Bayesian inference-based fusion of radar imagery, military forces and tactical terrain models in the image exploitation system/balanced technology initiative

T. S. Levitt, C Larrabee Winter, C. J. Turner, R. A. Chestek, G. J. Ettinger, S. M. Sayre

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The Imagery Exploitation System/Balanced Technology Initiative (IES/BTI) inputs synthetic aperture radar (SAR) imagery and outputs probabilistically ranked interpretations of the presence and location of military force membership, organization, and expected ground formations. There are also probabilistic models of underlying terrain types from a tactical perspective that provide evidence supporting or denying the presence of forces at a location. The system compares sets of detected military vehicles extracted from imagery against the models of military units and their formations to create evidence of force type and location. Based on this evidence, the system dynamically forms hypotheses of the presence, location and formations of military forces on the ground, which it represents in a dynamically modified Bayesian network. The IES/BTI functional design is based on a decision theoretic model in which processing choices are determined as a utility function of the current state of interpretation of imagery and a top-level goal to exploit imagery as accurately and rapidly as possible, given the available data, current state of the interpretation of force hypotheses and the system processing suite. In order to obtain sufficient throughput in processing multi-megabyte SAR imagery, and also to take advantage of natural parallelism in 2D-spatial reasoning, the system is hosted on a heterogeneous network of multiple parallel computers including a SIMD Connection Machine 2 and a MIMD Encore Multimax. Independent testing by the US Army using imagery of Iraqi forces taken during Desert Storm, indicated an average 260% improvement in the performance of expert SAR imagery analysts using IES/BTI as a front end to their image exploitation.

Original languageEnglish (US)
Pages (from-to)667-686
Number of pages20
JournalInternational Journal of Human Computer Studies
Volume42
Issue number6
DOIs
StatePublished - Jun 1995
Externally publishedYes

Fingerprint

exploitation
Radar
Fusion reactions
Synthetic aperture radar
Military
Processing
Military vehicles
Heterogeneous networks
Bayesian networks
interpretation
evidence
Throughput
decision model
desert
Testing
military
expert
organization
performance

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Education
  • Engineering(all)
  • Software
  • Human-Computer Interaction
  • Hardware and Architecture

Cite this

Bayesian inference-based fusion of radar imagery, military forces and tactical terrain models in the image exploitation system/balanced technology initiative. / Levitt, T. S.; Winter, C Larrabee; Turner, C. J.; Chestek, R. A.; Ettinger, G. J.; Sayre, S. M.

In: International Journal of Human Computer Studies, Vol. 42, No. 6, 06.1995, p. 667-686.

Research output: Contribution to journalArticle

@article{ed656779ebb94472ac0eab6771394c05,
title = "Bayesian inference-based fusion of radar imagery, military forces and tactical terrain models in the image exploitation system/balanced technology initiative",
abstract = "The Imagery Exploitation System/Balanced Technology Initiative (IES/BTI) inputs synthetic aperture radar (SAR) imagery and outputs probabilistically ranked interpretations of the presence and location of military force membership, organization, and expected ground formations. There are also probabilistic models of underlying terrain types from a tactical perspective that provide evidence supporting or denying the presence of forces at a location. The system compares sets of detected military vehicles extracted from imagery against the models of military units and their formations to create evidence of force type and location. Based on this evidence, the system dynamically forms hypotheses of the presence, location and formations of military forces on the ground, which it represents in a dynamically modified Bayesian network. The IES/BTI functional design is based on a decision theoretic model in which processing choices are determined as a utility function of the current state of interpretation of imagery and a top-level goal to exploit imagery as accurately and rapidly as possible, given the available data, current state of the interpretation of force hypotheses and the system processing suite. In order to obtain sufficient throughput in processing multi-megabyte SAR imagery, and also to take advantage of natural parallelism in 2D-spatial reasoning, the system is hosted on a heterogeneous network of multiple parallel computers including a SIMD Connection Machine 2 and a MIMD Encore Multimax. Independent testing by the US Army using imagery of Iraqi forces taken during Desert Storm, indicated an average 260{\%} improvement in the performance of expert SAR imagery analysts using IES/BTI as a front end to their image exploitation.",
author = "Levitt, {T. S.} and Winter, {C Larrabee} and Turner, {C. J.} and Chestek, {R. A.} and Ettinger, {G. J.} and Sayre, {S. M.}",
year = "1995",
month = "6",
doi = "10.1006/ijhc.1995.1030",
language = "English (US)",
volume = "42",
pages = "667--686",
journal = "International Journal of Human Computer Studies",
issn = "1071-5819",
publisher = "Academic Press Inc.",
number = "6",

}

TY - JOUR

T1 - Bayesian inference-based fusion of radar imagery, military forces and tactical terrain models in the image exploitation system/balanced technology initiative

AU - Levitt, T. S.

AU - Winter, C Larrabee

AU - Turner, C. J.

AU - Chestek, R. A.

AU - Ettinger, G. J.

AU - Sayre, S. M.

PY - 1995/6

Y1 - 1995/6

N2 - The Imagery Exploitation System/Balanced Technology Initiative (IES/BTI) inputs synthetic aperture radar (SAR) imagery and outputs probabilistically ranked interpretations of the presence and location of military force membership, organization, and expected ground formations. There are also probabilistic models of underlying terrain types from a tactical perspective that provide evidence supporting or denying the presence of forces at a location. The system compares sets of detected military vehicles extracted from imagery against the models of military units and their formations to create evidence of force type and location. Based on this evidence, the system dynamically forms hypotheses of the presence, location and formations of military forces on the ground, which it represents in a dynamically modified Bayesian network. The IES/BTI functional design is based on a decision theoretic model in which processing choices are determined as a utility function of the current state of interpretation of imagery and a top-level goal to exploit imagery as accurately and rapidly as possible, given the available data, current state of the interpretation of force hypotheses and the system processing suite. In order to obtain sufficient throughput in processing multi-megabyte SAR imagery, and also to take advantage of natural parallelism in 2D-spatial reasoning, the system is hosted on a heterogeneous network of multiple parallel computers including a SIMD Connection Machine 2 and a MIMD Encore Multimax. Independent testing by the US Army using imagery of Iraqi forces taken during Desert Storm, indicated an average 260% improvement in the performance of expert SAR imagery analysts using IES/BTI as a front end to their image exploitation.

AB - The Imagery Exploitation System/Balanced Technology Initiative (IES/BTI) inputs synthetic aperture radar (SAR) imagery and outputs probabilistically ranked interpretations of the presence and location of military force membership, organization, and expected ground formations. There are also probabilistic models of underlying terrain types from a tactical perspective that provide evidence supporting or denying the presence of forces at a location. The system compares sets of detected military vehicles extracted from imagery against the models of military units and their formations to create evidence of force type and location. Based on this evidence, the system dynamically forms hypotheses of the presence, location and formations of military forces on the ground, which it represents in a dynamically modified Bayesian network. The IES/BTI functional design is based on a decision theoretic model in which processing choices are determined as a utility function of the current state of interpretation of imagery and a top-level goal to exploit imagery as accurately and rapidly as possible, given the available data, current state of the interpretation of force hypotheses and the system processing suite. In order to obtain sufficient throughput in processing multi-megabyte SAR imagery, and also to take advantage of natural parallelism in 2D-spatial reasoning, the system is hosted on a heterogeneous network of multiple parallel computers including a SIMD Connection Machine 2 and a MIMD Encore Multimax. Independent testing by the US Army using imagery of Iraqi forces taken during Desert Storm, indicated an average 260% improvement in the performance of expert SAR imagery analysts using IES/BTI as a front end to their image exploitation.

UR - http://www.scopus.com/inward/record.url?scp=0010516970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0010516970&partnerID=8YFLogxK

U2 - 10.1006/ijhc.1995.1030

DO - 10.1006/ijhc.1995.1030

M3 - Article

VL - 42

SP - 667

EP - 686

JO - International Journal of Human Computer Studies

JF - International Journal of Human Computer Studies

SN - 1071-5819

IS - 6

ER -