Anomaly Detection from Hyperspectral Remote Sensing Imagery
Hyperspectral remote sensing imagery contains much more information in the spectral domain than does multispectral imagery. The consecutive and abundant spectral signals provide a great potential for classification and anomaly detection. In this study, two real hyperspectral data sets were used for...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-12-01
|
Series: | Geosciences |
Subjects: | |
Online Access: | http://www.mdpi.com/2076-3263/6/4/56 |
id |
doaj-9106aa88a8934ef4a83351075fa8635c |
---|---|
record_format |
Article |
spelling |
doaj-9106aa88a8934ef4a83351075fa8635c2020-11-24T21:05:39ZengMDPI AGGeosciences2076-32632016-12-01645610.3390/geosciences6040056geosciences6040056Anomaly Detection from Hyperspectral Remote Sensing ImageryQiandong Guo0Ruiliang Pu1Jun Cheng2School of Geosciences, University of South Florida, Tampa, FL 33620, USASchool of Geosciences, University of South Florida, Tampa, FL 33620, USASchool of Geosciences, University of South Florida, Tampa, FL 33620, USAHyperspectral remote sensing imagery contains much more information in the spectral domain than does multispectral imagery. The consecutive and abundant spectral signals provide a great potential for classification and anomaly detection. In this study, two real hyperspectral data sets were used for anomaly detection. One data set was an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data covering the post-attack World Trade Center (WTC) and anomalies are fire spots. The other data set called SpecTIR contained fabric panels as anomalies compared to their background. Existing anomaly detection algorithms including the Reed–Xiaoli detector (RXD), the blocked adaptive computation efficient outlier nominator (BACON), the random selection based anomaly detector (RSAD), the weighted-RXD (W-RXD), and the probabilistic anomaly detector (PAD) are reviewed here. The RXD generally sets strict assumptions to the background, which cannot be met in many scenarios, while BACON, RSAD, and W-RXD employ strategies to optimize the estimation of background information. The PAD firstly estimates both background information and anomaly information and then uses the information to conduct anomaly detection. Here, the BACON, RSAD, W-RXD, and PAD outperformed the RXD in terms of detection accuracy, and W-RXD and PAD required less time than BACON and RSAD.http://www.mdpi.com/2076-3263/6/4/56hyperspectral imageryanomaly detectionfire mapping |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Qiandong Guo Ruiliang Pu Jun Cheng |
spellingShingle |
Qiandong Guo Ruiliang Pu Jun Cheng Anomaly Detection from Hyperspectral Remote Sensing Imagery Geosciences hyperspectral imagery anomaly detection fire mapping |
author_facet |
Qiandong Guo Ruiliang Pu Jun Cheng |
author_sort |
Qiandong Guo |
title |
Anomaly Detection from Hyperspectral Remote Sensing Imagery |
title_short |
Anomaly Detection from Hyperspectral Remote Sensing Imagery |
title_full |
Anomaly Detection from Hyperspectral Remote Sensing Imagery |
title_fullStr |
Anomaly Detection from Hyperspectral Remote Sensing Imagery |
title_full_unstemmed |
Anomaly Detection from Hyperspectral Remote Sensing Imagery |
title_sort |
anomaly detection from hyperspectral remote sensing imagery |
publisher |
MDPI AG |
series |
Geosciences |
issn |
2076-3263 |
publishDate |
2016-12-01 |
description |
Hyperspectral remote sensing imagery contains much more information in the spectral domain than does multispectral imagery. The consecutive and abundant spectral signals provide a great potential for classification and anomaly detection. In this study, two real hyperspectral data sets were used for anomaly detection. One data set was an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data covering the post-attack World Trade Center (WTC) and anomalies are fire spots. The other data set called SpecTIR contained fabric panels as anomalies compared to their background. Existing anomaly detection algorithms including the Reed–Xiaoli detector (RXD), the blocked adaptive computation efficient outlier nominator (BACON), the random selection based anomaly detector (RSAD), the weighted-RXD (W-RXD), and the probabilistic anomaly detector (PAD) are reviewed here. The RXD generally sets strict assumptions to the background, which cannot be met in many scenarios, while BACON, RSAD, and W-RXD employ strategies to optimize the estimation of background information. The PAD firstly estimates both background information and anomaly information and then uses the information to conduct anomaly detection. Here, the BACON, RSAD, W-RXD, and PAD outperformed the RXD in terms of detection accuracy, and W-RXD and PAD required less time than BACON and RSAD. |
topic |
hyperspectral imagery anomaly detection fire mapping |
url |
http://www.mdpi.com/2076-3263/6/4/56 |
work_keys_str_mv |
AT qiandongguo anomalydetectionfromhyperspectralremotesensingimagery AT ruiliangpu anomalydetectionfromhyperspectralremotesensingimagery AT juncheng anomalydetectionfromhyperspectralremotesensingimagery |
_version_ |
1716768063909527552 |