Rapid, high performance hyperspectral anomaly detection via global support vector data description

Reuven Meth, Amit Banerjee, Philippe Burlina, Thomas Strat

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Existing techniques for hyperspectral image (HSI) anomaly detection are computationally intensive precluding real-time implementation. The high dimensionality of the spatial/spectral hypercube with associated correlations between spectral bands present significant impediments to real time full hypercube processing that accurately encapsulates the underlying modeling. Traditional techniques have imposed Gaussian models, but these have suffered from significant computational requirements to compute large inverse covariance matrices as well as modeling inaccuracies. We have developed a novel data-driven, non-parametric HSI anomaly detector that has significantly reduced computational complexity with enhanced HSI modeling, providing the capability for real time performance with detection rates that match or surpass existing approaches. This detector, based on the Support Vector Data Description (SVDD), provides accurate, automated modeling of multi-modal data, facilitating effective application of a global background estimation technique which provides the capability for real time operation on a standard PC platform. We have demonstrated one second processing time on hypercubes of dimension 256×256×145, along with superior detection performance relative to alternate detectors. Computation performance analysis has been quantified via processing runtimes on a PC platform, and detection/false-alarm performance is described via Region Operating Characteristic (ROC) curve analysis for the SVDD anomaly detector vs. alternate anomaly detectors.

Original languageEnglish (US)
Title of host publicationAutomatic Target Recognition XVIII
Volume6967
DOIs
StatePublished - Jun 17 2008
EventAutomatic Target Recognition XVIII - Orlando, FL, United States
Duration: Mar 19 2008Mar 20 2008

Other

OtherAutomatic Target Recognition XVIII
CountryUnited States
CityOrlando, FL
Period3/19/083/20/08

Fingerprint

Support Vector Data Description
Data description
Anomaly Detection
High Performance
Detector
Hyperspectral Image
anomalies
Detectors
Hypercube
detectors
Anomaly
Alternate
platforms
Processing
Modeling
Image Modeling
real time operation
Characteristic Curve
Inverse matrix
Operating Characteristics

Keywords

  • Anomaly detection
  • HSI
  • Hyperspectral
  • Real-time anomaly detection
  • SVDD
  • SVM

ASJC Scopus subject areas

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

Cite this

Meth, R., Banerjee, A., Burlina, P., & Strat, T. (2008). Rapid, high performance hyperspectral anomaly detection via global support vector data description. In Automatic Target Recognition XVIII (Vol. 6967). [69670A] https://doi.org/10.1117/12.777164

Rapid, high performance hyperspectral anomaly detection via global support vector data description. / Meth, Reuven; Banerjee, Amit; Burlina, Philippe; Strat, Thomas.

Automatic Target Recognition XVIII. Vol. 6967 2008. 69670A.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meth, R, Banerjee, A, Burlina, P & Strat, T 2008, Rapid, high performance hyperspectral anomaly detection via global support vector data description. in Automatic Target Recognition XVIII. vol. 6967, 69670A, Automatic Target Recognition XVIII, Orlando, FL, United States, 3/19/08. https://doi.org/10.1117/12.777164
Meth R, Banerjee A, Burlina P, Strat T. Rapid, high performance hyperspectral anomaly detection via global support vector data description. In Automatic Target Recognition XVIII. Vol. 6967. 2008. 69670A https://doi.org/10.1117/12.777164
Meth, Reuven ; Banerjee, Amit ; Burlina, Philippe ; Strat, Thomas. / Rapid, high performance hyperspectral anomaly detection via global support vector data description. Automatic Target Recognition XVIII. Vol. 6967 2008.
@inproceedings{ddf42364ebde494a85df338ef577ba4d,
title = "Rapid, high performance hyperspectral anomaly detection via global support vector data description",
abstract = "Existing techniques for hyperspectral image (HSI) anomaly detection are computationally intensive precluding real-time implementation. The high dimensionality of the spatial/spectral hypercube with associated correlations between spectral bands present significant impediments to real time full hypercube processing that accurately encapsulates the underlying modeling. Traditional techniques have imposed Gaussian models, but these have suffered from significant computational requirements to compute large inverse covariance matrices as well as modeling inaccuracies. We have developed a novel data-driven, non-parametric HSI anomaly detector that has significantly reduced computational complexity with enhanced HSI modeling, providing the capability for real time performance with detection rates that match or surpass existing approaches. This detector, based on the Support Vector Data Description (SVDD), provides accurate, automated modeling of multi-modal data, facilitating effective application of a global background estimation technique which provides the capability for real time operation on a standard PC platform. We have demonstrated one second processing time on hypercubes of dimension 256×256×145, along with superior detection performance relative to alternate detectors. Computation performance analysis has been quantified via processing runtimes on a PC platform, and detection/false-alarm performance is described via Region Operating Characteristic (ROC) curve analysis for the SVDD anomaly detector vs. alternate anomaly detectors.",
keywords = "Anomaly detection, HSI, Hyperspectral, Real-time anomaly detection, SVDD, SVM",
author = "Reuven Meth and Amit Banerjee and Philippe Burlina and Thomas Strat",
year = "2008",
month = "6",
day = "17",
doi = "10.1117/12.777164",
language = "English (US)",
isbn = "9780819471581",
volume = "6967",
booktitle = "Automatic Target Recognition XVIII",

}

TY - GEN

T1 - Rapid, high performance hyperspectral anomaly detection via global support vector data description

AU - Meth, Reuven

AU - Banerjee, Amit

AU - Burlina, Philippe

AU - Strat, Thomas

PY - 2008/6/17

Y1 - 2008/6/17

N2 - Existing techniques for hyperspectral image (HSI) anomaly detection are computationally intensive precluding real-time implementation. The high dimensionality of the spatial/spectral hypercube with associated correlations between spectral bands present significant impediments to real time full hypercube processing that accurately encapsulates the underlying modeling. Traditional techniques have imposed Gaussian models, but these have suffered from significant computational requirements to compute large inverse covariance matrices as well as modeling inaccuracies. We have developed a novel data-driven, non-parametric HSI anomaly detector that has significantly reduced computational complexity with enhanced HSI modeling, providing the capability for real time performance with detection rates that match or surpass existing approaches. This detector, based on the Support Vector Data Description (SVDD), provides accurate, automated modeling of multi-modal data, facilitating effective application of a global background estimation technique which provides the capability for real time operation on a standard PC platform. We have demonstrated one second processing time on hypercubes of dimension 256×256×145, along with superior detection performance relative to alternate detectors. Computation performance analysis has been quantified via processing runtimes on a PC platform, and detection/false-alarm performance is described via Region Operating Characteristic (ROC) curve analysis for the SVDD anomaly detector vs. alternate anomaly detectors.

AB - Existing techniques for hyperspectral image (HSI) anomaly detection are computationally intensive precluding real-time implementation. The high dimensionality of the spatial/spectral hypercube with associated correlations between spectral bands present significant impediments to real time full hypercube processing that accurately encapsulates the underlying modeling. Traditional techniques have imposed Gaussian models, but these have suffered from significant computational requirements to compute large inverse covariance matrices as well as modeling inaccuracies. We have developed a novel data-driven, non-parametric HSI anomaly detector that has significantly reduced computational complexity with enhanced HSI modeling, providing the capability for real time performance with detection rates that match or surpass existing approaches. This detector, based on the Support Vector Data Description (SVDD), provides accurate, automated modeling of multi-modal data, facilitating effective application of a global background estimation technique which provides the capability for real time operation on a standard PC platform. We have demonstrated one second processing time on hypercubes of dimension 256×256×145, along with superior detection performance relative to alternate detectors. Computation performance analysis has been quantified via processing runtimes on a PC platform, and detection/false-alarm performance is described via Region Operating Characteristic (ROC) curve analysis for the SVDD anomaly detector vs. alternate anomaly detectors.

KW - Anomaly detection

KW - HSI

KW - Hyperspectral

KW - Real-time anomaly detection

KW - SVDD

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=44949100470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949100470&partnerID=8YFLogxK

U2 - 10.1117/12.777164

DO - 10.1117/12.777164

M3 - Conference contribution

AN - SCOPUS:44949100470

SN - 9780819471581

VL - 6967

BT - Automatic Target Recognition XVIII

ER -