Using Multiple Robust Parameter Design Techniques to Improve Hyperspectral Anomaly Detection Algorithm Performance

Author

Matthew T. Davis

Date of Award

3-9-2009

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Operational Sciences

First Advisor

Kenneth W. Bauer, PhD

Abstract

Detecting and identifying objects of interest is the goal of all remote sensing. New advances, specifically in hyperspectral imaging technology have provided the analyst with immense amounts of data requiring evaluation. Several filtering techniques or anomaly detection algorithms have been proposed. However, most new algorithms are insufficiently verified to be robust to the broad range of hyperspectral data being made available. One such algorithm, AutoGAD, is tested here via two separate robust parameter design techniques to determine optimal parameters for consistent performance on a range of data with large attribute variances. Additionally, the results of the two techniques are compared for overall effectiveness. The results of the test as well as optimal parameters for AutoGAD are presented and future research efforts proposed.

AFIT Designator

AFIT-GOR-ENS-09-05

DTIC Accession Number

ADA500322

Recommended Citation

Davis, Matthew T., "Using Multiple Robust Parameter Design Techniques to Improve Hyperspectral Anomaly Detection Algorithm Performance" (2009). Theses and Dissertations. 2506.
https://scholar.afit.edu/etd/2506