Hyperspectral anomaly detection: A comparative evaluation of methods

D. Borghys, V. Achard, S. R. Rotman, N. Gorelik, C. Perneel, E. Schweicher

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

12 Scopus citations

Abstract

Anomaly detection in hyperspectral data has received a lot of attention for various applications. The aim of anomaly detection is to detect pixels in the hyperspectral datacube whose spectra differ significantly from the background spectra. In anomaly detection no prior knowledge about the target is assumed. Anomaly detection methods in general estimate the spectra of the background (locally or globally) and then detect anomalies as pixels with a large spectral distance w.r.t. the determined background spectra. Many types of anomaly detectors have been proposed in literature, each depending on several parameters. The aim of this paper is to compare the results of different types of anomaly detection when they are applied to scenes with different complexity: urban scenes with different complexity and rural scenes with sub-pixel anomalies. This paper only considers hyperspectral data in the VNIR and SWIR part of the EM spectrum (λ = 0.4-2.5μm).

Original languageEnglish
Title of host publication2011 30th URSI General Assembly and Scientific Symposium, URSIGASS 2011
DOIs
StatePublished - 21 Nov 2011
Event2011 30th URSI General Assembly and Scientific Symposium, URSIGASS 2011 - Istanbul, Turkey
Duration: 13 Aug 201120 Aug 2011

Publication series

Name2011 30th URSI General Assembly and Scientific Symposium, URSIGASS 2011

Conference

Conference2011 30th URSI General Assembly and Scientific Symposium, URSIGASS 2011
Country/TerritoryTurkey
CityIstanbul
Period13/08/1120/08/11

Fingerprint

Dive into the research topics of 'Hyperspectral anomaly detection: A comparative evaluation of methods'. Together they form a unique fingerprint.

Cite this