most of the transformations used in computer vision hav...
 
3D ultrasound tracking of the left ventricle using one-step forward prediction and data fusion of collaborative trackers
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lin Yang, Bogdan Georgescu, Yefeng Zheng, Peter Meer, Dorin Comaniciu
Issue Date:June 2008
pp. 1-8
Tracking the left ventricle (LV) in 3D ultrasound data is a challenging task because of the poor image quality and speed requirements. Many previous algorithms applied standard 2D tracking methods to tackle the 3D problem. However, the performance is limit...
 
Pedestrian Detection via Classification on Riemannian Manifolds
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Oncel Tuzel, Fatih Porikli, Peter Meer
Issue Date:October 2008
pp. 1713-1727
We present a new algorithm to detect pedestrian in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, well known machine learning techniques are not well suited to learn the classifiers. The ...
 
Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lin Yang, Peter Meer, David J. Foran
Issue Date:June 2007
pp. 1-8
Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints mo...
 
Human Detection via Classification on Riemannian Manifolds
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oncel Tuzel, Fatih Porikli, Peter Meer
Issue Date:June 2007
pp. 1-8
We present a new algorithm to detect humans in still images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, well known machine learning techniques are not adequate to learn the classifiers. The spa...
 
Discontinuity Preserving Filtering over Analytic Manifolds
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raghav Subbarao, Peter Meer
Issue Date:June 2007
pp. 1-6
Discontinuity preserving filtering of images is an important low-level vision task. With the development of new imaging techniques like diffusion tensor imaging (DTI), where the data does not lie in a vector space, previous methods like the original mean s...
 
The Hyperbolic Geometry of Illumination-Induced Chromaticity Changes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Reiner Lenz, Pedro Latorre Carmona, Peter Meer
Issue Date:June 2007
pp. 1-6
The non-negativity of color signals implies that they span a conical space with a hyperbolic geometry. We use perspective projections to separate intensity from chromaticity, and for 3-D color descriptors the chromatic properties are represented by points ...
 
Nonlinear Mean Shift for Robust Pose Estimation
Found in: Applications of Computer Vision, IEEE Workshop on
By Raghav Subbarao, Yakup Genc, Peter Meer
Issue Date:February 2007
pp. 6
We propose a new robust estimator for camera pose estimation based on a recently developed nonlinear mean shift algorithm. This allows us to treat pose estimation as a clustering problem in the presence of outliers. We compare our method to RANSAC, which i...
 
Nonlinear Mean Shift for Clustering over Analytic Manifolds
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raghav Subbarao, Peter Meer
Issue Date:June 2006
pp. 1168-1175
The mean shift algorithm is widely applied for nonparametric clustering in Euclidean spaces. Recently, mean shift was generalized for clustering on matrix Lie groups. We further extend the algorithm to a more general class of nonlinear spaces, the set of a...
 
Covariance Tracking using Model Update Based on Lie Algebra
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fatih Porikli, Oncel Tuzel, Peter Meer
Issue Date:June 2006
pp. 728-735
We propose a simple and elegant algorithm to track nonrigid objects using a covariance based object description and a Lie algebra based update mechanism. We represent an object window as the covariance matrix of features, therefore we manage to capture the...
 
Beyond RANSAC: User Independent Robust Regression
Found in: Computer Vision and Pattern Recognition Workshop
By Raghav Subbarao, Peter Meer
Issue Date:June 2006
pp. 101
RANSAC is the most widely used robust regression algorithm in computer vision. However, RANSAC has a few drawbacks which make it difficult to use in a lot of applications. Some of these problems have been addressed through improved sampling algorithms or b...
 
Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups
Found in: Computer Vision, IEEE International Conference on
By Oncel Tuzel, Raghav Subbarao, Peter Meer
Issue Date:October 2005
pp. 18-25
We propose a new method to estimate multiple rigid motions from noisy 3D point correspondences in the presence of outliers. The method does not require prior specification of number of motion groups and estimates all the motion parameters simultaneously. W...
 
A Bayesian Approach to Background Modeling
Found in: Computer Vision and Pattern Recognition Workshop
By Oncel Tuzel, Fatih Porikli, Peter Meer
Issue Date:June 2005
pp. 58
<p>Learning background statistics is an essential task for several visual surveillance applications such as incident detection and traf.c management. In this paper, we propose a new method for modeling background statistics of a dynamic scene. Each p...
 
Heteroscedastic Projection Based M-Estimators
Found in: Computer Vision and Pattern Recognition Workshop
By Raghav Subbarao, Peter Meer
Issue Date:June 2005
pp. 38
<p>Robust regression methods, such as RANSAC, suffer from a sensitivity to the scale parameter used for generating the inlier-outlier dichotomy. Projection based M-estimators (pbM) offer a solution to this by reframing the regression problem in a pro...
 
Model Based Object Recognition by Robust Information Fusion
Found in: Pattern Recognition, International Conference on
By Haifeng Chen, Ilan Shimshoni, Peter Meer
Issue Date:August 2004
pp. 57-60
Given a set of 3D model features and their 2D image, model based object recognition determines the correspondences between those features and hence computes the pose of the object. To achieve good recognition results, a novel approach based on robust infor...
 
Point Matching under Large Image Deformations and Illumination Changes
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bogdan Georgescu, Peter Meer
Issue Date:June 2004
pp. 674-688
<p><b>Abstract</b>—To solve the general point correspondence problem in which the underlying transformation between image patches is represented by a homography, a solution based on extensive use of first order differential techniques is ...
 
Mean Shift Based Clustering in High Dimensions: A Texture Classification Example
Found in: Computer Vision, IEEE International Conference on
By Bogdan Georgescu, Ilan Shimshoni, Peter Meer
Issue Date:October 2003
pp. 456
Feature space analysis is the main module in many computer vision tasks. The most popular technique, k-means clustering, however, has two inherent limitations: the clusters are constrained to be spherically symmetric and their number has to be known a prio...
 
Robust Regression with Projection Based M-estimators
Found in: Computer Vision, IEEE International Conference on
By Haifeng Chen, Peter Meer
Issue Date:October 2003
pp. 878
The robust regression techniques in the RANSAC family are popular today in computer vision, but their performance depends on a user supplied threshold. We eliminate this draw-back of RANSAC by reformulating another robust method, the M-estimator, as a proj...
 
Kernel-Based Object Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Dorin Comaniciu, Visvanathan Ramesh, Peter Meer
Issue Date:May 2003
pp. 564-575
<p><b>Abstract</b>—A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial mask...
 
Synergism in Low Level Vision
Found in: Pattern Recognition, International Conference on
By Christopher M. Christoudias, Bogdan Georgescu, Peter Meer
Issue Date:August 2002
pp. 40150
Guiding image segmentation with edge information is an often employed strategy in low level computer vision. To improve the trade-off between the sensitivity of homogeneous region delineation and the oversegmentation of the image, we have incorporated a re...
 
Robust Regression for Data with Multiple Structures
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Haifeng Chen, Peter Meer, David E. Tyler
Issue Date:December 2001
pp. 1069
In many vision problems (e.g., stereo, motion) multiple structures can occur in the data, in which case several instances of the same model need to be recovered from a single data set. However, once the measurement noise becomes significantly large relativ...
 
A Versatile Method for Trifocal Tensor Estimation
Found in: Computer Vision, IEEE International Conference on
By Bogdan Matei, Bogdan Georgescu, Peter Meer
Issue Date:July 2001
pp. 578
Reliable estimation of the trifocal tensor is crucial for 3D reconstruction from uncalibrated cameras. The estimation process is based on minimizing the geometric distances between the measurements and the corrected data points, the underlying nonlinear op...
 
Performance Analysis in Content-Based Retrieval with Textures
Found in: Pattern Recognition, International Conference on
By Kun Xu, Bogdan Georgescu, Peter Meer, Dorin Comaniciu
Issue Date:September 2000
pp. 4275
The features employed in content-based retrieval are most often simple low-level representations, while a human observer judges similarity between images based on high-level semantic properties. Using textures as an example, we show that a more accurate de...
 
Reduction of Bias in Maximum Likelihood Ellipse Fitting
Found in: Pattern Recognition, International Conference on
By Bogdan Matei, Peter Meer
Issue Date:September 2000
pp. 3802
An improved maximum likelihood estimator for ellipse fitting based on the heteroscedastic errors-in-variables (HEIV) regression algorithm is proposed. The technique significantly reduces the bias of the parameter estimates present in the Direct Least Squar...
 
A General Method for Errors-in-Variables Problems in Computer Vision
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bogdan Matei, Peter Meer
Issue Date:June 2000
pp. 2018
The Errors-in-Variables (EIV) model from statistics is often employed in computer vision though only rarely under this name. In an EIV model, all the measurements are corrupted by noise while the a priori information is captured with a nonlinear constraint...
 
Mean Shift Analysis and Applications
Found in: Computer Vision, IEEE International Conference on
By Dorin Comaniciu, Peter Meer
Issue Date:September 1999
pp. 1197
A non-parametric estimator of density gradient, the mean shift, is employed in the joint, spatial-range (value) domain of gray level and color images for discontinuity preserving filtering and image segmentation. Properties of the mean shift are reviewed a...
 
Automatic Correction of Bias Field in Magnetic Resonance Images
Found in: Image Analysis and Processing, International Conference on
By María Garza-Jinich, Verónica Medina, Oscar Yañez, Peter Meer
Issue Date:September 1999
pp. 752
Two fully automatic restoration-segmentation algorithms are proposed for the processing of biased magnetic resonance images. A first approach is based on an expectation- maximization procedure, where the initial conditions for the class distribution parame...
 
Decision Support System for Multiuser Remote Microscopy in Telepathology
Found in: Computer-Based Medical Systems, IEEE Symposium on
By Dorin Comaniciu, Bogdan Georgescu, Peter Meer, Wenjin Chen, David Foran
Issue Date:June 1999
pp. 150
Recent advances in networking, robotics, and computer technology allow today real-time diagnosis, consultation, and education by using images obtained through remote microscopy. This paper presents a new approach in telepathology, the Image Guided Decision...
 
Optimal Rigid Motion Estimation and Performance Evaluation with Bootstrap
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bogdan Matei, Peter Meer
Issue Date:June 1999
pp. 1339
A new method for 3D rigid motion estimation is derived under the most general assumption that the measurements are corrupted by inhomogeneous and anisotropic, i.e., heteroscedastic noise. This is the case, for example, when the motion of a calibrated stere...
 
Retrieval Performance Improvement through Low Rank Corrections
Found in: Content-Based Access of Image and Video Libraries, IEEE Workshop on
By Dorin Comaniciu, Peter Meer, Kun Xu, David Tyler
Issue Date:June 1999
pp. 50
Whenever a feature extracted from an image has a unimodal distribution, information about its covariance matrix can be exploited for content-based retrieval using as dissimilarity measure the Bhattacharyya distance. To reduce the amount of computations and...
 
Bimodal System for Interactive Indexing and Retrieval of Pathology Images
Found in: Applications of Computer Vision, IEEE Workshop on
By Dorin Comaniciu, Peter Meer, David Foran, Attila Medl
Issue Date:October 1998
pp. 76
The prototype of a system to assist the physicians in differential diagnosis of lymphoproliferative disorders of blood cells from digitized specimens is presented. The user selects the region of interest (ROI) in the image which is then analyzed with a fas...
 
Bimodal System for Interactive Indexing and Retrieval of Pathology Images
Found in: Applications of Computer Vision, IEEE Workshop on
By Dorin Comaniciu, Peter Meer, David Foran, Attila Medl
Issue Date:October 1998
pp. 268
The prototype of a system to assist the physicians in differential diagnosis of lymphoproliferative disorders of blood cells from digitized specimens is presented. The user selects the region of interest (ROI) in the image which is then analyzed with a fas...
 
Shape-Based Image Indexing and Retrieval for Diagnostic Pathology
Found in: Pattern Recognition, International Conference on
By Dorin Comaniciu, David Foran, Peter Meer
Issue Date:August 1998
pp. 902
No summary available.
 
Robust Adaptive Segmentation of Range Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kil-Moo Lee, Peter Meer, Rae-Hong Park
Issue Date:February 1998
pp. 200-205
<p><b>Abstract</b>—We propose a novel image segmentation technique using the robust, adaptive least <it>k</it>th order squares (ALKS) estimator which minimizes the <it>k</it>th order statistics of the squared of re...
 
Correction to
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kyuchin Cho, Peter Meer, Javier Cabrera
Issue Date:January 1998
pp. 94
No summary available.
 
Performance Assessment Through Bootstrap
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kyujin Cho, Peter Meer, Javier Cabrera
Issue Date:November 1997
pp. 1185-1198
<p><b>Abstract</b>—A new performance evaluation paradigm for computer vision systems is proposed. In real situation, the complexity of the input data and/or of the computational procedure can make traditional error propagation methods inf...
 
Unbiased Estimation of Ellipses by Bootstrapping
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Javier Cabrera, Peter Meer
Issue Date:July 1996
pp. 752-756
<p><b>Abstract</b>—A general method for eliminating the bias of nonlinear estimators using bootstrap is presented. Instead of the traditional mean bias we consider the definition of bias based on the median. The method is applied to the p...
 
Frequency Domain Analysis and Synthesis of Image Pyramid Generating Kernels
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Peter Meer,Ernest S. Baugher,Azriel Rosenfeld
Issue Date:April 1987
pp. 512-522
Construction of image pyramids is described as a two-di-mensional decimation process. Frequently employed generating kernels are compared to the optimal kernel that assures minimal information loss after the resolution reduction, i.e., the one correspondin...
 
Semi-Supervised Kernel Mean Shift Clustering
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Saket Anand,Sushil Mittal,Oncel Tuzel,Peter Meer
Issue Date:November 2013
pp. 1
Mean shift clustering is a powerful nonparametric technique that does not require prior knowledge of the number of clusters and does not constrain the shape of the clusters. However, being completely unsupervised, its performance suffers when the original ...
 
Robust Fusion of Uncertain Information
Found in: Computer Vision and Pattern Recognition Workshop
By Haifeng Chen, Peter Meer
Issue Date:June 2003
pp. 64
A technique is presented to combine n data points, each available with point-dependent uncertainty, when only a subset of these points come from N \ll n sources, where N is unknown. We detect the significant modes of the underlying multivariate probability...
 
Registration via Direct Methods: A Statistical Approach
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jacques Bride, Peter Meer
Issue Date:December 2001
pp. 984
The
 
The Variable Bandwidth Mean Shift and Data-Driven Scale Selection
Found in: Computer Vision, IEEE International Conference on
By Dorin Comaniciu, Visvanathan Ramesh, Peter Meer
Issue Date:July 2001
pp. 438
We present two solutions for the scale selection problem in computer vision. The first one is completely non-parametric and is based on the the adaptive estimation of the normalized density gradient. Employing the sample point estimator, we define the Vari...
 
Real-Time Tracking of Non-Rigid Objects Using Mean Shift
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Dorin Comaniciu, Visvanathan Ramesh, Peter Meer
Issue Date:June 2000
pp. 2142
A new method for real-time tracking of non-rigid objects seen from a moving camera is proposed. The central computational module is based on the mean shift iterations and finds the most probable target position in the current frame. The dissimilarity betwe...
 
Parameterized Image Varieties and Estimation with Bilinear Constraints
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yakup Genc, Jean Ponce, Yoram Leedan, Peter Meer
Issue Date:June 1999
pp. 2067
This paper addresses the problem of reliably estimating the coefficients of the parameterized image variety (PIV) associated with the set of weak perspective images of a rigid scene, with applications in image-based rendering. Exploiting the fact that the ...
 
 1