DMCA
The Advanced Distributed Region of Interest Tool
| Citations: | 3 - 1 self |
BibTeX
@MISC{Marchette_theadvanced,
author = {D. J. Marchette and J.L. Solka and R. Guidry and J. Green},
title = {The Advanced Distributed Region of Interest Tool},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Keywords: low-level vision, statistical pattern recognition, genetic algorithms, fractal dimension, mixture models This paper details recent work on the use of low-level features for the identification of regions of interest in images. Using low-level features, the system classifies regions in the image via probability densities estimates for each class. These densities are estimated semi-parametrically, giving the system great flexibility in the functional form of the densities. This paper details the environment designed to allow easy implementation of pattern recognition algorithms. 1. INTRODUCTION There is an increasing need within the department of defense (DOD) community for constant assessment and monitoring of battle-field conditions world-wide. This monitoring is usually performed using human resources for the analysis of imagery obtained from a variety of assets. These assets include such sources as national imagery, aerial reconnaissance imagery, and unmanned aerial vehic...
Keyphrases
advanced distributed region interest tool low-level feature paper detail system great flexibility unmanned aerial vehic mixture model genetic algorithm constant assessment national imagery battle-field condition human resource statistical pattern recognition fractal dimension low-level vision functional form pattern recognition algorithm probability density easy implementation paper detail recent work aerial reconnaissance imagery
