Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery

<p dir="ltr">With the advances in sonar imaging technology, sonar imagery has increasingly been used for oceanographic studies in civilian and military applications. High-resolution imaging sonars can be mounted on various survey platforms, typically autonomous underwater vehicles, w...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Hoang Thanh Le (18940666) (author)
مؤلفون آخرون: Son Lam Phung (18460602) (author), Philip B. Chapple (18940669) (author), Abdesselam Bouzerdoum (17900021) (author), Christian H. Ritz (18940672) (author), Le Chung Tran (18560944) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513511906869248
author Hoang Thanh Le (18940666)
author2 Son Lam Phung (18460602)
Philip B. Chapple (18940669)
Abdesselam Bouzerdoum (17900021)
Christian H. Ritz (18940672)
Le Chung Tran (18560944)
author2_role author
author
author
author
author
author_facet Hoang Thanh Le (18940666)
Son Lam Phung (18460602)
Philip B. Chapple (18940669)
Abdesselam Bouzerdoum (17900021)
Christian H. Ritz (18940672)
Le Chung Tran (18560944)
author_role author
dc.creator.none.fl_str_mv Hoang Thanh Le (18940666)
Son Lam Phung (18460602)
Philip B. Chapple (18940669)
Abdesselam Bouzerdoum (17900021)
Christian H. Ritz (18940672)
Le Chung Tran (18560944)
dc.date.none.fl_str_mv 2020-05-18T12:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2020.2995390
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Deep_Gabor_Neural_Network_for_Automatic_Detection_of_Mine-Like_Objects_in_Sonar_Imagery/26134090
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Maritime engineering
Information and computing sciences
Data management and data science
Machine learning
Gabor neural network detector
Gabor layer
side-scan sonar
mine-like objects
Feature extraction
Sonar detection
Detectors
Neural networks
Object detection
Proposals
dc.title.none.fl_str_mv Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">With the advances in sonar imaging technology, sonar imagery has increasingly been used for oceanographic studies in civilian and military applications. High-resolution imaging sonars can be mounted on various survey platforms, typically autonomous underwater vehicles, which provide enhanced speed and improved data quality with long-range support. This paper addresses the automatic detection of mine-like objects using sonar images. The proposed Gabor-based detector is designed as a feature pyramid network with a small number of trainable weights. Our approach combines both semantically weak and strong features to handle mine-like objects at multiple scales effectively. For feature extraction, we introduce a parameterized Gabor layer which improves the generalization capability and computational efficiency. The steerable Gabor filtering modules are embedded within the cascaded layers to enhance the scale and orientation decomposition of images. The entire deep Gabor neural network is trained in an end-to-end manner from input sonar images with annotated mine-like objects. An extensive experimental evaluation on a real sonar dataset shows that the proposed method achieves competitive performance compared to the existing approaches.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.2995390" target="_blank">https://dx.doi.org/10.1109/access.2020.2995390</a></p>
eu_rights_str_mv openAccess
id Manara2_0144c55d2ac56660417d5cb8db051cac
identifier_str_mv 10.1109/access.2020.2995390
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26134090
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar ImageryHoang Thanh Le (18940666)Son Lam Phung (18460602)Philip B. Chapple (18940669)Abdesselam Bouzerdoum (17900021)Christian H. Ritz (18940672)Le Chung Tran (18560944)EngineeringMaritime engineeringInformation and computing sciencesData management and data scienceMachine learningGabor neural network detectorGabor layerside-scan sonarmine-like objectsFeature extractionSonar detectionDetectorsNeural networksObject detectionProposals<p dir="ltr">With the advances in sonar imaging technology, sonar imagery has increasingly been used for oceanographic studies in civilian and military applications. High-resolution imaging sonars can be mounted on various survey platforms, typically autonomous underwater vehicles, which provide enhanced speed and improved data quality with long-range support. This paper addresses the automatic detection of mine-like objects using sonar images. The proposed Gabor-based detector is designed as a feature pyramid network with a small number of trainable weights. Our approach combines both semantically weak and strong features to handle mine-like objects at multiple scales effectively. For feature extraction, we introduce a parameterized Gabor layer which improves the generalization capability and computational efficiency. The steerable Gabor filtering modules are embedded within the cascaded layers to enhance the scale and orientation decomposition of images. The entire deep Gabor neural network is trained in an end-to-end manner from input sonar images with annotated mine-like objects. An extensive experimental evaluation on a real sonar dataset shows that the proposed method achieves competitive performance compared to the existing approaches.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.2995390" target="_blank">https://dx.doi.org/10.1109/access.2020.2995390</a></p>2020-05-18T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2020.2995390https://figshare.com/articles/journal_contribution/Deep_Gabor_Neural_Network_for_Automatic_Detection_of_Mine-Like_Objects_in_Sonar_Imagery/26134090CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/261340902020-05-18T12:00:00Z
spellingShingle Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
Hoang Thanh Le (18940666)
Engineering
Maritime engineering
Information and computing sciences
Data management and data science
Machine learning
Gabor neural network detector
Gabor layer
side-scan sonar
mine-like objects
Feature extraction
Sonar detection
Detectors
Neural networks
Object detection
Proposals
status_str publishedVersion
title Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
title_full Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
title_fullStr Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
title_full_unstemmed Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
title_short Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
title_sort Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
topic Engineering
Maritime engineering
Information and computing sciences
Data management and data science
Machine learning
Gabor neural network detector
Gabor layer
side-scan sonar
mine-like objects
Feature extraction
Sonar detection
Detectors
Neural networks
Object detection
Proposals