Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms

Gil Sharon; Roee Enbar; Stanley R. Rotman; Dan G. Blumberg; Ariel Schlamm; David Messinger

doi:10.1117/12.915346

Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms

Gil Sharon, Roee Enbar, Stanley R. Rotman, Dan G. Blumberg, Ariel Schlamm, David Messinger

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

Abstract

In this paper, we consider detecting man-made objects in natural images. We segment the image into tiles; we consider a variety of statistical metrics and correlate them to the presence of man-made targets. To quantify the metric, we apply a method of implanting targets and evaluating the resulting ROC (Receiver Operating Characteristic) curves. We rank previously reported algorithms and develop new ones in this paper.

Original language	English
Title of host publication	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII
Publisher	SPIE
ISBN (Print)	9780819490681
DOIs	https://doi.org/10.1117/12.915346
State	Published - 1 Jan 2012
Event	18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery - Baltimore, MD, United States Duration: 23 Apr 2012 → 27 Apr 2012

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	8390
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery
Country/Territory	United States
City	Baltimore, MD
Period	23/04/12 → 27/04/12

Keywords

Anomaly Detection
Convex Hull
Hyperspectral

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.915346

Cite this

Sharon, G., Enbar, R., Rotman, S. R., Blumberg, D. G., Schlamm, A., & Messinger, D. (2012). Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII Article 83900D (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8390). SPIE. https://doi.org/10.1117/12.915346

@inproceedings{8fa07d9f9dd34ab69614ac508606fe4e,

title = "Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms",

abstract = "In this paper, we consider detecting man-made objects in natural images. We segment the image into tiles; we consider a variety of statistical metrics and correlate them to the presence of man-made targets. To quantify the metric, we apply a method of implanting targets and evaluating the resulting ROC (Receiver Operating Characteristic) curves. We rank previously reported algorithms and develop new ones in this paper.",

keywords = "Anomaly Detection, Convex Hull, Hyperspectral",

author = "Gil Sharon and Roee Enbar and Rotman, {Stanley R.} and Blumberg, {Dan G.} and Ariel Schlamm and David Messinger",

year = "2012",

month = jan,

day = "1",

doi = "10.1117/12.915346",

language = "English",

isbn = "9780819490681",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

booktitle = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII",

address = "United States",

note = "18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery ; Conference date: 23-04-2012 Through 27-04-2012",

}

Sharon, G, Enbar, R, Rotman, SR , Blumberg, DG, Schlamm, A & Messinger, D 2012, Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms. in Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII., 83900D, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8390, SPIE, 18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery, Baltimore, MD, United States, 23/04/12. https://doi.org/10.1117/12.915346

Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms. / Sharon, Gil; Enbar, Roee; Rotman, Stanley R. et al.
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII. SPIE, 2012. 83900D (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8390).

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

TY - GEN

T1 - Detection of anomalous activity in hyperspectral imaging

T2 - 18th Annual Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery

AU - Sharon, Gil

AU - Enbar, Roee

AU - Rotman, Stanley R.

AU - Blumberg, Dan G.

AU - Schlamm, Ariel

AU - Messinger, David

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In this paper, we consider detecting man-made objects in natural images. We segment the image into tiles; we consider a variety of statistical metrics and correlate them to the presence of man-made targets. To quantify the metric, we apply a method of implanting targets and evaluating the resulting ROC (Receiver Operating Characteristic) curves. We rank previously reported algorithms and develop new ones in this paper.

AB - In this paper, we consider detecting man-made objects in natural images. We segment the image into tiles; we consider a variety of statistical metrics and correlate them to the presence of man-made targets. To quantify the metric, we apply a method of implanting targets and evaluating the resulting ROC (Receiver Operating Characteristic) curves. We rank previously reported algorithms and develop new ones in this paper.

KW - Anomaly Detection

KW - Convex Hull

KW - Hyperspectral

UR - http://www.scopus.com/inward/record.url?scp=84899424078&partnerID=8YFLogxK

U2 - 10.1117/12.915346

DO - 10.1117/12.915346

M3 - Conference contribution

AN - SCOPUS:84899424078

SN - 9780819490681

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII

PB - SPIE

Y2 - 23 April 2012 through 27 April 2012

ER -

Sharon G, Enbar R, Rotman SR , Blumberg DG, Schlamm A, Messinger D. Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII. SPIE. 2012. 83900D. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.915346

Detection of anomalous activity in hyperspectral imaging: Metrics for evaluating algorithms

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this