Automatic Target Recognition for Hyperspectral Imagery
Abstract
Automatic target detection and recognition in hyperspectral imagery offer passive means to detect and identify anomalies based on their material composition. In many combat identification methods that use pattern recognition a minimum level of confidence is expected, with costs associated with labeling anomalies as targets, nontargets, or out-of-library. This research approaches the problem by developing a baseline, autonomous four-step automatic target recognition (ATR) process: (1) anomaly detection, (2) spectral matching, (3) out-of-library decision, and (4) non-declaration decision. Atmospheric compensation techniques are employed in the initial steps to compare truth library signatures with sensor processed signatures. ATR performance is assessed and contrasted with two modified ATR processes to study the effects of steps three and four. The research also explores the impact of two different anomaly detection methods on the ATR process presented here.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2012
- Accession Number
- ADA557283
Entities
People
- Kelly D. Friesen
Organizations
- Air Force Institute of Technology