Classification using active polarimetry

Israel J. Vaughn, Brian G. Hoover, J. Scott Tyo

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

27 Citations (Scopus)

Abstract

Active (Mueller matrix) remote sensing is an under-utilized technique for material discrimination and classication. A full Mueller matrix instrument returns more information than a passive (Stokes) polarimeter; Mueller polarimeters measure depolarization and other linear transformations that materials impart on incident Stokes vectors, which passive polarimeters cannot measure. This increase in information therefore allows for better classication of materials (in general). Ideally, material classication over the entire polarized BRDF is desired, but sets of Mueller matrices for dierent materials are generally not separable by a linear classier over elevation and azimuthal target angles. We apply non-linear support vector machines (SVM) to classify materials over BRDF (all relevant angles) and show variations in receiver operator characteristic curves with scene composition and number of Mueller matrix channels in the observation.

Original languageEnglish
Title of host publicationPolarization
Subtitle of host publicationMeasurement, Analysis, and Remote Sensing X
PublisherSPIE
Number of pages6
ISBN (Print)9780819490421
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventPolarization: Measurement, Analysis, and Remote Sensing X - Baltimore, United States of America
Duration: 23 Apr 201224 Apr 2012
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/8364.toc

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8364
ISSN (Print)0277-786X

Conference

ConferencePolarization: Measurement, Analysis, and Remote Sensing X
Country/TerritoryUnited States of America
CityBaltimore
Period23/04/1224/04/12
Internet address

Cite this