Hyperspectral target detection using cluster-based probability models implemented in a generalized likelihood ratio test

Itan Levin, Tomer Hershkovitz, Stanley Rotman

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

2 Scopus citations

Abstract

We present an algorithm for sub-pixel target detection in hyperspectral images, considering both the common additive target model, and a replacement target model where the target's spectrum partially replaces that of the background. We implement an LRT based decision rule, estimating the underlying distributions using cluster detection in feature subsets of a decorrelated image. We select these subsets in subspaces corresponding to sets of consecutive eigenvalues of the data's empiric covariance. The densities are approximated using products of lower dimensional Gaussian mixture models. We utilize the estimated density functions to compute maximum likelihood estimates of the target's relative portion of the observed pixel spectrum, and obtain a GLRT based test statistic. Performance analysis of this proposed detector shows promising results when compared to the detection capabilities of the matched filter, which is used as a benchmark.

Original languageEnglish
Title of host publicationImage and Signal Processing for Remote Sensing XXV
EditorsLorenzo Bruzzone, Francesca Bovolo, Jon Atli Benediktsson
PublisherSPIE
ISBN (Electronic)9781510630130
DOIs
StatePublished - 1 Jan 2019
EventImage and Signal Processing for Remote Sensing XXV 2019 - Strasbourg, France
Duration: 9 Sep 201911 Sep 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11155
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceImage and Signal Processing for Remote Sensing XXV 2019
Country/TerritoryFrance
CityStrasbourg
Period9/09/1911/09/19

Keywords

  • GLRT
  • GMM
  • Hyperspectral
  • PCA
  • Replacement model
  • Subpixel target detection
  • Unsupervised clustering

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Hyperspectral target detection using cluster-based probability models implemented in a generalized likelihood ratio test'. Together they form a unique fingerprint.

Cite this