Anomaly detection in non-stationary backgrounds

Nir Gorelnik; Hadar Yehudai; Stanley R. Rotman

doi:10.1109/WHISPERS.2010.5594914

Anomaly detection in non-stationary backgrounds

Nir Gorelnik, Hadar Yehudai, Stanley R. Rotman

Department of Electrical & Computer Engineering

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

25 Scopus citations

Abstract

In this paper, several algorithms are considered as solutions for detecting anomalies in images which are inherently nonstationary, i.e., the images contain more than one type of background. We conclude that a recent algorithm suggested by A. Schaum [1] is most successful when coupled with several variations which we suggest. In particular, in concurrence with Schaum, for pixels in transition zones between two neighboring stationary areas, it is crucial to choose or construct a covariance matrix which is appropriate for that particular area. Methods to choose both the sample covariance matrix and the estimated local mean will be discussed.

Original language	English
Title of host publication	2nd Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program
DOIs	https://doi.org/10.1109/WHISPERS.2010.5594914
State	Published - 29 Nov 2010
Event	2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Reykjavik, Iceland Duration: 14 Jun 2010 → 16 Jun 2010

Publication series

Name	2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program

Conference

Conference	2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010
Country/Territory	Iceland
City	Reykjavik
Period	14/06/10 → 16/06/10

Keywords

Hyperspectral
Subpixel point target detection

ASJC Scopus subject areas

Information Systems
Signal Processing

Access to Document

10.1109/WHISPERS.2010.5594914

Cite this

Gorelnik, N., Yehudai, H., & Rotman, S. R. (2010). Anomaly detection in non-stationary backgrounds. In 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program Article 5594914 (2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program). https://doi.org/10.1109/WHISPERS.2010.5594914

@inproceedings{3b98c90649904ceba9efb997849a3812,

title = "Anomaly detection in non-stationary backgrounds",

abstract = "In this paper, several algorithms are considered as solutions for detecting anomalies in images which are inherently nonstationary, i.e., the images contain more than one type of background. We conclude that a recent algorithm suggested by A. Schaum [1] is most successful when coupled with several variations which we suggest. In particular, in concurrence with Schaum, for pixels in transition zones between two neighboring stationary areas, it is crucial to choose or construct a covariance matrix which is appropriate for that particular area. Methods to choose both the sample covariance matrix and the estimated local mean will be discussed.",

keywords = "Hyperspectral, Subpixel point target detection",

author = "Nir Gorelnik and Hadar Yehudai and Rotman, {Stanley R.}",

year = "2010",

month = nov,

day = "29",

doi = "10.1109/WHISPERS.2010.5594914",

language = "English",

isbn = "9781424489077",

series = "2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program",

booktitle = "2nd Workshop on Hyperspectral Image and Signal Processing",

note = "2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 ; Conference date: 14-06-2010 Through 16-06-2010",

}

Gorelnik, N, Yehudai, H & Rotman, SR 2010, Anomaly detection in non-stationary backgrounds. in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program., 5594914, 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program, 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010, Reykjavik, Iceland, 14/06/10. https://doi.org/10.1109/WHISPERS.2010.5594914

Anomaly detection in non-stationary backgrounds. / Gorelnik, Nir; Yehudai, Hadar; Rotman, Stanley R.
2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program. 2010. 5594914 (2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program).

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

TY - GEN

T1 - Anomaly detection in non-stationary backgrounds

AU - Gorelnik, Nir

AU - Yehudai, Hadar

AU - Rotman, Stanley R.

PY - 2010/11/29

Y1 - 2010/11/29

N2 - In this paper, several algorithms are considered as solutions for detecting anomalies in images which are inherently nonstationary, i.e., the images contain more than one type of background. We conclude that a recent algorithm suggested by A. Schaum [1] is most successful when coupled with several variations which we suggest. In particular, in concurrence with Schaum, for pixels in transition zones between two neighboring stationary areas, it is crucial to choose or construct a covariance matrix which is appropriate for that particular area. Methods to choose both the sample covariance matrix and the estimated local mean will be discussed.

AB - In this paper, several algorithms are considered as solutions for detecting anomalies in images which are inherently nonstationary, i.e., the images contain more than one type of background. We conclude that a recent algorithm suggested by A. Schaum [1] is most successful when coupled with several variations which we suggest. In particular, in concurrence with Schaum, for pixels in transition zones between two neighboring stationary areas, it is crucial to choose or construct a covariance matrix which is appropriate for that particular area. Methods to choose both the sample covariance matrix and the estimated local mean will be discussed.

KW - Hyperspectral

KW - Subpixel point target detection

UR - http://www.scopus.com/inward/record.url?scp=78649313822&partnerID=8YFLogxK

U2 - 10.1109/WHISPERS.2010.5594914

DO - 10.1109/WHISPERS.2010.5594914

M3 - Conference contribution

AN - SCOPUS:78649313822

SN - 9781424489077

T3 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program

BT - 2nd Workshop on Hyperspectral Image and Signal Processing

T2 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010

Y2 - 14 June 2010 through 16 June 2010

ER -

Gorelnik N, Yehudai H, Rotman SR. Anomaly detection in non-stationary backgrounds. In 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program. 2010. 5594914. (2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program). doi: 10.1109/WHISPERS.2010.5594914

Anomaly detection in non-stationary backgrounds

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this