Target recognition in synthetic aperture and high resolution sidescan sonar

J. M. Bell, Y. R. Petillot, K. Lebart, P. Y. Mignotte, H. Rohou, E. Coiras, S. Reed

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

Abstract

The accurate detection and identification of underwater targets continues as a major issue, despite, or perhaps as a result of, the promise of higher resolution underwater imaging systems, including synthetic aperture sonar and high frequency sidescan. Numerous techniques have been proposed for computer aided detection to detect all possible mine-like objects, and computer aided classification to classify whether the detected object is a target or not. The majority of existing techniques employ supervised classification systems which are reliant on training data. The success of these systems can be highly dependant on the similarity of the test data to the training data, which includes the effect of the background region on which the target was located. This paper will briefly discuss and compare two possible solutions to this problem. The first is a model based system for classification and the second utilises an augmented reality simulator to produce training data. © Heriot-Watt University and NURC.

Original languageEnglish
Title of host publicationIET Seminar on High Resolution Imaging and Target Classification
Pages99-106
Number of pages8
Volume2006
Edition11569
DOIs
Publication statusPublished - 2006
EventIET Seminar on High Resolution Imaging and Target Classification - London, United Kingdom
Duration: 21 Nov 200521 Nov 2005

Conference

ConferenceIET Seminar on High Resolution Imaging and Target Classification
CountryUnited Kingdom
CityLondon
Period21/11/0521/11/05

Fingerprint

Synthetic apertures
Sonar
Underwater imaging
Synthetic aperture sonar
Augmented reality
Imaging systems
Simulators

Keywords

  • Classification
  • Detection
  • Sonar

Cite this

Bell, J. M., Petillot, Y. R., Lebart, K., Mignotte, P. Y., Rohou, H., Coiras, E., & Reed, S. (2006). Target recognition in synthetic aperture and high resolution sidescan sonar. In IET Seminar on High Resolution Imaging and Target Classification (11569 ed., Vol. 2006, pp. 99-106) https://doi.org/10.1049/ic:20060079
Bell, J. M. ; Petillot, Y. R. ; Lebart, K. ; Mignotte, P. Y. ; Rohou, H. ; Coiras, E. ; Reed, S. / Target recognition in synthetic aperture and high resolution sidescan sonar. IET Seminar on High Resolution Imaging and Target Classification. Vol. 2006 11569. ed. 2006. pp. 99-106
@inproceedings{dc5dbdb7179544f99923fc7ad28c89e9,
title = "Target recognition in synthetic aperture and high resolution sidescan sonar",
abstract = "The accurate detection and identification of underwater targets continues as a major issue, despite, or perhaps as a result of, the promise of higher resolution underwater imaging systems, including synthetic aperture sonar and high frequency sidescan. Numerous techniques have been proposed for computer aided detection to detect all possible mine-like objects, and computer aided classification to classify whether the detected object is a target or not. The majority of existing techniques employ supervised classification systems which are reliant on training data. The success of these systems can be highly dependant on the similarity of the test data to the training data, which includes the effect of the background region on which the target was located. This paper will briefly discuss and compare two possible solutions to this problem. The first is a model based system for classification and the second utilises an augmented reality simulator to produce training data. {\circledC} Heriot-Watt University and NURC.",
keywords = "Classification, Detection, Sonar",
author = "Bell, {J. M.} and Petillot, {Y. R.} and K. Lebart and Mignotte, {P. Y.} and H. Rohou and E. Coiras and S. Reed",
year = "2006",
doi = "10.1049/ic:20060079",
language = "English",
isbn = "0863417205",
volume = "2006",
pages = "99--106",
booktitle = "IET Seminar on High Resolution Imaging and Target Classification",
edition = "11569",

}

Bell, JM, Petillot, YR, Lebart, K, Mignotte, PY, Rohou, H, Coiras, E & Reed, S 2006, Target recognition in synthetic aperture and high resolution sidescan sonar. in IET Seminar on High Resolution Imaging and Target Classification. 11569 edn, vol. 2006, pp. 99-106, IET Seminar on High Resolution Imaging and Target Classification, London, United Kingdom, 21/11/05. https://doi.org/10.1049/ic:20060079

Target recognition in synthetic aperture and high resolution sidescan sonar. / Bell, J. M.; Petillot, Y. R.; Lebart, K.; Mignotte, P. Y.; Rohou, H.; Coiras, E.; Reed, S.

IET Seminar on High Resolution Imaging and Target Classification. Vol. 2006 11569. ed. 2006. p. 99-106.

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

TY - GEN

T1 - Target recognition in synthetic aperture and high resolution sidescan sonar

AU - Bell, J. M.

AU - Petillot, Y. R.

AU - Lebart, K.

AU - Mignotte, P. Y.

AU - Rohou, H.

AU - Coiras, E.

AU - Reed, S.

PY - 2006

Y1 - 2006

N2 - The accurate detection and identification of underwater targets continues as a major issue, despite, or perhaps as a result of, the promise of higher resolution underwater imaging systems, including synthetic aperture sonar and high frequency sidescan. Numerous techniques have been proposed for computer aided detection to detect all possible mine-like objects, and computer aided classification to classify whether the detected object is a target or not. The majority of existing techniques employ supervised classification systems which are reliant on training data. The success of these systems can be highly dependant on the similarity of the test data to the training data, which includes the effect of the background region on which the target was located. This paper will briefly discuss and compare two possible solutions to this problem. The first is a model based system for classification and the second utilises an augmented reality simulator to produce training data. © Heriot-Watt University and NURC.

AB - The accurate detection and identification of underwater targets continues as a major issue, despite, or perhaps as a result of, the promise of higher resolution underwater imaging systems, including synthetic aperture sonar and high frequency sidescan. Numerous techniques have been proposed for computer aided detection to detect all possible mine-like objects, and computer aided classification to classify whether the detected object is a target or not. The majority of existing techniques employ supervised classification systems which are reliant on training data. The success of these systems can be highly dependant on the similarity of the test data to the training data, which includes the effect of the background region on which the target was located. This paper will briefly discuss and compare two possible solutions to this problem. The first is a model based system for classification and the second utilises an augmented reality simulator to produce training data. © Heriot-Watt University and NURC.

KW - Classification

KW - Detection

KW - Sonar

UR - http://www.scopus.com/inward/record.url?scp=34047127462&partnerID=8YFLogxK

U2 - 10.1049/ic:20060079

DO - 10.1049/ic:20060079

M3 - Conference contribution

SN - 0863417205

SN - 9780863417207

VL - 2006

SP - 99

EP - 106

BT - IET Seminar on High Resolution Imaging and Target Classification

ER -

Bell JM, Petillot YR, Lebart K, Mignotte PY, Rohou H, Coiras E et al. Target recognition in synthetic aperture and high resolution sidescan sonar. In IET Seminar on High Resolution Imaging and Target Classification. 11569 ed. Vol. 2006. 2006. p. 99-106 https://doi.org/10.1049/ic:20060079