Search For:

Displaying 1-50 out of 96 total
A Representation of Image Structure and Its Application to Object Selection Using Freehand Sketches
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kar-Han Tan, Narendra Ahuja
Issue Date:December 2001
pp. 677
We present an algorithm for computing a representation of image structure, or image segmentation, and use it for selecting objects in the image with freehand sketches drawn by the user over the image. The sketches are mapped onto image segments whose union...
 
Panoramic Image Acquisition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Arun Krishnan, Narendra Ahuja
Issue Date:June 1996
pp. 379
This paper is concerned with acquiring panoramic focused images using a small field of view video camera. When scene points are distributed over a range of distances from the sensor, obtaining a focused composite image involves focus computations and mecha...
 
Unsupervised Category Modeling, Recognition, and Segmentation in Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Sinisa Todorovic, Narendra Ahuja
Issue Date:December 2008
pp. 2158-2174
Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and...
 
Videoshop: A New Framework for Spatio-Temporal Video Editing in Gradient Domain
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongcheng Wang, Ning Xu, Ramesh Raskar, Narendra Ahuja
Issue Date:June 2005
pp. 1201
No summary available.
   
Low-Rank Sparse Coding for Image Classification
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tianzhu Zhang,Bernard Ghanem,Si Liu,Changsheng Xu,Narendra Ahuja
Issue Date:December 2013
pp. 281-288
In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood...
 
Imaging via three-dimensional compressive sampling (3DCS)
Found in: Computer Vision, IEEE International Conference on
By Xianbiao Shu,Narendra Ahuja
Issue Date:November 2011
pp. 439-446
Compressive sampling (CS) aims at acquiring a signal at a sampling rate that is significantly below the Nyquist rate. Its main idea is that a signal can be decoded from incomplete linear measurements by seeking its sparsity in some domain. Despite the rema...
 
Sparse Coding of Linear Dynamical Systems with an Application to Dynamic Texture Recognition
Found in: Pattern Recognition, International Conference on
By Bernard Ghanem, Narendra Ahuja
Issue Date:August 2010
pp. 987-990
Given a sequence of observable features of a linear dynamical system (LDS), we propose the problem of finding a representation of the LDS which is sparse in terms of a given dictionary of LDSs. Since LDSs do not belong to Euclidean space, traditional spars...
 
Low-Level Image Segmentation Based Scene Classification
Found in: Pattern Recognition, International Conference on
By Emre Akbas, Narendra Ahuja
Issue Date:August 2010
pp. 3623-3626
This paper is aimed at evaluating the semantic information content of multiscale, low-level image segmentation. As a method of doing this, we use selected features of segmentation for semantic classification of real images. To estimate the relative measure...
 
SVM for edge-preserving filtering
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qingxiong Yang, Shengnan Wang, Narendra Ahuja
Issue Date:June 2010
pp. 1775-1782
In this paper, we propose a new method to construct an edge-preserving filter which has very similar response to the bilateral filter. The bilateral filter is a normalized convolution in which the weighting for each pixel is determined by the spatial dista...
 
A constant-space belief propagation algorithm for stereo matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qingxiong Yang, Liang Wang, Narendra Ahuja
Issue Date:June 2010
pp. 1458-1465
In this paper, we consider the problem of stereo matching using loopy belief propagation. Unlike previous methods which focus on the original spatial resolution, we hierarchically reduce the disparity search range. By fixing the number of disparity levels ...
 
Non-uniform sampling: A novel approach
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By G. Rama Murthy, Narendra Ahuja
Issue Date:April 2009
pp. 3229-3232
In this paper a novel approach to non-uniform sampling is proposed. Two engineering methods are discussed.
 
Learning subcategory relevances for category recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sinisa Todorovic, Narendra Ahuja
Issue Date:June 2008
pp. 1-8
A real-world object category can be viewed as a characteristic configuration of its parts, that are themselves simpler, smaller (sub)categories. Recognition of a category can therefore be made easier by detecting its constituent subcategories and combing t...
 
Connected Segmentation Tree
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Narendra Ahuja, Sinisa Todorovic
Issue Date:June 2008
pp. 1-8
This paper proposes a new object representation, called Connected Segmentation Tree (CST), which captures canonical characteristics of the object in terms of the photometric, geometric, and spatial adjacency and containment properties of its constituent im...
 
Extracting a fluid dynamic texture and the background from video
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bernard Ghanem, Narendra Ahuja
Issue Date:June 2008
pp. 1-8
Given the video of a still background occluded by a fluid dynamic texture (FDT), this paper addresses the problem of separating the video sequence into its two constituent layers. One layer corresponds to the video of the unoccluded background, and the oth...
 
Matching images under unstable segmentations
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Varsha Hedau, Himanshu Arora, Narendra Ahuja
Issue Date:June 2008
pp. 1-8
Region based features are getting popular due to their higher descriptive power relative to other features. However, real world images exhibit changes in image segments capturing the same scene part taken at different time, under different lighting conditi...
 
Learning the Taxonomy and Models of Categories Present in Arbitrary Images
Found in: Computer Vision, IEEE International Conference on
By Narendra Ahuja, Sinisa Todorovic
Issue Date:October 2007
pp. 1-8
This paper proposes, and presents a solution to, the problem of simultaneous learning of multiple visual categories present in an arbitrary image set and their intercategory relationships. These relationships, also called their taxonomy, allow categories t...
 
Phase Based Modelling of Dynamic Textures
Found in: Computer Vision, IEEE International Conference on
By Bernard Ghanem, Narendra Ahuja
Issue Date:October 2007
pp. 1-8
This paper presents a model of spatiotemporal variations in a dynamic texture (DT) sequence. Most recent work on DT modelling represents images in a DT sequence as the responses of a linear dynamical system (LDS) to noise. Despite its merits, this model ha...
 
Extracting Texels in 2.1D Natural Textures
Found in: Computer Vision, IEEE International Conference on
By Narendra Ahuja, Sinisa Todorovic
Issue Date:October 2007
pp. 1-8
This paper proposes the problem of unsupervised extraction of texture elements, called texels, which repeatedly occur in the image of a frontally viewed, homogeneous, 2.1D, planar texture, and presents a solution. 2.1D texture here means that the physical ...
 
Modelling Objects using Distribution and Topology of Multiscale Region Pairs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Himanshu Arora, Narendra Ahuja
Issue Date:June 2007
pp. 1-8
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this end, we propose an object model in which the image is represented as a tree, ...
 
Unsupervised Segmentation of Objects using Efficient Learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Himanshu Arora, Nicolas Loeff, David A. Forsyth, Narendra Ahuja
Issue Date:June 2007
pp. 1-7
We describe an unsupervised method to segment objects detected in images using a novel variant of an interest point template, which is very efficient to train and evaluate. Once an object has been detected, our method segments an image using a Conditional ...
 
Active Aperture Control and Sensor Modulation for Flexible Imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunyu Gao, Narendra Ahuja, Hong Hua
Issue Date:June 2007
pp. 1-8
In the paper, we describe an optical system which is capable of providing external access to both the sensor and the lens aperture (i.e., projection center) of a conventional camera. The proposed optical system is attached in front of the camera, and is th...
 
A Vision System for Monitoring Intermodal Freight Trains
Found in: Applications of Computer Vision, IEEE Workshop on
By Avinash Kumar, Narendra Ahuja, John M Hart, U K Visesh, P J Narayanan, C V Jawahar
Issue Date:February 2007
pp. 24
We describe the design and implementation of a vision based Intermodal Train Monitoring System(ITMS) for extracting various features like length of gaps in an intermodal( IM) train which can later be used for higher level inferences. An intermodal train is...
 
Object Tracking Using Globally Coordinated Nonlinear Manifolds
Found in: Pattern Recognition, International Conference on
By Che-Bin Liu, Ruei-Sung Lin, Ming-Hsuan Yang, Narendra Ahuja, Stephen Levinson
Issue Date:August 2006
pp. 844-847
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually nonlinear, embedded in a high dimensional space, and can be approximated by a mi...
 
3D Texture Classification Using the Belief Net of a Segmentation Tree
Found in: Pattern Recognition, International Conference on
By Sinisa Todorovic, Narendra Ahuja
Issue Date:August 2006
pp. 33-36
This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture c...
 
Spatial and Fourier Error Minimization for Motion Estimation and Segmentation
Found in: Pattern Recognition, International Conference on
By Alexia Briassouli, Narendra Ahuja
Issue Date:August 2006
pp. 94-97
We present a new approach to motion estimation by minimizing the squared error in both the spatial and frequency domains and we show that the spatially global nature of FT leads to a motion estimation error that is much lower than that obtained via spatial...
 
An Omnidirectional Stereo Vision System Using a Single Camera
Found in: Pattern Recognition, International Conference on
By Sooyeong Yi, Narendra Ahuja
Issue Date:August 2006
pp. 861-865
We describe a new omnidirectional stereo imaging system that uses a concave lens and a convex mirror to produce a stereo pair of images on the sensor of a conventional camera. The light incident from a scene point is split and directed to the camera in two...
 
Analysis of Ramp Discontinuity Model for Multiscale Image Segmentation
Found in: Pattern Recognition, International Conference on
By Himanshu Arora, Narendra Ahuja
Issue Date:August 2006
pp. 99-103
This paper presents an algorithm for multiscale image segmentation. Towards this, it proposes a new region model, that of a homogenous region surrounded by ramp discontinuities (a scenario usually encountered in real images). This paper presents the analys...
 
A Refractive Camera for Acquiring Stereo and Super-resolution Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunyu Gao, Narendra Ahuja
Issue Date:June 2006
pp. 2316-2323
We propose a novel depth sensing system composed of a single camera, and a transparent plate which is placed in front of the camera and rotates about the optical axis of the camera. The camera takes a sequence of images as the plate rotates, which provide ...
 
SDG Cut: 3D Reconstruction of Non-lambertian Objects Using Graph Cuts on Surface Distance Grid
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tianli Yu, Narendra Ahuja, Wei-Chao Chen
Issue Date:June 2006
pp. 2269-2276
We show that the approaches to 3D reconstruction that use volumetric graph cuts to minimize a cost function over the object surface have two types of biases, the minimal surface bias and the discretization bias. These biases make it difficult to recover su...
 
Extracting Subimages of an Unknown Category from a Set of Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sinisa Todorovic, Narendra Ahuja
Issue Date:June 2006
pp. 927-934
Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological (mutual cont...
 
Joint Spatial and Frequency Domain Motion Analysis
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Narendra Ahuja, Alexia Briassouli
Issue Date:April 2006
pp. 197-204
Traditionally, motion estimation and segmentation have been performed mostly in the spatial domain, i.e., using the luminance information in the video sequence. Frequency domain representation offers an alternative, rich source of motion information, which...
 
Integrated Spatial and Frequency Domain 2D Motion Segmentation and Estimation
Found in: Computer Vision, IEEE International Conference on
By Alexia Briassouli, Narendra Ahuja
Issue Date:October 2005
pp. 244-250
A video containing multiple objects in rotational and translational motion is analyzed through a combination of spatial and frequency domain representations. It is argued that the combined analysis can take advantage of the strengths of both representation...
 
Shape Regularized Active Contour Using Iterative Global Search and Local Optimization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tianli Yu, Jiebo Luo, Narendra Ahuja
Issue Date:June 2005
pp. 655-662
Recently, nonlinear shape models have been shown to improve the robustness and flexibility of segmentation. In this paper, we propose Shape Regularized Active Contour (ShRAC) that incorporates existing nonlinear shape models into the classical active conto...
 
Rank-R Approximation of Tensors: Using Image-as-Matrix Representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongcheng Wang, Narendra Ahuja
Issue Date:June 2005
pp. 346-353
We present a novel multilinear algebra based approach for reduced dimensionality representation of image ensembles. We treat an image as a matrix, instead of a vector as in traditional dimensionality reduction techniques like PCA, and higher-dimensional da...
 
Reconstructing a Dynamic Surface from Video Sequences Using Graph Cuts in 4D Space-Time
Found in: Pattern Recognition, International Conference on
By Tianli Yu, Ning Xu, Narendra Ahuja
Issue Date:August 2004
pp. 245-248
This paper is concerned with the problem of dynamically reconstructing the 3D surface of an object undergoing non-rigid motion. The problem is cast as reconstructing a continuous optimal 3D hyper-surface in 4D space-time from a set of calibrated video sequ...
 
Vision Based Fire Detection
Found in: Pattern Recognition, International Conference on
By Che-Bin Liu, Narendra Ahuja
Issue Date:August 2004
pp. 134-137
Vision based fire detection is potentially a useful technique. With the increase in the number of surveillance cameras being installed, a vision based fire detection capability can be incorporated in existing surveillance systems at relatively low addition...
 
Single Camera Stereo using Planar Parallel Plate
Found in: Pattern Recognition, International Conference on
By Chunyu Gao, Narendra Ahuja
Issue Date:August 2004
pp. 108-111
A system of using a planar parallel plate to achieve single camera stereo has been proposed by Nishimoto and Shirai[A feature-based stereo model using small disparities]. Their work was based on an assumption that the optical axis of the camera was equally...
 
Seamless Video Editing
Found in: Pattern Recognition, International Conference on
By Hongcheng Wang, Ramesh Raskar, Narendra Ahuja
Issue Date:August 2004
pp. 858-861
This paper presents a new framework for seamless video editing in the gradient domain. The spatio-temporal gradient fields of target videos are modified or mixed to generate a new gradient field, which is usually not integrable. We propose a 3D video integ...
 
Fusion of Frequency and Spatial Domain Information for Motion Analysis
Found in: Pattern Recognition, International Conference on
By Alexia Briassouli, Narendra Ahuja
Issue Date:August 2004
pp. 175-178
This paper presents an approach to the analysis of multiple motions in video, which combines frequency and spatial domain information in a new manner. The tasks of interest are finding the number of moving objects, velocity estimation, object tracking, and...
 
Multiview Panoramic Cameras Using Mirror Pyramids
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kar-Han Tan, Hong Hua, Narendra Ahuja
Issue Date:July 2004
pp. 941-946
<p><b>Abstract</b>—A mirror pyramid consists of a set of planar mirror faces arranged around an axis of symmetry and inclined to form a pyramid. By strategically positioning a number of conventional cameras around a mirror pyramid, the vi...
 
A Model for Dynamic Shape and Its Applications
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Che-Bin Liu, Narendra Ahuja
Issue Date:July 2004
pp. 129-134
Variation in object shape is an important visual cue for deformable object recognition and classification. In this paper, we present an approach to model gradual changes in the 2-D shape of an object. We represent in terms of the spatial frequency content ...
 
Recovering Shape and Reflectance Model of Non-Lambertian Objects from Multiple Views
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tianli Yu, Ning Xu, Narendra Ahuja
Issue Date:July 2004
pp. 226-233
This paper proposes an algorithm to simultaneously estimate both the 3D shape and parameters of a surface reflectance model from multiple views of an object made of a single material. The algorithm is based on a multiple view shape from shading method. The...
 
Robust Registration and Tracking Using Kernel Density Correlation
Found in: Computer Vision and Pattern Recognition Workshop
By Maneesh Singh, Himanshu Arora, Narendra Ahuja
Issue Date:July 2004
pp. 174
Challenges to accurate registration come from three factors -presence of background clutter, occlusion of the pattern being registered and changes in feature values across images. To address these concerns, we propose a robust probabilistic estimation appr...
 
Regression based Bandwidth Selection for Segmentation using Parzen Windows
Found in: Computer Vision, IEEE International Conference on
By Maneesh Singh, Narendra Ahuja
Issue Date:October 2003
pp. 2
We consider the problem of segmentation of images that can be modelled as piecewise continuous signals having unknown, non-stationary statistics. We propose a solution to this problem which first uses a regression framework to estimate the image PDF, and t...
 
Object Segmentation Using Graph Cuts Based Active Contours
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ning Xu, Ravi Bansal, Narendra Ahuja
Issue Date:June 2003
pp. 46
In this paper we present a graph cuts based active contours (GCBAC) approach to object segmentation problems. Our method is a combination of active contours and the optimization tool of graph cuts and differs fundamentally from traditional active contours ...
 
Appearance-based Eye Gaze Estimation
Found in: Applications of Computer Vision, IEEE Workshop on
By Kar-Han Tan, David J Kriegman, Narendra Ahuja
Issue Date:December 2002
pp. 191
We present a method for estimating eye gaze direction, which represents a departure from conventional eye gaze estimation methods, the majority of which are based on tracking specific optical phenomena like corneal reflection and the Purkinje images. We em...
 
Extraction of 2D Motion Trajectories and Its Application to Hand Gesture Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ming-Hsuan Yang, Narendra Ahuja, Mark Tabb
Issue Date:August 2002
pp. 1061-1074
<p>We present an algorithm for extracting and classifying two-dimensional motion in an image sequence based on motion trajectories. First, a multiscale segmentation is performed to generate homogeneous regions in each frame. Regions between consecuti...
 
A Testbed for Precise Registration, Natural Occlusion and Interaction in an Augmented Environment Using a Head-Mounted Projective Display (HMPD)
Found in: Virtual Reality Conference, IEEE
By Hong Hua, Chunyu Gao, Leonard D. Brown, Narendra Ahuja, Jannick P. Rolland
Issue Date:March 2002
pp. 81
A head-mounted projective display (HMPD) consists of a pair of miniature projection lenses, beamsplitters, and displays mounted on the helmet and retro-reflective sheeting materials placed strategically in the environment. It has been recently proposed as ...
 
Detecting Faces in Images: A Survey
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ming-Hsuan Yang, David J. Kriegman, Narendra Ahuja
Issue Date:January 2002
pp. 34-58
<p>Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported meth...
 
A High-Resolution Panoramic Camera
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hong Hua, Narendra Ahuja
Issue Date:December 2001
pp. 960
Widefield of view (FOV) and high resolution are two desirable properties in many vision-based applications such as tele-conferencing, surveillance, and robot navigation. In some applications such as 30 reconstruction and rendering, it is also desired that ...
 
 1  2 Next >>