Non-negative matrix factorization for hyperspectral anomaly detection

Sofia Aizenshtein, Ido Abergel, Moshe Mailler, Gili Segal, 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 image mean. This is a benchmark algorithm which 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 study the implementation of the NNMF algorithm on a hyperspectral data cube and propose two new anomaly detection algorithms, based on combining the NNMF and the RX algorithms. In the first version, we apply the NNMF algorithm on a hyperspectral image reducing the dimensionality; we then apply the RX algorithm. In the second version, we segment and cluster the dataset after applying the NNMF algorithm. Anomaly detection is then performed on this dataset. Using either of these algorithms overcomes a weakness of the RX algorithm in handling background clusters which are close to each other. The algorithm was tested on the RIT blind test dataset. From our results, we conclude that the two versions of the algorithm are sensitive to different types of anomalies; a two-dimensional scatterplot of the data comparing the RX values to either of the NNMF algorithms enables us to distinguish between the anomaly types. The ground truth shows that we have achieved high accuracy and less false alarms.

Original languageEnglish
Title of host publicationAlgorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXVI
EditorsMiguel Velez-Reyes, David W. Messinger
PublisherSPIE
ISBN (Electronic)9781510635616
DOIs
StatePublished - 1 Jan 2020
EventAlgorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXVI 2020 - Virtual, Online, United States
Duration: 27 Apr 20208 May 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11392
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceAlgorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXVI 2020
Country/TerritoryUnited States
CityVirtual, Online
Period27/04/208/05/20

Keywords

  • Anomaly detection
  • Hyperspectral
  • Non-negative matrix factorization.
  • Rx-algorithm

Fingerprint

Dive into the research topics of 'Non-negative matrix factorization for hyperspectral anomaly detection'. Together they form a unique fingerprint.

Cite this