Uncorrelated versus independent elliptically-contoured distributions for anomalous change detection in hyperspectral imagery

Conference · Tue Jan 01 04:00:00 EST 2008

OSTI ID:956664

Theiler, James P ^[1]; Scovel, James C ^[1]

---

1. Los Alamos National Laboratory

The detection of actual changes in a pair of images is confounded by the inadvertent but pervasive differences that inevitably arise whenever two pictures are taken of the same scene, but at different times and under different conditions. These differences include effects due to illumination, calibration, misregistration, etc. If the actual changes are assumed to be rare, then one can 'learn' what the pervasive differences are, and can identify the deviations from this pattern as the anomalous changes. A recently proposed framework for anomalous change detection recasts the problem as one of binary classification between pixel pairs in the data and pixel pairs that are independently chosen from the two images. When an elliptically-contoured (EC) distribution is assumed for the data, then analytical expressions can be derived for the measure of anomalousness of change. However, these expression are only available for a limited class of EC distributions. By replacing independent pixel pairs with uncorrelated pixel pairs, an approximate solution can be found for a much broader class of EC distributions. The performance of this approximation is investigated analytically and empirically, and includes experiments comparing the detection of real changes in real data.

• Research Organization: Los Alamos National Laboratory (LANL)
• Sponsoring Organization: DOE
• DOE Contract Number: AC52-06NA25396
• OSTI ID: 956664
• Report Number(s): LA-UR-08-08009; LA-UR-08-8009
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
APPROXIMATIONS
CALIBRATION
CLASSIFICATION
DATA
DETECTION
DISTRIBUTION
ILLUMINANCE
IMAGE PROCESSING
IMAGES
PERFORMANCE