Share Email Print

Proceedings Paper

A parametric study of unsupervised anomaly detection performance in maritime imagery using manifold learning techniques
Author(s): C. C. Olson; T. Doster
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We investigate the parameters that govern an unsupervised anomaly detection framework that uses nonlinear techniques to learn a better model of the non-anomalous data. A manifold or kernel-based model is learned from a small, uniformly sampled subset in order to reduce computational burden and under the assumption that anomalous data will have little effect on the learned model because their rarity reduces the likelihood of their inclusion in the subset. The remaining data are then projected into the learned space and their projection errors used as detection statistics. Here, kernel principal component analysis is considered for learning the background model. We consider spectral data from an 8-band multispectral sensor as well as panchromatic infrared images treated by building a data set composed of overlapping image patches. We consider detection performance as a function of patch neighborhood size as well as embedding parameters such as kernel bandwidth and dimension. ROC curves are generated over a range of parameters and compared to RX performance.

Paper Details

Date Published: 25 May 2016
PDF: 9 pages
Proc. SPIE 9840, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXII, 984016 (25 May 2016); doi: 10.1117/12.2227226
Show Author Affiliations
C. C. Olson, U.S. Naval Research Lab. (United States)
T. Doster, U.S. Naval Research Lab. (United States)

Published in SPIE Proceedings Vol. 9840:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXII
Miguel Velez-Reyes; David W. Messinger, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?