Share Email Print

Proceedings Paper

Anomaly detection in hyperspectral imagery using stable distribution
Author(s): S. Mercan; Mohammad S. Alam
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In hyperspectral imaging applications, the background generally exhibits a clearly non-Gaussian impulsive behavior, where valuable information stays in the tail. In this paper, we propose a new technique, where the background is modeled using the stable distribution for robust detection of outliers. The outliers of the distribution can be considered as potential anomalies or regions of interests (ROIs). We effectively utilize the stable model for detecting targets in impulsive hyperspectral data. To decrease the false alarm rate, it is necessary to compare the ROI with the known reference using a suitable technique, such as the Euclidian distance. Modeling data with stable distribution compensates a drawback of the Gaussian model, which is not well suited for describing signals with impulsive behavior. In addition, thresholding is considered to avoid misclassification of targets. Test results using real life hyperspectral image datasets are presented to verify the effectiveness of the proposed technique.

Paper Details

Date Published: 19 May 2011
PDF: 9 pages
Proc. SPIE 8049, Automatic Target Recognition XXI, 80490V (19 May 2011); doi: 10.1117/12.884913
Show Author Affiliations
S. Mercan, Univ. of Nevada, Reno (United States)
Mohammad S. Alam, Univ. of South Alabama (United States)

Published in SPIE Proceedings Vol. 8049:
Automatic Target Recognition XXI
Firooz A. Sadjadi; Abhijit Mahalanobis, Editor(s)

© SPIE. Terms of Use
Back to Top