Consensus Anomaly Detection Using Clustering Methods in Hyperspectral imagery

Yoav Amiel, Adar Frajman, Stanley R. Rotman

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

Abstract

A common anomaly detection algorithm for hyperspectral imagery is the RX algorithm based on the Mahalanobis distance of each pixel from the expected value of that pixel. This algorithm can be applied either directly on a hyperspectral image or on a dimensionality-reduced hyperspectral image. Recent work on Non-Negative Matrix Factorization (NNMF) provides a fast-iterative algorithm for decomposing a hyperspectral cube and achieving dimensionality reduction. In this paper, we present the RICHARD (Robust Iterative Consensus Anomaly RX Detection) algorithm that generates more than 100 RX tests after data manipulations (such as Principal Component Analysis (PCA) and NNMF) which vary in their specific parameters; we then use a weighted consensus voting process in order to detect anomalies without any prior knowledge. Using the RICHARD algorithm can enhance our options in finding obscure anomalies which do not appear in every algorithm.

Original languageEnglish
Title of host publicationImaging Spectrometry XXIV
Subtitle of host publicationApplications, Sensors, and Processing
EditorsEmmett J. Ientilucci, Pantazis Mouroulis
PublisherSPIE
ISBN (Electronic)9781510638143
DOIs
StatePublished - 1 Jan 2020
EventImaging Spectrometry XXIV: Applications, Sensors, and Processing 2020 - Virtual, Online, United States
Duration: 24 Aug 20204 Sep 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11504
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceImaging Spectrometry XXIV: Applications, Sensors, and Processing 2020
Country/TerritoryUnited States
CityVirtual, Online
Period24/08/204/09/20

Keywords

  • Anomalies detection
  • Consensus Detection
  • Hyperspectral
  • Image Processing
  • Machine Learning
  • NNMF algorithm
  • RX algorithm
  • SSRX

Fingerprint

Dive into the research topics of 'Consensus Anomaly Detection Using Clustering Methods in Hyperspectral imagery'. Together they form a unique fingerprint.

Cite this