Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models

In this study, we propose a method for inspecting the condition of hull surfaces using underwater images acquired from the camera of a remotely controlled underwater vehicle (ROUV). To this end, a soft voting ensemble classifier comprising six well-known convolutional neural network models was used....

Full description

Bibliographic Details
Main Authors: Byung Chul Kim, Hoe Chang Kim, Sungho Han, Dong Kyou Park
Format: Article
Language:English
Published: MDPI AG 2022-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/22/12/4392
_version_ 1827656759273062400
author Byung Chul Kim
Hoe Chang Kim
Sungho Han
Dong Kyou Park
author_facet Byung Chul Kim
Hoe Chang Kim
Sungho Han
Dong Kyou Park
author_sort Byung Chul Kim
collection DOAJ
description In this study, we propose a method for inspecting the condition of hull surfaces using underwater images acquired from the camera of a remotely controlled underwater vehicle (ROUV). To this end, a soft voting ensemble classifier comprising six well-known convolutional neural network models was used. Using the transfer learning technique, the images of the hull surfaces were used to retrain the six models. The proposed method exhibited an accuracy of 98.13%, a precision of 98.73%, a recall of 97.50%, and an F<sub>1</sub>-score of 98.11% for the classification of the test set. Furthermore, the time taken for the classification of one image was verified to be approximately 56.25 ms, which is applicable to ROUVs that require real-time inspection.
first_indexed 2024-03-09T22:33:51Z
format Article
id doaj.art-6a90c5b83cc042029f6604062abead68
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-09T22:33:51Z
publishDate 2022-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-6a90c5b83cc042029f6604062abead682023-11-23T18:52:43ZengMDPI AGSensors1424-82202022-06-012212439210.3390/s22124392Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned ModelsByung Chul Kim0Hoe Chang Kim1Sungho Han2Dong Kyou Park3School of Mechanical Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaSchool of Mechanical Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaSLM Global Co., Ltd., Daejeon 34037, KoreaDepartment of Electromechanical Convergence Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaIn this study, we propose a method for inspecting the condition of hull surfaces using underwater images acquired from the camera of a remotely controlled underwater vehicle (ROUV). To this end, a soft voting ensemble classifier comprising six well-known convolutional neural network models was used. Using the transfer learning technique, the images of the hull surfaces were used to retrain the six models. The proposed method exhibited an accuracy of 98.13%, a precision of 98.73%, a recall of 97.50%, and an F<sub>1</sub>-score of 98.11% for the classification of the test set. Furthermore, the time taken for the classification of one image was verified to be approximately 56.25 ms, which is applicable to ROUVs that require real-time inspection.https://www.mdpi.com/1424-8220/22/12/4392hull cleaning conditionunderwater inspection imagesoft voting ensemble classificationtransfer learning
spellingShingle Byung Chul Kim
Hoe Chang Kim
Sungho Han
Dong Kyou Park
Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
Sensors
hull cleaning condition
underwater inspection image
soft voting ensemble classification
transfer learning
title Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
title_full Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
title_fullStr Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
title_full_unstemmed Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
title_short Inspection of Underwater Hull Surface Condition Using the Soft Voting Ensemble of the Transfer-Learned Models
title_sort inspection of underwater hull surface condition using the soft voting ensemble of the transfer learned models
topic hull cleaning condition
underwater inspection image
soft voting ensemble classification
transfer learning
url https://www.mdpi.com/1424-8220/22/12/4392
work_keys_str_mv AT byungchulkim inspectionofunderwaterhullsurfaceconditionusingthesoftvotingensembleofthetransferlearnedmodels
AT hoechangkim inspectionofunderwaterhullsurfaceconditionusingthesoftvotingensembleofthetransferlearnedmodels
AT sunghohan inspectionofunderwaterhullsurfaceconditionusingthesoftvotingensembleofthetransferlearnedmodels
AT dongkyoupark inspectionofunderwaterhullsurfaceconditionusingthesoftvotingensembleofthetransferlearnedmodels