Search For:

Displaying 1-50 out of 120 total
Robust Estimation of Albedo for Illumination-invariant Matching and Shape Recovery
Found in: Computer Vision, IEEE International Conference on
By Soma Biswas, Gaurav Aggarwal, Rama Chellappa
Issue Date:October 2007
pp. 1-8
In this paper, we propose a non-stationary stochastic filtering framework for the task of albedo estimation from a single image. There are several approaches in literature for albedo estimation, but few include the errors in estimates of surface normals an...
 
Fast Bilinear SfM with Side Information
Found in: Computer Vision, IEEE International Conference on
By Mahesh Ramachandran, Ashok Veeraraghavan, Rama Chellappa
Issue Date:October 2007
pp. 1-8
We study the beneficial effect of side information on the Structure from Motion (SfM) estimation problem. The side information that we consider is measurement of a `reference vector' and distance from fixed plane perpendicular to that reference vector. Fir...
 
Gaussian Approximations for Energy-Based Detection and Localization in Sensor Networks
Found in: Statistical Signal Processing, IEEE/SP Workshop on
By Volkan Cevher, Rama Chellappa, James H. McClellan
Issue Date:August 2007
pp. 655-659
Energy-based detection and estimation are crucial in sensor networks for sensor localization, target tracking, etc. In this paper, we present novel Gaussian approximations that are applicable to general energy-based source detection and localization proble...
 
Symmetric Objects are Hardly Ambiguous
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Gaurav Aggarwal, Soma Biswas, Rama Chellappa
Issue Date:June 2007
pp. 1-7
Given any two images taken under different illumination conditions, there always exist a physically realizable object which is consistent with both the images even if the lighting in each scene is constrained to be a known point light source at infinity [1...
 
Epitomic Representation of Human Activities
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Naresh P. Cuntoor, Rama Chellappa
Issue Date:June 2007
pp. 1-8
We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed to be linear and modeled using linear dynamical systems. The tuple consistin...
 
Efficient Indexing For Articulation Invariant Shape Matching And Retrieval
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Soma Biswas, Gaurav Aggarwal, Rama Chellappa
Issue Date:June 2007
pp. 1-8
Most shape matching methods are either fast but too simplistic to give the desired performance or promising as far as performance is concerned but computationally demanding. In this paper, we present a very simple and efficient approach that not only perfo...
 
Markerless Motion Capture using Multiple Cameras
Found in: Computer Vision for Interactive and Intelligent Environment
By Aravind Sundaresan, Rama Chellappa
Issue Date:November 2005
pp. 15-26
Motion capture has important applications in different areas such as biomechanics, computer animation, and human-computer interaction. Current motion capture methods use passive markers that are attached to different body parts of the subject and are there...
 
Camera Networks for Healthcare, Teleimmersion, and Surveillance
Found in: Computer
By Ching-Hui Chen,Julien Favre,Gregorij Kurillo,Thomas P. Andriacchi,Ruzena Bajcsy,Rama Chellappa
Issue Date:May 2014
pp. 26-36
Markerless technology is a game changer for motion-capture applications, such as the monitoring of patients outside the hospital, realistic face-to-face communication across continents, and observation across large spaces.
 
Screen Fingerprints: A Novel Modality for Active Authentication
Found in: IT Professional
By Vishal M. Patel,Tom Yeh,Mohammed E. Fathy,Yangmuzi Zhang,Yan Chen,Rama Chellappa,Larry Davis
Issue Date:July 2013
pp. 38-42
The authors propose a new biometric modality, called a screen fingerprint, for active authentication. A screen fingerprint is acquired by taking a screen recording of the computer being used and extracting discriminative visual features from the recording....
 
Domain adaptation for object recognition: An unsupervised approach
Found in: Computer Vision, IEEE International Conference on
By Raghuraman Gopalan, Ruonan Li,Rama Chellappa
Issue Date:November 2011
pp. 999-1006
Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the conte...
 
Blurring-invariant Riemannian metrics for comparing signals and images
Found in: Computer Vision, IEEE International Conference on
By Zhengwu Zhang,Eric Klassen,Anuj Srivastava,Pavan Turaga,Rama Chellappa
Issue Date:November 2011
pp. 1770-1775
We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of signals/images in which the set of all possible Gaussian blurs of a signal, ...
 
Sparse dictionary-based representation and recognition of action attributes
Found in: Computer Vision, IEEE International Conference on
By Qiang Qiu,Zhuolin Jiang,Rama Chellappa
Issue Date:November 2011
pp. 707-714
We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective fun...
 
Synthesis-based recognition of low resolution faces
Found in: Biometrics, International Joint Conference on
By Sumit Shekhar,Vishal M. Patel,Rama Chellappa
Issue Date:October 2011
pp. 1-6
Recognition of low resolution face images is a challenging problem in many practical face recognition systems. Methods have been proposed in the face recognition literature for the problem when the probe is of low resolution, and a high resolution gallery ...
 
Moving vistas: Exploiting motion for describing scenes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nitesh Shroff, Pavan Turaga, Rama Chellappa
Issue Date:June 2010
pp. 1911-1918
Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representation of scenes. We subsequently propose dynamic attributes which can be augme...
 
Group motion segmentation using a Spatio-Temporal Driving Force Model
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ruonan Li, Rama Chellappa
Issue Date:June 2010
pp. 2038-2045
We consider the ‘group motion segmentation’ problem and provide a solution for it. The group motion segmentation problem aims at analyzing motion trajectories of multiple objects in video and finding among them the ones involved in a ‘group motion pattern’...
 
Fast directional chamfer matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ming-Yu Liu, Oncel Tuzel, Ashok Veeraraghavan, Rama Chellappa
Issue Date:June 2010
pp. 1696-1703
We study the object localization problem in images given a single hand-drawn example or a gallery of shapes as the object model. Although many shape matching algorithms have been proposed for the problem over the decades, chamfer matching remains to be the...
 
Robust RVM regression using sparse outlier model
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kaushik Mitra, Ashok Veeraraghavan, Rama Chellappa
Issue Date:June 2010
pp. 1887-1894
Kernel regression techniques such as Relevance Vector Machine (RVM) regression, Support Vector Regression and Gaussian processes are widely used for solving many computer vision problems such as age, head pose, 3D human pose and lighting estimation. Howeve...
 
Pose-robust albedo estimation from a single image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Soma Biswas, Rama Chellappa
Issue Date:June 2010
pp. 2683-2690
We present a stochastic filtering approach to perform albedo estimation from a single non-frontal face image. Albedo estimation has far reaching applications in various computer vision tasks like illumination-insensitive matching, shape recovery, etc. We e...
 
A Scalable Projective Bundle Adjustment Algorithm using the L infinity Norm
Found in: Computer Vision, Graphics & Image Processing, Indian Conference on
By Kaushik Mitra, Rama Chellappa
Issue Date:December 2008
pp. 79-86
The traditional bundle adjustment algorithm for structure from motion problem has a computational complexity of $O((m+n)^3)$ per iteration and memory requirement of $O(mn(m+n))$, where $m$ is the number of cameras and $n$ is the number of structure points....
 
Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Pavan Turaga, Ashok Veeraraghavan, Rama Chellappa
Issue Date:June 2008
pp. 1-8
Many applications in computer vision and pattern recognition involve drawing inferences on certain manifold-valued parameters. In order to develop accurate inference algorithms on these manifolds we need to a) understand the geometric structure of these ma...
 
Optimal Multi-View Fusion of Object Locations
Found in: Motion and Video Computing, IEEE Workshop on
By Aswin C Sankaranarayanan, Rama Chellappa
Issue Date:January 2008
pp. 1-8
In surveillance applications, it is common to have multiple cameras observing targets exhibiting motion on a ground plane. Tracking and estimation of the location of a target on the plane becomes an important inference problem. In this paper, we study the ...
 
Video Biometrics
Found in: Image Analysis and Processing, International Conference on
By Rama Chellappa, Gaurav Aggarwal
Issue Date:September 2007
pp. 363-370
A strong requirement to come up with secure and user- friendly ways to authenticate and identify people, to safe- guard their rights and interests, has probably been the main guiding force behind biometrics research. Though a vast amount of research has be...
 
From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Pavan K. Turaga, Ashok Veeraraghavan, Rama Chellappa
Issue Date:June 2007
pp. 1-8
Clustering video sequences in order to infer and extract activities from a single video stream is an extremely important problem and has significant potential in video indexing, surveillance, activity discovery and event recognition. Clustering a video seq...
 
Appearance Characterization of Linear Lambertian Objects, Generalized Photometric Stereo, and Illumination-Invariant Face Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shaohua Kevin Zhou, Gaurav Aggarwal, Rama Chellappa, David W. Jacobs
Issue Date:February 2007
pp. 230-245
Traditional photometric stereo algorithms employ a Lambertian reflectance model with a varying albedo field and involve the appearance of only one object. In this paper, we generalize photometric stereo algorithms to handle all appearances of all objects i...
 
Segmentation and Probabilistic Registration of Articulated Body Models
Found in: Pattern Recognition, International Conference on
By Aravind Sundaresan, Rama Chellappa
Issue Date:August 2006
pp. 92-96
There are different approaches to pose estimation and registration of different body parts using voxel data. We propose a general bottom-up approach in order to segment the voxels into different body parts. The voxels are first transformed into a high dime...
 
From Sample Similarity to Ensemble Similarity: Probabilistic Distance Measures in Reproducing Kernel Hilbert Space
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shaohua Kevin Zhou, Rama Chellappa
Issue Date:June 2006
pp. 917-929
This paper addresses the problem of characterizing ensemble similarity from sample similarity in a principled manner. Using reproducing kernel as a characterization of sample similarity, we suggest a probabilistic distance measure in the reproducing kernel...
 
Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Amit Agrawal, Ramesh Raskar, Rama Chellappa
Issue Date:June 2006
pp. 2301-2308
We propose a new technique for edge-suppressing operations on images. We introduce cross projection tensors to achieve affine transformations of gradient fields. We use these tensors, for example, to remove edges in one image based on the edge-information ...
 
Modeling Age Progression in Young Faces
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Narayanan Ramanathan, Rama Chellappa
Issue Date:June 2006
pp. 387-394
We propose a craniofacial growth model that characterizes growth related shape variations observed in human faces during formative years. The model draws inspiration from the ?revised? cardioidal strain transformation model proposed in psychophysical studi...
 
Attribute Grammar-Based Event Recognition and Anomaly Detection
Found in: Computer Vision and Pattern Recognition Workshop
By Seong-Wook Joo, Rama Chellappa
Issue Date:June 2006
pp. 107
We propose to use attribute grammars for recognizing normal events and detecting abnormal events in a video. Attribute grammars can describe constraints on features (attributes) in addition to the syntactic structure of the input. Events are recognized usi...
 
The Function Space of an Activity
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ashok Veeraraghavan, Rama Chellappa, Amit K. Roy-Chowdhury
Issue Date:June 2006
pp. 959-968
An activity consists of an actor performing a series of actions in a pre-defined temporal order. An action is an individual atomic unit of an activity. Different instances of the same activity may consist of varying relative speeds at which the various act...
 
Moving Object Verification from Airborne Video
Found in: Computer Vision Systems, International Conference on
By Zhanfeng Yue, Rama Chellappa, David Guarino
Issue Date:January 2006
pp. 29
This paper presents an end-to-end verification system for moving objects in airborne video. Lacking prior training data, the object information is collected on the fly from a short real-time learning sequence. Using a sample selection module, the system se...
 
Algorithmic and Architectural Design Methodology for Particle Filters in Hardware
Found in: Computer Design, International Conference on
By Aswin C Sankaranarayanan, Rama Chellappa, Ankur Srivastava
Issue Date:October 2005
pp. 275-280
<p>In this paper we present algorithmic and architectural methodology for building Particle Filters in hardware. Particle filtering is a new paradigm for filtering in presence of non-Gaussian non-linear state evolution and observation models. This te...
 
Appearance Modeling Under Geometric Context
Found in: Computer Vision, IEEE International Conference on
By Jian Li, Shaohua Kevin Zhou, Rama Chellappa
Issue Date:October 2005
pp. 1252-1259
We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals over certain geometric sets. We show that image warping, Radon transform, trac...
 
An Algebraic Approach to Surface Reconstruction from Gradient Fields
Found in: Computer Vision, IEEE International Conference on
By Amit Agrawal, Rama Chellappa, Ramesh Raskar
Issue Date:October 2005
pp. 174-181
Several important problems in computer vision such as Shape from Shading (SFS) and Photometric Stereo (PS) require reconstructing a surface from an estimated gradient field, which is usually non-integrable, i.e. have non-zero curl. We propose a purely alge...
 
Face Recognition in the Presence of Multiple Illumination Sources
Found in: Computer Vision, IEEE International Conference on
By Gaurav Aggarwal, Rama Chellappa
Issue Date:October 2005
pp. 1169-1176
Most existing face recognition algorithms work well for controlled images but are quite susceptible to changes in illumination and pose. This has led to the rise of analysis-by-synthesis approaches due to their inherent potential to handle these external f...
 
Introduction of New Editor-in-Chief
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rama Chellappa
Issue Date:January 2005
pp. 1
No summary available.
 
Ego-Motion Estimation and 3D Model Refinement in Scenes with Varying Illumination
Found in: Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
By Amit K Agrawal, Rama Chellappa
Issue Date:January 2005
pp. 140-146
We present an iterative algorithm for robustly estimating the ego-motion and refining and updating a coarse depth map using surface parallax and a generalized dynamic image (GDI) model. Given a coarse depth map acquired by a range-finder or extracted from ...
 
A Factorization Method for Structure from Planar Motion
Found in: Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
By Jian Li, Rama Chellappa
Issue Date:January 2005
pp. 154-159
We propose a factorization method for structure from planar motion using a stationary perspective camera. Compared with [A factorization based algorithm for multi-image projective structure and motion] for general motion, our work has three major differenc...
 
A System Identification Approach for Video-based Face Recognition
Found in: Pattern Recognition, International Conference on
By Gaurav Aggarwal, Amit K. Roy Chowdhury, Rama Chellappa
Issue Date:August 2004
pp. 175-178
The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of videos. We model a moving face as a linear dynamical system whose appearance chang...
 
Multiple-Exemplar Discriminant Analysis for Face Recognition
Found in: Pattern Recognition, International Conference on
By S. Kevin Zhou, Rama Chellappa
Issue Date:August 2004
pp. 191-194
Face recognition is characteristically different from regular pattern recognition and, therefore, requires a different discriminant analysis other than linear discriminant analysis (LDA). LDA is a single-exemplar method in the sense that each class during ...
 
Classification Probability Analysis of Principal Component Null Space Analysis
Found in: Pattern Recognition, International Conference on
By Namrata Vaswani, Rama Chellappa
Issue Date:August 2004
pp. 240-243
In a previous paper [A linear classifier for gaussian class conditional distributions with unequal covariance matrices], we have presented a new linear classification algorithm, Principal Component Null Space Analysis (PC-NSA) which is designed for problem...
 
Probabilistic Identity Characterization for Face Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shaohua Kevin Zhou, Rama Chellappa
Issue Date:July 2004
pp. 805-812
We present a general framework for characterizing the object identity in a single image or a group of images with each image containing a transformed version of the object, with applications to face recognition. In terms of the transformation, the group is...
 
View Independent Human Body Pose Estimation from a Single Perspective Image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vasu Parameswaran, Rama Chellappa
Issue Date:July 2004
pp. 16-22
Recovering the 3D coordinates of various joints of the human body from an image is a critical first step for several model-based human tracking and optical motion capture systems. Unlike previous approaches that have used a restrictive camera model or assu...
 
Role of Shape and Kinematics in Human Movement Analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ashok Veeraraghavan, Amit Roy Chowdhury, Rama Chellappa
Issue Date:July 2004
pp. 730-737
Human gait and activity analysis from video is presently attracting a lot of attention in the computer vision community. In this paper, we analyze the role of two of the most important cues in human motion- shape and kinematics. We present an experimental ...
 
Introduction of New Associate Editors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rama Chellappa, David J. Kriegman
Issue Date:May 2004
pp. 529
No summary available.
 
Introduction of New Associate Editor
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rama Chellappa, David J. Kriegman
Issue Date:April 2004
pp. 433
No summary available.
 
Introduction of New Associate Editors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rama Chellappa, David J. Kriegman
Issue Date:October 2003
pp. 1201
No summary available.
 
Rank Constrained Recognition under Unknown Illuminations
Found in: Analysis and Modeling of Faces and Gestures, IEEE International Workshop on
By Shaohua Zhou, Rama Chellappa
Issue Date:October 2003
pp. 11
Recognition under illumination variations is a challenging problem. The key is to successfully separate the illumination source from the observed appearance. Once separated, what remains is invariant to illuminant and appropriate for recognition. Most curr...
 
Introduction of New Associate Editor
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rama Chellappa, David J. Kriegman
Issue Date:August 2003
pp. 929
No summary available.
 
Activity Recognition Using the Dynamics of the Configuration of Interacting Objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Namrata Vaswani, Amit Roy Chowdhury, Rama Chellappa
Issue Date:June 2003
pp. 633
Monitoring activities using video data is an important surveillance problem. A special scenario is to learn the pattern of normal activities and detect abnormal events from a very low resolution video where the moving objects are small enough to be modeled...
 
 1  2 Next >>