Search For:

Displaying 1-14 out of 14 total
Parallel Algorithms for Image Enhancement and Segmentation by Region Growing with an Experimental Study
Found in: Parallel Processing Symposium, International
By David A. Bader, Joseph JaJa, David Harwood, and Larry S. Davis
Issue Date:April 1996
pp. 414
This paper presents efficient and portable implementations of a useful image enhancement process, the Symmetric Neighborhood Filter (SNF), and an image segmentation technique which makes use of the SNF and a variant of the conventional connected components...
 
Vehicle Detection Using Partial Least Squares
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Aniruddha Kembhavi, David Harwood, Larry S. Davis
Issue Date:June 2011
pp. 1250-1265
Detecting vehicles in aerial images has a wide range of applications, from urban planning to visual surveillance. We describe a vehicle detector that improves upon previous approaches by incorporating a very large and rich set of image descriptors. A new f...
 
A Fast Background Scene Modeling and Maintenance for Outdoor Surveillance
Found in: Pattern Recognition, International Conference on
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:September 2000
pp. 4179
We described fast background scene modeling and maintenance techniques for real time visual surveillance system for tracking people in an outdoor environment. It operates on monocular grayscale video imagery, or on video imagery from an infrared camera. Th...
 
An Appearance-Based Body Model for Multiple People Tracking
Found in: Pattern Recognition, International Conference on
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:September 2000
pp. 4184
We describe an appearance-based human body model for tracking multiple people when they are interaction with others causing significant occlusion amongst them, or when they reenter the scene. The proposed model allows real time surveillance systems underst...
 
W4: Real-Time Surveillance of People and Their Activities
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:August 2000
pp. 809-830
<p><b>Abstract</b>—<tmath>$W^4$</tmath> is a real time visual surveillance system for detecting and tracking multiple people and monitoring their activities in an outdoor environment. It operates on monocular gray-scale video ...
 
Hydra: Multiple People Detection and Tracking Using Silhouettes
Found in: Image Analysis and Processing, International Conference on
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:September 1999
pp. 280
Hydra is a real-time system for detecting and tracking multiple people when they appear in a group. We describe the computational models employed by Hydra to track multiple people before, during and after occlusion. Hydra combines a silhouette-based shape ...
 
Active Outdoor Surveillance
Found in: Image Analysis and Processing, International Conference on
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:September 1999
pp. 1096
We describe a real time visual surveillance system for detecting and tracking people in an outdoor environment with an active camera which has zoom, tilt and pan control. It operates on monocular grayscale video imagery, or on video imagery from an infrare...
 
Virtual Metamorphosis
Found in: IEEE Multimedia
By Jun Ohya, Jun Kurumisawa, Ryohei Nakatsu, Kazuyuki Ebihara, Shoichiro Iwasawa, David Harwood, Thanarat Horprasert
Issue Date:April 1999
pp. 29-39
The virtual metamorphosis system lets people change their forms into any other form in a virtual scene. To realize these changes, a computer vision system estimates facial expressions and body postures and reproduces them in a computer graphics avatar in r...
 
Ghost: A Human Body Part Labeling System Using Silhouettes
Found in: Pattern Recognition, International Conference on
By Ismail Haritaoglu, David Harwood, Larry S Davis
Issue Date:August 1998
pp. 77
No summary available.
 
Local Estimation of the Uniform Error Threshold
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stanley M. Dunn,David Harwood,Larry S. Davis
Issue Date:June 1984
pp. 742-747
The theory behind selection of the ``uniform error'' threshold which equalizes the probability of misclassification in an image containing two classes is presented. It is shown how this threshold can be estimated using local operations. Some examples and p...
 
Composite Discriminant Factor analysis
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Vlad I. Morariu,Ejaz Ahmed,Venkataraman Santhanam,David Harwood,Larry S. Davis
Issue Date:March 2014
pp. 564-571
We propose a linear dimensionality reduction method, Composite Discriminant Factor (CDF) analysis, which searches for a discriminative but compact feature subspace that can be used as input to classifiers that suffer from problems such as multi-collinearit...
   
Hydra: Multiple People Detection and Tracking Using Silhouettes
Found in: Visual Surveillance, IEEE Workshop on
By Ismail Haritaoglu, David Harwood, Larry S. Davis
Issue Date:June 1999
pp. 6
Hydra is a real-time system for detecting and tracking multiple people when they appear in a group. We describe the computational models employed by Hydra to track multiple people before, during and after occlusion. Hydra combines a silhouette-based shape ...
 
Appearance-Based Automatic Target Recognition in Overhead LADAR Range Imagery
Found in: Pattern Recognition, International Conference on
By Vasanth Philomin, David Harwood, Larry S Davis
Issue Date:August 1998
pp. 1320
No summary available.
 
Top-down, bottom-up multivalued default reasoning for identity maintenance
Found in: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks (VSSN '06)
By David Harwood, Larry S. Davis, Vinay D. Shet
Issue Date:October 2006
pp. 79-86
Persistent tracking systems require the capacity to track individuals by maintaining identity across visibility gaps caused by occlusion events. In traditional computer vision systems, the flow of information is typically bottom-up. The low level image pro...
     
 1