Comparative evaluation of hyperspectral anomaly detectors in different types of background

Dirk Borghys, Ingebjorg Kasen, Veronique Achard, Christiaan Perneel

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

Abstract

Anomaly detection (AD) in hyperspectral data has received a lot of attention for various applications. The aim of anomaly detection is to detect pixels in the hyperspectral data cube whose spectra differ significantly from the background spectra. Many anomaly detectors have been proposed in literature. They differ by the way the background is characterized and by the method used for determining the difference between the current pixel and the background. The most well-known anomaly detector is the RX detector that calculates the Mahalanobis distance between the pixel under test (PUT) and the background. Global RX characterizes the background of the complete scene by a single multi-variate normal distribution. In many cases this model is not appropriate for describing the background. For that reason a variety of other anomaly detection methods have been developed. This paper examines three classes of anomaly detectors: sub-space methods, local methods and segmentation-based methods. Representative examples of each class are chosen and applied on a set of hyperspectral data with different backgrounds. The results are evaluated and compared.

Original languageEnglish
Title of host publicationAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII
PublisherSociety of Photo-Optical Instrumentation Engineers
ISBN (Print)9780819490681
DOIs
Publication statusPublished - 2012
Event18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery - Baltimore, MD, United States
Duration: 23 Apr 201227 Apr 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8390
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery
Country/TerritoryUnited States
CityBaltimore, MD
Period23/04/1227/04/12

Keywords

  • Anomaly detection
  • Local anomaly detection
  • Segmentation-based anomaly detection
  • Sub-pixel anomalies
  • Sub-space anomaly detection
  • Urban scenes

Fingerprint

Dive into the research topics of 'Comparative evaluation of hyperspectral anomaly detectors in different types of background'. Together they form a unique fingerprint.

Cite this