Anomaly detection with high resolution hyperspectral observations

Cécile Chenot; Mehrdad Yaghoobi; Mike E. Davies; Yoann Altmann

doi:10.1109/GlobalSIP.2018.8646705

Anomaly detection with high resolution hyperspectral observations

Cécile Chenot, Mehrdad Yaghoobi, Mike E. Davies, Yoann Altmann

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

66 Downloads (Pure)

Abstract

Hyperspectral images enable the detection of targets due to the high spectral sampling. The latest generation of sensors also provides an unprecedented spatial resolution which is further exploited in this article to uncover hard to detect anomalies. In particular, we model and estimate the background building upon robust supervised linear unmixing. We benefit from the high resolution of the data to spatially constrain the background. This provides a novel framework for exploiting both the spectral and the energy variations created by the presence of unknown targets to detect them.

Original language	English
Title of host publication	2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
Publisher	IEEE
Pages	963-967
Number of pages	5
ISBN (Electronic)	9781728112954
DOIs	https://doi.org/10.1109/GlobalSIP.2018.8646705
Publication status	Published - 21 Feb 2019
Event	6th IEEE Global Conference on Signal and Information Processing 2018 - Anaheim, United States Duration: 26 Nov 2018 → 29 Nov 2018

Conference

Conference	6th IEEE Global Conference on Signal and Information Processing 2018
Abbreviated title	Global SIP 2018
Country/Territory	United States
City	Anaheim
Period	26/11/18 → 29/11/18

Keywords

Anomaly detection
Hyperspectral imaging
Linear mixture model

ASJC Scopus subject areas

Information Systems
Signal Processing

Access to Document

10.1109/GlobalSIP.2018.8646705

Download pdf
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 2.75 MBLicence: Copyright Publisher

Cite this

@inproceedings{92e8e3b310294923b12c0c347a586385,

title = "Anomaly detection with high resolution hyperspectral observations",

abstract = "Hyperspectral images enable the detection of targets due to the high spectral sampling. The latest generation of sensors also provides an unprecedented spatial resolution which is further exploited in this article to uncover hard to detect anomalies. In particular, we model and estimate the background building upon robust supervised linear unmixing. We benefit from the high resolution of the data to spatially constrain the background. This provides a novel framework for exploiting both the spectral and the energy variations created by the presence of unknown targets to detect them.",

keywords = "Anomaly detection, Hyperspectral imaging, Linear mixture model",

author = "C{\'e}cile Chenot and Mehrdad Yaghoobi and Davies, {Mike E.} and Yoann Altmann",

year = "2019",

month = feb,

day = "21",

doi = "10.1109/GlobalSIP.2018.8646705",

language = "English",

pages = "963--967",

booktitle = "2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)",

publisher = "IEEE",

address = "United States",

note = "6th IEEE Global Conference on Signal and Information Processing 2018, Global SIP 2018 ; Conference date: 26-11-2018 Through 29-11-2018",

}

Chenot, C, Yaghoobi, M, Davies, ME & Altmann, Y 2019, Anomaly detection with high resolution hyperspectral observations. in 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, pp. 963-967, 6th IEEE Global Conference on Signal and Information Processing 2018, Anaheim, California, United States, 26/11/18. https://doi.org/10.1109/GlobalSIP.2018.8646705

TY - GEN

T1 - Anomaly detection with high resolution hyperspectral observations

AU - Chenot, Cécile

AU - Yaghoobi, Mehrdad

AU - Davies, Mike E.

AU - Altmann, Yoann

PY - 2019/2/21

Y1 - 2019/2/21

N2 - Hyperspectral images enable the detection of targets due to the high spectral sampling. The latest generation of sensors also provides an unprecedented spatial resolution which is further exploited in this article to uncover hard to detect anomalies. In particular, we model and estimate the background building upon robust supervised linear unmixing. We benefit from the high resolution of the data to spatially constrain the background. This provides a novel framework for exploiting both the spectral and the energy variations created by the presence of unknown targets to detect them.

AB - Hyperspectral images enable the detection of targets due to the high spectral sampling. The latest generation of sensors also provides an unprecedented spatial resolution which is further exploited in this article to uncover hard to detect anomalies. In particular, we model and estimate the background building upon robust supervised linear unmixing. We benefit from the high resolution of the data to spatially constrain the background. This provides a novel framework for exploiting both the spectral and the energy variations created by the presence of unknown targets to detect them.

KW - Anomaly detection

KW - Hyperspectral imaging

KW - Linear mixture model

UR - http://www.scopus.com/inward/record.url?scp=85063102781&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2018.8646705

DO - 10.1109/GlobalSIP.2018.8646705

M3 - Conference contribution

SP - 963

EP - 967

BT - 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

PB - IEEE

T2 - 6th IEEE Global Conference on Signal and Information Processing 2018

Y2 - 26 November 2018 through 29 November 2018

ER -

Anomaly detection with high resolution hyperspectral observations

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this