Title :
Clutter invariant ATR
Author :
Bitouk, Dmitri ; Miller, Michael I. ; Younes, Laurent
Author_Institution :
Center for Imaging Sci., Johns Hopkins Univ., Baltimore, MD, USA
fDate :
5/1/2005 12:00:00 AM
Abstract :
One of the central problems in automated target recognition is to accommodate the infinite variety of clutter in real military environments. The principle focus of our paper is on the construction of metric spaces where the metric measures the distance between objects of interest invariant to the infinite variety of clutter. Such metrics are formulated using second-order random field models. Our results indicate that this approach significantly improves detection/classification rates of targets in clutter.
Keywords :
clutter; image classification; military computing; object recognition; automated target recognition; clutter invariance; deformable templates; real military environments; second-order random field models; Context modeling; Extraterrestrial measurements; Layout; Object detection; Photometry; Principal component analysis; Robustness; Statistics; Strontium; Target recognition; Automated Target Recognition (ATR).; Index Terms- Riemannian metrics; deformable templates; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Models, Statistical; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Stochastic Processes; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2005.97
