Search For:

Displaying 1-50 out of 50 total
Object association across PTZ cameras using logistic MIL
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By K. Sankaranarayanan,J. W. Davis
Issue Date:June 2011
pp. 3433-3440
We propose a novel approach to associate objects across multiple PTZ cameras that can be used to perform camera handoff in wide-area surveillance scenarios. While previous approaches relied on geometric, appearance, or correlation-based information for est...
 
A Software Approach to Avoiding Spatial Cache Collisions in Parallel Processor Systems
Found in: IEEE Transactions on Parallel and Distributed Systems
By David C. Wong, Edward W. Davis, Jeffrey O. Young
Issue Date:June 1998
pp. 601-608
<p><b>Abstract</b>—In parallel processor systems, the performance of individual processors is a key factor in overall performance. Processor performance is strongly affected by the behavior of cache memory in that high hit rates are essen...
 
Exploiting frame coherence with the temporal depth buffer in a distributed computing environment
Found in: Parallel and Large-Data Visualization and Graphics, IEEE Symposium on
By Edward W. Davis, Timothy A. Davis
Issue Date:October 1999
pp. 29-38
In this paper we introduce the notion of a parallel temporal depth buffer (or t-buffer) to speed up the rendering process for ray-traced animations. The t-buffer is a conceptually simple data structure which stores knowledge about coherent pixel values acr...
 
Measurements of parallelism in ordinary FORTRAN programs
Found in: Computer
By David J Kuck,Paul P. Budnik,Shyh-Ching Chen,Duncan H. Lawrie,Ross A. Towle,Richard E. Strebendt,Edward W. Davis,Joseph Han,Paul W. Kraska,Yoichi Muraoka
Issue Date:January 1974
pp. 37-46
In the folklore of computer architecture there has been much speculation about the effectiveness of various machines in performing various computations. While it is easy to design a machine (or part of a machine) and study its effectiveness on this algorit...
 
Extracting Pathlets FromWeak Tracking Data
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Kevin Streib, James W. Davis
Issue Date:September 2010
pp. 353-360
We present a novel framework for extracting “pathlets”from tracking data. A pathlet is defined as a motion regionthat contains tracks having the same origin and destinationin the scene and that are temporally correlated. The proposedmethod requires only we...
 
Steepest Descent For Efficient Covariance Tracking
Found in: Motion and Video Computing, IEEE Workshop on
By Ambrish Tyagi, James W. Davis, Gerasimos Potamianos
Issue Date:January 2008
pp. 1-6
Recent research has advocated the use of a covariance matrix of image features for tracking objects instead of the conventional histogram object representation models used in popular algorithms. In this paper we extend the covariance tracker and propose ef...
 
Fusion of Multiple Camera Views for Kernel-Based 3D Tracking
Found in: Motion and Video Computing, IEEE Workshop on
By Ambrish Tyagi, Gerasimos Potamianos, James W. Davis, Stephen M. Chu
Issue Date:February 2007
pp. 1
We present a computer vision system to robustly track an object in 3D by combining evidence from multiple calibrated cameras. Its novelty lies in the proposed unified approach to 3D kernel based tracking, that amounts to fusing the appearance features from...
 
A Context-Based Tracker Switching Framework
Found in: Motion and Video Computing, IEEE Workshop on
By Ambrish Tyagi, James W. Davis
Issue Date:January 2008
pp. 1-8
We present a robust framework for tracking people in crowded outdoor environments monitored by multiple cameras with a goal of real-time performance. Since no single algorithm is perfect for the task of object tracking in all cases, we instead take an alte...
 
Kernel-Based 3D Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ambrish Tyagi, Mark Keck, James W. Davis, Gerasimos Potamianos
Issue Date:June 2007
pp. 1-8
We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstrapped by constructing 3D point clouds. These points clouds are then clustered ...
 
Using Ripley's K-function to improve graph-based clustering techniques
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By K. Streib,J. W. Davis
Issue Date:June 2011
pp. 2305-2312
The success of any graph-based clustering algorithm depends heavily on the quality of the similarity matrix being clustered, which is itself highly dependent on point-wise scaling parameters. We propose a novel technique for finding point-wise scaling para...
 
A recursive filter for linear systems on Riemannian manifolds
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ambrish Tyagi, James W. Davis
Issue Date:June 2008
pp. 1-8
We present an online, recursive filtering technique to model linear dynamical systems that operate on the state space of symmetric positive definite matrices (tensors) that lie on a Riemannian manifold. The proposed approach describes a predict-and-update ...
 
Integrating Appearance and Motion Cues for Simultaneous Detection and Segmentation of Pedestrians
Found in: Computer Vision, IEEE International Conference on
By Vinay Sharma, James W. Davis
Issue Date:October 2007
pp. 1-8
We present a unified method for simultaneously acquiring both the location and the silhouette shape of people in outdoor scenes. The proposed algorithm integrates top-down and bottom-up processes in a balanced manner, employing both appearance and motion c...
 
Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vinay Sharma, James W. Davis
Issue Date:June 2007
pp. 1-8
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and exploits top-down and bottom-up processing within a single framework for both obje...
 
Extraction of Person Silhouettes from Surveillance Imagery using MRFs
Found in: Applications of Computer Vision, IEEE Workshop on
By Vinay Sharma, James W. Davis
Issue Date:February 2007
pp. 33
We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object shape using a simple training phase requiring no manual segmentation. Based on ...
 
A Three-Mode Expressive Feature Model of Action Effort
Found in: Motion and Video Computing, IEEE Workshop on
By James W. Davis, Hui Gao, Vignesh S. Kannappan
Issue Date:December 2002
pp. 139
We present an expressive feature model for recognizing the performance effort of human actions. A set of low and high effort examples for an action are initially factored into its three-mode principal components, followed by a learning phase to compute the...
 
The Recognition of Human Movement Using Temporal Templates
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Aaron F. Bobick, James W. Davis
Issue Date:March 2001
pp. 257-267
<p><b>Abstract</b>—A new view-based approach to the representation and recognition of human movement is presented. The basis of the representation is a <it>temporal template</it>—a static vector-image where the vector value at...
 
Improving Cross-Language Text Retrieval with Human Interactions
Found in: Hawaii International Conference on System Sciences
By William C. Ogden, Mark W. Davis
Issue Date:January 2000
pp. 3044
Can we expect people to be able to get information from texts in languages they cannot read? In this paper we review two relevant lines of research bearing on this question and will show how our results are being used in the design of a new Web interface f...
   
Application of the massively parallel processor to database management systems
Found in: Managing Requirements Knowledge, International Workshop on
By Edward W. Davis
Issue Date:May 1983
pp. 299
No summary available.
   
Exploiting frame coherence with the temporal depth buffer in a distributed computing environment
Found in: Proceedings of the 1999 IEEE symposium on Parallel visualization and graphics (PVGS '99)
By Edward W. Davis, Timothy A. Davis
Issue Date:October 1999
pp. 29-38
In this paper we introduce the notion of a parallel temporal depth buffer (or t-buffer) to speed up the rendering process for ray-traced animations. The t-buffer is a conceptually simple data structure which stores knowledge about coherent pixel values acr...
     
Learning Directed Intention-driven Activities using Co-Clustering
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Karthik Sankaranarayanan, James W. Davis
Issue Date:September 2010
pp. 400-407
We present a novel approach for discovering directedintention-driven pedestrian activities across large urban areas.The proposed approach is based on a mutual informationco-clustering technique that simultaneously clusterstrajectory start locations in the ...
 
A Fast Linear Registration Framework for Multi-camera GIS Coordination
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Karthik Sankaranarayanan, James W. Davis
Issue Date:September 2008
pp. 245-251
We propose a novel registration framework to map the field-of-coverage of pan-tilt cameras to a GIS (Geographic Information System) planar coordinate system. The camera's field-of-coverage is obtained by building a spherical panorama using an efficient act...
 
3D occlusion recovery using few cameras
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mark Keck, James W. Davis
Issue Date:June 2008
pp. 1-8
We present a practical framework for detecting and modeling 3D static occlusions for wide-baseline, multi-camera scenarios where the number of cameras is small. The framework consists of an iterative learning procedure where at each frame the occlusion mod...
 
An Efficient Active Camera Model for Video Surveillance
Found in: Applications of Computer Vision, IEEE Workshop on
By Karthik Sankaranarayanan, James W. Davis
Issue Date:January 2008
pp. 1-7
We propose an efficient active camera model to map image coordinates to the camera's pan-tilt orientations in constant time. The model is based on the elliptical locus of the projections of a fixed point on the original image plane of a moving camera. The ...
 
Feature-level Fusion for Object Segmentation using Mutual Information
Found in: Computer Vision and Pattern Recognition Workshop
By Vinay Sharma, James W. Davis
Issue Date:June 2006
pp. 139
We present a new feature-level image fusion technique for object segmentation based on mutual information. Using object regions roughly detected from one sensor as input, the proposed technique extracts relevant information from another to complete the seg...
 
Fusion-Based Background-Subtraction using Contour Saliency
Found in: Computer Vision and Pattern Recognition Workshop
By James W. Davis, Vinay Sharma
Issue Date:June 2005
pp. 11
<p>We present a new contour-based background-subtraction technique using thermal and visible imagery for persistent object detection in urban settings. Statistical backgroundsubtraction in the thermal domain is used to identify the initial regions-of...
 
A Two-Stage Template Approach to Person Detection in Thermal Imagery
Found in: Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
By James W. Davis, Mark A. Keck
Issue Date:January 2005
pp. 364-369
We present a two-stage template-based method to detect people in widely varying thermal imagery. The approach initially performs a fast screening procedure using a generalized template to locate potential person locations. Next an AdaBoosted ensemble class...
 
Robust Detection of People in Thermal Imagery
Found in: Pattern Recognition, International Conference on
By James W. Davis, Vinay Sharma
Issue Date:August 2004
pp. 713-716
We present a new contour analysis technique to detect people in thermal imagery. Background-subtraction is first used to identify local regions-of-interest. Gradient information within each region is then combined into a contour saliency map. To extract co...
 
Sequential Reliable-Inference for Rapid Detection of Human Actions
Found in: Computer Vision and Pattern Recognition Workshop
By James W. Davis
Issue Date:July 2004
pp. 111
We present a probabilistic reliable-inference framework to address the issue of rapid-and-reliable detection of human actions. The approach determines the shortest video exposure needed for low-latency recognition by sequentially evaluating a series of pos...
 
A Reliable-Inference Framework for Recognition of Human Actions
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By James W. Davis, Ambrish Tyagi
Issue Date:July 2003
pp. 169
We present an action recognition method based on the concept of reliable inference. Our approach is formulated in a probabilistic framework using posterior class ratios to verify the saliency of an input before committing to any action classi.cation. The f...
 
Analysis and Recognition of Walking Movements
Found in: Pattern Recognition, International Conference on
By James W. Davis, Stephanie R. Taylor
Issue Date:August 2002
pp. 10315
We present an approach for recognizing human walking movements using low-level motion regularities and constraints. Biomechanical features for classification are automatically extracted from video sequences of walkers. A multiplicative classification rule ...
 
The Representation and Recognition of Human Movement Using Temporal Templates
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By James W. Davis, Aaron F. Bobick
Issue Date:June 1997
pp. 928
A new view-based approach to the representation and recognition of action is presented. The basis of the representation is a temporal template -- a static vector-image where the vector value at each point is a function of the motion properties at the corre...
 
Performance Evaluation of SIMD Processor Architectures Using Pairwise Multiplier Recoding
Found in: Parallel Processing, International Conference on
By Todd C. Marek, Edward W. Davis
Issue Date:August 1993
pp. 202-205
Research in the area of massively parallel processing with a focus on processor architecture is presented. Multiplication using conventional techniques and a modified multiplier recoding scheme for 2's complement fixed-point multiplication is used to evalu...
 
STARAN parallel processor system software
Found in: Managing Requirements Knowledge, International Workshop on
By E. W. Davis
Issue Date:May 1974
pp. 17
No summary available.
   
Robust Background-Subtraction for Person Detection in Thermal Imagery
Found in: Computer Vision and Pattern Recognition Workshop
By James W. Davis, Vinay Sharma
Issue Date:July 2004
pp. 128
We present a new contour-based background-subtraction technique to detect people in widely varying thermal imagery. Statistical background-subtraction is first used to identify local regions-of-interest. Within each region, gradient information in the fore...
 
Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework
Found in: Computer Vision, IEEE International Conference on
By James W. Davis, Hui Gao
Issue Date:October 2003
pp. 1463
We present a computational framework capable of labeling the effort of an action corresponding to the perceived level of exertion by the performer (low - high). The approach initially factorizes examples (at different efforts) of an action into its three-m...
 
Perceptual user interfaces: the KidsRoom
Found in: Communications of the ACM
By Aaron F. Bobick, Andrew Wilson, Arjan Schutte, Claudio S. Pinhanez, Freedom Baird, James W. Davis, Lee W. Campbell, Stephen S. Intille, Yuri A. Ivanov
Issue Date:January 1988
pp. 60-61
The online Risks Forum has long been a hotbed for discussions of the relative merits of openness relating to the dissemination of knowledge about security vulnerabilities. The debate has now been rekindled, and is summarized here.
     
Normal deviate [S14]
Found in: Communications of the ACM
By A. W. Davis, G. W. Hill
Issue Date:January 1973
pp. 51-52
The Elliott (I.C.L.) Algol 60 compiler contains a restriction on the sequence of declarations such that no identifier may be used before it is declared. This means that direct mutual recursion between procedures declared in the same blockhead is not possib...
     
On the linearity of sequential machines
Found in: Foundations of Computer Science, Annual IEEE Symposium on
By W. A. Davis, J. A. Brzozowski
Issue Date:November 1964
pp. 197-208
This paper presents a method for determining, from the flow table of a sequential machine, whether the machine is linearly realizable using the minimum number of unit delay elements. The method is an extension of a previously presented method for autonomou...
 
Tracking mean shift clustered point clouds for 3D surveillance
Found in: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks (VSSN '06)
By Ambrish Tyagi, James W. Davis, Mark A. Keck
Issue Date:October 2006
pp. 187-194
We present in this paper a method of tracking multiple objects (people) in 3D for application in video surveillance. The tracking method is designed to work on images with objects at low resolution and has two major contributions. First we propose a way to...
     
Multiview fusion for canonical view generation based on homography constraints
Found in: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks (VSSN '06)
By Ambrish Tyagi, James W. Davis, Mark Keck
Issue Date:October 2006
pp. 61-70
Activity and gait recognition are among the various applications that necessitate view-specific input. In a real surveillance scenario it is impractical to assume that the desired canonical view will always be available. We present a framework to generate ...
     
Expressive features for movement exaggeration
Found in: ACM SIGGRAPH 2002 conference abstracts and applications (SIGGRAPH '02)
By James W. Davis, Vignesh S. Kannappan
Issue Date:July 2002
pp. 182-182
Given a single motion-capture sequence of a person performing a dynamic activity at a particular intensity (or effort), our goal is to automatically warp that movement into a natural-looking exaggerated version of that action. Consider warping a movement o...
     
QUILT: implementing a large-scale cross-language text retrieval system
Found in: Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR '97)
By Mark W. Davis, William C. Ogden
Issue Date:July 1997
pp. 340
The TIPSTER collection is unusual because of both its size and detail. In particular, it describes a set of information needs, as opposed to traditional queries. These detailed representations of information need are an opportunity for research on differen...
     
Using focusing search algorithms and a strong heuristic to solve the findpath problem in robotics
Found in: Proceedings of the 1990 ACM annual conference on Cooperation (CSC '90)
By Henry W. Davis, Jim Wang, Verlynda S. Dobbs
Issue Date:February 1990
pp. 63-69
Two problems are associated with the seeking of good solutions to the find path problem (Find Path) in robotics. First, the use of artificial intelligence searching techniques is limited to the A* algorithm. Secondly, simple and poor heuristics are employe...
     
Altering heuristics by means of statistical transformations
Found in: Proceedings of the second international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2 (IEA/AIE '89)
By A. Bramanti-Gregor, H. W. Davis, X. Chen
Issue Date:June 1989
pp. 716-721
Design has been one of the most difficult problems that Artificial Intelligence has faced until now. Design knowledge is almost impossible to gather and put into rules or other structured reasoning tool, and studies of human expert designers have shown tha...
     
An application of heuristic search techniques to the problem of flight path generation in a military hostile environment
Found in: Proceedings of the first international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 1 (IEA/AIE '88)
By Carl Lizza, Henry W. Davis, Verlynda S. Dobbs
Issue Date:June 1988
pp. 273-280
This paper is a study of the effectiveness of heuristic search algorithms in generating flight paths. Due to the need to generate and revise paths dynamically we are interested in execution speed as well as solution quality (conflict cost plus path length)...
     
Cost-error relationships in A* tree-searching
Found in: Journal of the ACM (JACM)
By Henry W. Davis
Issue Date:January 1988
pp. 195-199
Pearl has shown that, in admissible A* tree-searching, the expected number of nodes expanded is bounded above and below by exponential functions of heuristic error. An additional assumption required for the validity of Pearl's argument is given. The assump...
     
A technique for comparing search algorithm run-times
Found in: Proceedings of the 1986 ACM fourteenth annual conference on Computer science (CSC '86)
By Dennis J. Golden, Henry W. Davis, Randy B. Pollack
Issue Date:February 1986
pp. 301-308
A description of an advanced graphics interface design that provides the applications developer with a very high level graphics environment is presented. The object oriented design is shown to be appropriate to achieving device and implementation independe...
     
A computerized health and nutrition assessment for school children
Found in: Proceedings of the 16th annual Southeast regional conference (ACM-SE 16)
By Barry Bateman, Gerald N. Pitts, Martha W. Davis
Issue Date:April 1978
pp. 201-203
A comprehensive school health and nutrition program requires an interdisciplinary (team) approach to the delivery of services. To achieve this, a management system requiring participation of project components (mental, physical, educational, and nutritiona...
     
The control of congestion in packet switching networks
Found in: Proceedings of the second symposium on Problems in the optimizations of data communications systems
By D. W. Davies
Issue Date:January 1971
pp. 46-49
Any communication network has a limit to the traffic it can carry. If there is more than a certain traffic demand, some of the traffic must be rejected. Both the nature of the limitation and the reaction of the network to excess demand depend on the design...
     
A digital communication network for computers giving rapid response at remote terminals
Found in: Proceedings of the ACM symposium on Operating System Principles (SOSP '67)
By D. W. Davies, K. A. Bartlett, P. T. Wilkinson, R. A. Scantlebury
Issue Date:January 1967
pp. 2.1-2.17
Those computer applications which involve rapid response to events at distant points create special problems in digital communication. Such applications are increasing in number, and could increase more rapidly if better solutions existed to the communicat...
     
 1