Adaptive target recognition

Bir Bhanu, Yingqiang Lin, Grinnell Jones, Jing Peng

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

5 Citations (Scopus)

Abstract

Target recognition is a multi-level process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their performance at the given probability of correct identification (PCI) and probability of false alarm (Pf) is a key challenge in computer vision and pattern recognition research. In this paper a robust closed-loop system for recognition of SAR images based on reinforcement learning is presented. The parameters in the model-based SAR target recognition are learned. The method meets performance specifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targets of different configuration and targets of different depression angles.

Original languageEnglish
Title of host publicationProceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum
Subtitle of host publicationMethods and Applications, CVBVS 1999
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages71-81
Number of pages11
ISBN (Electronic)0769500501, 9780769500508
DOIs
StatePublished - 1 Jan 1999
Event1st IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999 - Fort Collins, United States
Duration: 21 Jun 199922 Jun 1999

Other

Other1st IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999
CountryUnited States
CityFort Collins
Period21/06/9922/06/99

Fingerprint

target recognition
learning
Feedback
Open systems
false alarms
Reinforcement learning
computer vision
reinforcement
feedback control
Closed loop systems
pattern recognition
imagery
Computer vision
Pattern recognition
Learning systems
specifications
Specifications
configurations

Cite this

Bhanu, B., Lin, Y., Jones, G., & Peng, J. (1999). Adaptive target recognition. In Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999 (pp. 71-81). [781096] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVBVS.1999.781096
Bhanu, Bir ; Lin, Yingqiang ; Jones, Grinnell ; Peng, Jing. / Adaptive target recognition. Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999. Institute of Electrical and Electronics Engineers Inc., 1999. pp. 71-81
@inproceedings{b47ec271a4714d71a32c6fe33648a391,
title = "Adaptive target recognition",
abstract = "Target recognition is a multi-level process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their performance at the given probability of correct identification (PCI) and probability of false alarm (Pf) is a key challenge in computer vision and pattern recognition research. In this paper a robust closed-loop system for recognition of SAR images based on reinforcement learning is presented. The parameters in the model-based SAR target recognition are learned. The method meets performance specifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targets of different configuration and targets of different depression angles.",
author = "Bir Bhanu and Yingqiang Lin and Grinnell Jones and Jing Peng",
year = "1999",
month = "1",
day = "1",
doi = "10.1109/CVBVS.1999.781096",
language = "English",
pages = "71--81",
booktitle = "Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Bhanu, B, Lin, Y, Jones, G & Peng, J 1999, Adaptive target recognition. in Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999., 781096, Institute of Electrical and Electronics Engineers Inc., pp. 71-81, 1st IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999, Fort Collins, United States, 21/06/99. https://doi.org/10.1109/CVBVS.1999.781096

Adaptive target recognition. / Bhanu, Bir; Lin, Yingqiang; Jones, Grinnell; Peng, Jing.

Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999. Institute of Electrical and Electronics Engineers Inc., 1999. p. 71-81 781096.

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

TY - GEN

T1 - Adaptive target recognition

AU - Bhanu, Bir

AU - Lin, Yingqiang

AU - Jones, Grinnell

AU - Peng, Jing

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Target recognition is a multi-level process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their performance at the given probability of correct identification (PCI) and probability of false alarm (Pf) is a key challenge in computer vision and pattern recognition research. In this paper a robust closed-loop system for recognition of SAR images based on reinforcement learning is presented. The parameters in the model-based SAR target recognition are learned. The method meets performance specifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targets of different configuration and targets of different depression angles.

AB - Target recognition is a multi-level process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their performance at the given probability of correct identification (PCI) and probability of false alarm (Pf) is a key challenge in computer vision and pattern recognition research. In this paper a robust closed-loop system for recognition of SAR images based on reinforcement learning is presented. The parameters in the model-based SAR target recognition are learned. The method meets performance specifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targets of different configuration and targets of different depression angles.

UR - http://www.scopus.com/inward/record.url?scp=85013963179&partnerID=8YFLogxK

U2 - 10.1109/CVBVS.1999.781096

DO - 10.1109/CVBVS.1999.781096

M3 - Conference contribution

AN - SCOPUS:85013963179

SP - 71

EP - 81

BT - Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bhanu B, Lin Y, Jones G, Peng J. Adaptive target recognition. In Proceedings - IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, CVBVS 1999. Institute of Electrical and Electronics Engineers Inc. 1999. p. 71-81. 781096 https://doi.org/10.1109/CVBVS.1999.781096