Accession Number : ADA557283


Title :   Automatic Target Recognition for Hyperspectral Imagery


Descriptive Note : Master's thesis


Corporate Author : AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT


Personal Author(s) : Friesen, Kelly D


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a557283.pdf


Report Date : Mar 2012


Pagination or Media Count : 102


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.


Descriptors :   *ANOMALIES , *AUTOMATIC , *CLASSIFICATION , *HYPERSPECTRAL IMAGERY , *TARGET DETECTION , *TARGET RECOGNITION , BASE LINES , DECISION MAKING , DIGITAL IMAGES , IDENTIFICATION SYSTEMS , MATCHED FILTERS , MATCHING , PASSIVE SYSTEMS , PATTERN RECOGNITION , RADIATIVE TRANSFER , SIGNATURES , THESES


Subject Categories : Target Direction, Range and Position Finding
      Atomic and Molecular Physics and Spectroscopy


Distribution Statement : APPROVED FOR PUBLIC RELEASE