Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures
We study the problem of underwater debris classification and removal by remotely operated vehicles. This task is particularly important for subsea oil and gas fields exploitation. The classification of underwater debris is a challenging and difficult problem because of the complexity of underwater e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
Assiut University, Faculty of Engineering
2024-01-01
|
| Series: | JES: Journal of Engineering Sciences |
| Subjects: | |
| Online Access: | https://jesaun.journals.ekb.eg/article_330062_f6ebf6d22bda583c2f03288be414fbb2.pdf |
| _version_ | 1827391721773727744 |
|---|---|
| author | Mahmoud Assem Ibrahim M. Hassab-Allah Mohamed E.H. Eltaib Mahmoud Abdelrahim |
| author_facet | Mahmoud Assem Ibrahim M. Hassab-Allah Mohamed E.H. Eltaib Mahmoud Abdelrahim |
| author_sort | Mahmoud Assem |
| collection | DOAJ |
| description | We study the problem of underwater debris classification and removal by remotely operated vehicles. This task is particularly important for subsea oil and gas fields exploitation. The classification of underwater debris is a challenging and difficult problem because of the complexity of underwater environments. We investigate four different algorithms based on deep convolutional neural networks for detecting and classifying marine debris. The proposed techniques are built on Keras and Tensorflow using Python programming environment. To train the algorithm for detection, various dataset information containing different types of marine debris have been established. Four distinct classifier and activation function combinations have been compared experimentally. The dataset is consist of fifteen category. The suggested approach is a modified VGGNet-16 trained on the dataset. The use of a sigmoid classifier and the Relu activation function to categories marine improves classification accuracy. The overall result indicates that classification accuracy on the testing set is satisfactory. |
| first_indexed | 2024-03-08T17:16:20Z |
| format | Article |
| id | doaj.art-e8fbc9d3a1094a2784ed543ef24ad1fd |
| institution | Directory Open Access Journal |
| issn | 1687-0530 2356-8550 |
| language | Arabic |
| last_indexed | 2024-03-08T17:16:20Z |
| publishDate | 2024-01-01 |
| publisher | Assiut University, Faculty of Engineering |
| record_format | Article |
| series | JES: Journal of Engineering Sciences |
| spelling | doaj.art-e8fbc9d3a1094a2784ed543ef24ad1fd2024-01-03T11:49:57ZaraAssiut University, Faculty of EngineeringJES: Journal of Engineering Sciences1687-05302356-85502024-01-01521365110.21608/jesaun.2023.250095.1289330062Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network StructuresMahmoud Assem0Ibrahim M. Hassab-Allah1Mohamed E.H. Eltaib2Mahmoud Abdelrahim3M.Sc. Graduate student, Mechatronics Engineering Dept., Faculty of Engineering, Assiut University, Assiut, EgyptProfessor, Mechanical Engineering Dept., Faculty of Engineering, Assiut University, Assiut, Egypt.Assoc. Professor, Mechanical Engineering Dept., Faculty of Engineering, Kafrelsheikh University, Egypt.Assoc. Professor, Mechatronics Engineering Dept., Faculty of Engineering, Assiut University, Assiut, EgyptWe study the problem of underwater debris classification and removal by remotely operated vehicles. This task is particularly important for subsea oil and gas fields exploitation. The classification of underwater debris is a challenging and difficult problem because of the complexity of underwater environments. We investigate four different algorithms based on deep convolutional neural networks for detecting and classifying marine debris. The proposed techniques are built on Keras and Tensorflow using Python programming environment. To train the algorithm for detection, various dataset information containing different types of marine debris have been established. Four distinct classifier and activation function combinations have been compared experimentally. The dataset is consist of fifteen category. The suggested approach is a modified VGGNet-16 trained on the dataset. The use of a sigmoid classifier and the Relu activation function to categories marine improves classification accuracy. The overall result indicates that classification accuracy on the testing set is satisfactory.https://jesaun.journals.ekb.eg/article_330062_f6ebf6d22bda583c2f03288be414fbb2.pdfkeywords— remotely operated vehiclesmarine debrisdeep learningconvolutional neural networkimage processing |
| spellingShingle | Mahmoud Assem Ibrahim M. Hassab-Allah Mohamed E.H. Eltaib Mahmoud Abdelrahim Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures JES: Journal of Engineering Sciences keywords— remotely operated vehicles marine debris deep learning convolutional neural network image processing |
| title | Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures |
| title_full | Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures |
| title_fullStr | Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures |
| title_full_unstemmed | Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures |
| title_short | Identification of Unknown Marine Debris by ROVs Using Deep Learning and Different Convolutional Neural Network Structures |
| title_sort | identification of unknown marine debris by rovs using deep learning and different convolutional neural network structures |
| topic | keywords— remotely operated vehicles marine debris deep learning convolutional neural network image processing |
| url | https://jesaun.journals.ekb.eg/article_330062_f6ebf6d22bda583c2f03288be414fbb2.pdf |
| work_keys_str_mv | AT mahmoudassem identificationofunknownmarinedebrisbyrovsusingdeeplearninganddifferentconvolutionalneuralnetworkstructures AT ibrahimmhassaballah identificationofunknownmarinedebrisbyrovsusingdeeplearninganddifferentconvolutionalneuralnetworkstructures AT mohamedeheltaib identificationofunknownmarinedebrisbyrovsusingdeeplearninganddifferentconvolutionalneuralnetworkstructures AT mahmoudabdelrahim identificationofunknownmarinedebrisbyrovsusingdeeplearninganddifferentconvolutionalneuralnetworkstructures |