Share Email Print

Proceedings Paper

Fusion and normalization to enhance anomaly detection
Author(s): R. Mayer; G. Atkinson; J. Antoniades; M. Baumback; D. Chester; J. Edwards; A. Goldstein; D. Haas; S. Henderson; L. Liu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This study examines normalizing the imagery and the optimization metrics to enhance anomaly and change detection, respectively. The RX algorithm, the standard anomaly detector for hyperspectral imagery, more successfully extracts bright rather than dark man-made objects when applied to visible hyperspectral imagery. However, normalizing the imagery prior to applying the anomaly detector can help detect some of the problematic dark objects, but can also miss some bright objects. This study jointly fuses images of RX applied to normalized and unnormalized imagery and has a single decision surface. The technique was tested using imagery of commercial vehicles in urban environment gathered by a hyperspectral visible/near IR sensor mounted in an airborne platform. Combining detections first requires converting the detector output to a target probability. The observed anomaly detections were fitted with a linear combination of chi square distributions and these weights were used to help compute the target probability. Receiver Operator Characteristic (ROC) quantitatively assessed the target detection performance. The target detection performance is highly variable depending on the relative number of candidate bright and dark targets and false alarms and controlled in this study by using vegetation and street line masks. The joint Boolean OR and AND operations also generate variable performance depending on the scene. The joint SUM operation provides a reasonable compromise between OR and AND operations and has good target detection performance. In addition, new transforms based on normalizing correlation coefficient and least squares generate new transforms related to canonical correlation analysis (CCA) and a normalized image regression (NIR). Transforms based on CCA and NIR performed better than the standard approaches. Only RX detection of the unnormalized of the difference imagery in change detection provides adequate change detection performance.

Paper Details

Date Published: 27 April 2009
PDF: 12 pages
Proc. SPIE 7334, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV, 73340N (27 April 2009); doi: 10.1117/12.819921
Show Author Affiliations
R. Mayer, BAE Systems (United States)
G. Atkinson, BAE Systems (United States)
J. Antoniades, BAE Systems (United States)
M. Baumback, BAE Systems (United States)
D. Chester, BAE Systems (United States)
J. Edwards, BAE Systems (United States)
A. Goldstein, BAE Systems (United States)
D. Haas, BAE Systems (United States)
S. Henderson, BAE Systems (United States)
L. Liu, BAE Systems (United States)

Published in SPIE Proceedings Vol. 7334:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV
Sylvia S. Shen; Paul E. Lewis, 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?