Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks
Seabed acoustic images are image data mosaics derived from seafloor acoustic backscattering intensity data, which is related to the type of sediment covering the seabed. Therefore, submarine sediment classification can be realized using seabed acoustic images, and has been studied extensively. Recen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8756236/ |
| _version_ | 1829470968835211264 |
|---|---|
| author | Xiaowen Luo Xiaoming Qin Ziyin Wu Fanlin Yang Mingwei Wang Jihong Shang |
| author_facet | Xiaowen Luo Xiaoming Qin Ziyin Wu Fanlin Yang Mingwei Wang Jihong Shang |
| author_sort | Xiaowen Luo |
| collection | DOAJ |
| description | Seabed acoustic images are image data mosaics derived from seafloor acoustic backscattering intensity data, which is related to the type of sediment covering the seabed. Therefore, submarine sediment classification can be realized using seabed acoustic images, and has been studied extensively. Recently, deep learning has also rapidly advanced; in particular, deep convolutional neural networks (CNNs) are now being used to achieve remarkable results in the field of image processing-showing that they are well-suited for image classification tasks. Previous studies have used GoogleNet to classify large-scale side-scan sonar data, with some sediments being well-classified. However, deep learning is data-driven and, theoretically, the greater the depth, the stronger is the learning ability of the feature. It is worth noting that the dataset used for sediment classification can sometimes be small. Hitherto, no related research has analyzed the feasibility and applicability of a CNN classifier for a small-sized seabed acoustic image dataset, so we adopted two different CNN classifier models to conduct the classification experiment in this study. As the results show, the CNN classifier can be applied to the classification of sediments based on a small-sized seabed acoustic image dataset, and the classification performance of shallow CNN was found to be better than that of the deep CNN on existing side-scan sonar data. In particular, the accuracy obtained from the results of several sediment classification experiments using a shallow CNN classifier ranged between 93.4% (Sand Wave) and 87.54% (Reef). |
| first_indexed | 2024-12-14T01:51:30Z |
| format | Article |
| id | doaj.art-df40f813bcd74f34915df16bc9c87519 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T01:51:30Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-df40f813bcd74f34915df16bc9c875192022-12-21T23:21:22ZengIEEEIEEE Access2169-35362019-01-017983319833910.1109/ACCESS.2019.29273668756236Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural NetworksXiaowen Luo0https://orcid.org/0000-0001-9185-6039Xiaoming Qin1https://orcid.org/0000-0001-8408-3998Ziyin Wu2Fanlin Yang3Mingwei Wang4Jihong Shang5Key Laboratory of Submarine Geosciences, State Oceanic Administration and Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaKey Laboratory of Submarine Geosciences, State Oceanic Administration and Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaKey Laboratory of Submarine Geosciences, State Oceanic Administration and Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaCollege of Geomatics, Shandong University of Science and Technology, Qingdao, ChinaCollege of Geomatics, Shandong University of Science and Technology, Qingdao, ChinaKey Laboratory of Submarine Geosciences, State Oceanic Administration and Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaSeabed acoustic images are image data mosaics derived from seafloor acoustic backscattering intensity data, which is related to the type of sediment covering the seabed. Therefore, submarine sediment classification can be realized using seabed acoustic images, and has been studied extensively. Recently, deep learning has also rapidly advanced; in particular, deep convolutional neural networks (CNNs) are now being used to achieve remarkable results in the field of image processing-showing that they are well-suited for image classification tasks. Previous studies have used GoogleNet to classify large-scale side-scan sonar data, with some sediments being well-classified. However, deep learning is data-driven and, theoretically, the greater the depth, the stronger is the learning ability of the feature. It is worth noting that the dataset used for sediment classification can sometimes be small. Hitherto, no related research has analyzed the feasibility and applicability of a CNN classifier for a small-sized seabed acoustic image dataset, so we adopted two different CNN classifier models to conduct the classification experiment in this study. As the results show, the CNN classifier can be applied to the classification of sediments based on a small-sized seabed acoustic image dataset, and the classification performance of shallow CNN was found to be better than that of the deep CNN on existing side-scan sonar data. In particular, the accuracy obtained from the results of several sediment classification experiments using a shallow CNN classifier ranged between 93.4% (Sand Wave) and 87.54% (Reef).https://ieeexplore.ieee.org/document/8756236/Deep convolutional neural networkseabed acoustic imageseabed sediment classification |
| spellingShingle | Xiaowen Luo Xiaoming Qin Ziyin Wu Fanlin Yang Mingwei Wang Jihong Shang Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks IEEE Access Deep convolutional neural network seabed acoustic image seabed sediment classification |
| title | Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks |
| title_full | Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks |
| title_fullStr | Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks |
| title_full_unstemmed | Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks |
| title_short | Sediment Classification of Small-Size Seabed Acoustic Images Using Convolutional Neural Networks |
| title_sort | sediment classification of small size seabed acoustic images using convolutional neural networks |
| topic | Deep convolutional neural network seabed acoustic image seabed sediment classification |
| url | https://ieeexplore.ieee.org/document/8756236/ |
| work_keys_str_mv | AT xiaowenluo sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks AT xiaomingqin sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks AT ziyinwu sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks AT fanlinyang sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks AT mingweiwang sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks AT jihongshang sedimentclassificationofsmallsizeseabedacousticimagesusingconvolutionalneuralnetworks |