Item


Automatic Detection of Underwater Chain Links using a Forward-Looking Sonar

Underwater chain cleaning and inspection tasks are costly and time consuming operations that must be performed periodically to guarantee the safety of the moorings. We propose a framework towards an efficient and costeffective solution by using an autonomous underwater vehicle equipped with a forward-looking sonar. As a first step, we tackle the problem of individual chain link detection from the challenging forward-looking sonar data. To cope with occlusions and intensity variations due to viewpoint changes, the recognition problem is addressed as local pattern matching of the different link parts. We exploit the high frame-rate of the sonar to improve, by registration, the signal-to-noise ratio of the individual sonar frames and to cluster the local detections over time to increase robustness. Experiments with sonar images of a real chain are reported, showing a high percentage of correct link detections with good accuracy while potentially keeping real-time capabilities

This work has been supported by the FP7-ICT-2011-7 project PANDORA-Persistent Autonomy through Learning, Adaptation, Observation and Re-planning (Ref 288273) funded by the European Commission and the Spanish Project ANDREA/RAIMON (Ref CTM2011-29691-C02-02) funded by the Ministry of Science and Innovation

© Proceedings MTS/IEEE OCEANS: Bergen, Noruega, 10-14 June 2013, 2013, 7 p.

Institute of Electrical and Electronics Engineers (IEEE)

Author: Hurtós Vilarnau, Natàlia
Palomeras Rovira, Narcís
Nagappa, Sharad
Salvi, Joaquim
Date: 2013
Abstract: Underwater chain cleaning and inspection tasks are costly and time consuming operations that must be performed periodically to guarantee the safety of the moorings. We propose a framework towards an efficient and costeffective solution by using an autonomous underwater vehicle equipped with a forward-looking sonar. As a first step, we tackle the problem of individual chain link detection from the challenging forward-looking sonar data. To cope with occlusions and intensity variations due to viewpoint changes, the recognition problem is addressed as local pattern matching of the different link parts. We exploit the high frame-rate of the sonar to improve, by registration, the signal-to-noise ratio of the individual sonar frames and to cluster the local detections over time to increase robustness. Experiments with sonar images of a real chain are reported, showing a high percentage of correct link detections with good accuracy while potentially keeping real-time capabilities
This work has been supported by the FP7-ICT-2011-7 project PANDORA-Persistent Autonomy through Learning, Adaptation, Observation and Re-planning (Ref 288273) funded by the European Commission and the Spanish Project ANDREA/RAIMON (Ref CTM2011-29691-C02-02) funded by the Ministry of Science and Innovation
Format: application/pdf
ISBN: 978-1-4799-0000-8
Document access: http://hdl.handle.net/10256/11629
Language: eng
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Collection: MICINN/PN 2012-2014/CTM2011-29691-C02-02
Reproducció digital del document publicat a: http://dx.doi.org/10.1109/OCEANS-Bergen.2013.6608106
Articles publicats (D-ATC)
info:eu-repo/grantAgreement/EC/FP7/288273
Is part of: © Proceedings MTS/IEEE OCEANS: Bergen, Noruega, 10-14 June 2013, 2013, 7 p.
Rights: Tots els drets reservats
Subject: Robots submarins
Underwater robots
Vehicles submergibles
Submersibles
Sonar (Navegació)
Title: Automatic Detection of Underwater Chain Links using a Forward-Looking Sonar
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors