Clairvoyant fusion detection of ocean anomalies in WorldView-2 spectral imagery

Alan Schaum; Eric Allman; Matthew Stites

doi:10.1117/12.2239142

19 September 2016 Clairvoyant fusion detection of ocean anomalies in WorldView-2 spectral imagery

Alan Schaum, Eric Allman, Matthew Stites

Proceedings Volume 9976, Imaging Spectrometry XXI; 99760G (2016) https://doi.org/10.1117/12.2239142
Event: SPIE Optical Engineering + Applications, 2016, San Diego, California, United States

Abstract

For every possible mixture of clouds and ocean in WorldView-2 8-band data, we construct an anomaly detector (called a “clairvoyant” because we never know which mixture is appropriate in any given pixel). Then we combine these using a fusion technique. The usual method of deriving an analytic expression describing the envelope of all the clairvoyants’ decision boundaries is not possible. Instead, we compute the intersections of infinitesimally close boundaries generated by differential changes in the mixing fraction. When glued together, these 6-dimensional hyperstrings constitute the desired 7-dimensional decision boundary of the fused anomaly detector. However, no closed-form solution exists for the fused result. Therefore, we construct an approximation to the fused detection boundary by first flattening the strings into 6-dimensional hyperplanes and then gluing them together à la 3D printing.

Conference Presentation

Citation Download Citation

Alan Schaum, Eric Allman, and Matthew Stites "Clairvoyant fusion detection of ocean anomalies in WorldView-2 spectral imagery", Proc. SPIE 9976, Imaging Spectrometry XXI, 99760G (19 September 2016); https://doi.org/10.1117/12.2239142

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available