A model based approach to mine detection and classification in sidescan sonar

S. Reed, Y. Petillot, J. Bell

Research output: Contribution to journalArticle

Abstract

Developments in Autonomous Underwater Vehicle(AUV) technology has shifted the direction of Mine-Counter-measure(MCM) research towards more automated techniques. This paper presents an automated approach to the detection and classification of mine-like objects using Sidescan Sonar images. Mine-like objects(MLO) are first detected using a Markov Random Field(MRF) model. The highlight and shadow regions of these MLO's are then extracted using a Co-operating Statistical Snake model. Objects which are not identified as false alarms are then considered in a third classification phase. A sonar simulator model considers different possible object shapes, measuring the plausibility of each match. A final classification decision is carried out using Dempster-Shafer theory which allows both mono-image and multi-image classification. Results for all phases are shown on real data.

Original languageEnglish
Pages (from-to)1402-1407
Number of pages6
JournalOceans Conference Record
Volume3
Publication statusPublished - 2003
EventCelebrating the Past... Teaming Toward the Future - San Diego, CA., United States
Duration: 22 Sep 200326 Sep 2003

Fingerprint

Sonar
Autonomous underwater vehicles
Image classification
Simulators

Cite this

@article{37ab9af3fec14ce6a7ed358bedc29b7c,
title = "A model based approach to mine detection and classification in sidescan sonar",
abstract = "Developments in Autonomous Underwater Vehicle(AUV) technology has shifted the direction of Mine-Counter-measure(MCM) research towards more automated techniques. This paper presents an automated approach to the detection and classification of mine-like objects using Sidescan Sonar images. Mine-like objects(MLO) are first detected using a Markov Random Field(MRF) model. The highlight and shadow regions of these MLO's are then extracted using a Co-operating Statistical Snake model. Objects which are not identified as false alarms are then considered in a third classification phase. A sonar simulator model considers different possible object shapes, measuring the plausibility of each match. A final classification decision is carried out using Dempster-Shafer theory which allows both mono-image and multi-image classification. Results for all phases are shown on real data.",
author = "S. Reed and Y. Petillot and J. Bell",
year = "2003",
language = "English",
volume = "3",
pages = "1402--1407",
journal = "Oceans Conference Record",
issn = "0197-7385",
publisher = "IEEE",

}

A model based approach to mine detection and classification in sidescan sonar. / Reed, S.; Petillot, Y.; Bell, J.

In: Oceans Conference Record, Vol. 3, 2003, p. 1402-1407.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A model based approach to mine detection and classification in sidescan sonar

AU - Reed, S.

AU - Petillot, Y.

AU - Bell, J.

PY - 2003

Y1 - 2003

N2 - Developments in Autonomous Underwater Vehicle(AUV) technology has shifted the direction of Mine-Counter-measure(MCM) research towards more automated techniques. This paper presents an automated approach to the detection and classification of mine-like objects using Sidescan Sonar images. Mine-like objects(MLO) are first detected using a Markov Random Field(MRF) model. The highlight and shadow regions of these MLO's are then extracted using a Co-operating Statistical Snake model. Objects which are not identified as false alarms are then considered in a third classification phase. A sonar simulator model considers different possible object shapes, measuring the plausibility of each match. A final classification decision is carried out using Dempster-Shafer theory which allows both mono-image and multi-image classification. Results for all phases are shown on real data.

AB - Developments in Autonomous Underwater Vehicle(AUV) technology has shifted the direction of Mine-Counter-measure(MCM) research towards more automated techniques. This paper presents an automated approach to the detection and classification of mine-like objects using Sidescan Sonar images. Mine-like objects(MLO) are first detected using a Markov Random Field(MRF) model. The highlight and shadow regions of these MLO's are then extracted using a Co-operating Statistical Snake model. Objects which are not identified as false alarms are then considered in a third classification phase. A sonar simulator model considers different possible object shapes, measuring the plausibility of each match. A final classification decision is carried out using Dempster-Shafer theory which allows both mono-image and multi-image classification. Results for all phases are shown on real data.

UR - http://www.scopus.com/inward/record.url?scp=1542609542&partnerID=8YFLogxK

M3 - Article

VL - 3

SP - 1402

EP - 1407

JO - Oceans Conference Record

JF - Oceans Conference Record

SN - 0197-7385

ER -