Anomaly subspace detection based on a multi-scale Markov random field model

Arnon Goldman, Israel Cohen

Research output: Chapter in Book/Report/Conference proceedingForeword/postscript

1 Scopus citations

Abstract

In this paper, we introduce a multi-scale Gaussian Markov random field (GMRF) model and a corresponding anomaly subspace detection algorithm. The proposed model is based on a multi-scale wavelet representation of the image, independent components analysis (ICA), and modeling each independent component as a GMRF. The anomaly detection is subsequently carried out by applying matched subspace detector (MSD) to the innovations process of the GMRFs, incorporating a priori information about the targets. The robustness of the proposed approach is demonstrated with application to automatic detection of airplanes on synthetic cloudy sky backgrounds.

Original languageEnglish
Title of host publication 2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel
Pages444-447
Number of pages4
StatePublished - 2004
Event2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings - Tel-Aviv, Israel
Duration: 6 Sep 20047 Sep 2004

Conference

Conference2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings
Country/TerritoryIsrael
CityTel-Aviv
Period6/09/047/09/04

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Fingerprint

Dive into the research topics of 'Anomaly subspace detection based on a multi-scale Markov random field model'. Together they form a unique fingerprint.

Cite this