Share Email Print
cover

Optical Engineering

Adaptive anomaly detection using subspace separation for hyperspectral imagery
Author(s): Heesung Kwon; Sandor Z. Der; Nasser M. Nasrabadi
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We propose adaptive anomaly detectors that find materials whose spectral characteristics are substantially different from those of the neighboring materials. Target spectral vectors are assumed to have different statistical characteristics from the background vectors. We use a dual rectangular window that separates the local area into two regions—the inner window region (IWR) and outer window region (OWR). The statistical spectral differences between the IWR and OWR are exploited by generating subspace projection vectors onto which the IWR and OWR vectors are projected. Anomalies are detected if the projection separation between the IWR and OWR vectors is greater than a predefined threshold. Four different methods are used to produce the subspace projection vectors. The four proposed anomaly detectors are applied to Hyperspectral Digital Imagery Collection Experiment (HYDICE) images and the detection performance for each method is evaluated.

Paper Details

Date Published: 1 November 2003
PDF: 10 pages
Opt. Eng. 42(11) doi: 10.1117/1.1614265
Published in: Optical Engineering Volume 42, Issue 11
Show Author Affiliations
Heesung Kwon, Army Research Lab. (United States)
Sandor Z. Der, Army Research Lab. (United States)
Nasser M. Nasrabadi, Army Research Lab. (United States)


© SPIE. Terms of Use
Back to Top