MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model
High-precision habitat mapping can contribute to the identification and quantification of the human footprint on the seafloor. As a representative of seafloor habitats, seabed sediment classification is crucial for marine geological research, marine environment monitoring, marine engineering constru...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3708 |
| _version_ | 1797432737074774016 |
|---|---|
| author | Jiaxin Wan Zhiliang Qin Xiaodong Cui Fanlin Yang Muhammad Yasir Benjun Ma Xueqin Liu |
| author_facet | Jiaxin Wan Zhiliang Qin Xiaodong Cui Fanlin Yang Muhammad Yasir Benjun Ma Xueqin Liu |
| author_sort | Jiaxin Wan |
| collection | DOAJ |
| description | High-precision habitat mapping can contribute to the identification and quantification of the human footprint on the seafloor. As a representative of seafloor habitats, seabed sediment classification is crucial for marine geological research, marine environment monitoring, marine engineering construction, and seabed biotic and abiotic resource assessment. Multibeam echo-sounding systems (MBES) have become the most popular tool in terms of acoustic equipment for seabed sediment classification. However, sonar images tend to consist of obvious noise and stripe interference. Furthermore, the low efficiency and high cost of seafloor field sampling leads to limited field samples. The factors above restrict high accuracy classification by a single classifier. To further investigate the classification techniques for seabed sediments, we developed a decision fusion algorithm based on voting strategies and fuzzy membership rules to integrate the merits of deep learning and shallow learning methods. First, in order to overcome the influence of obvious noise and the lack of training samples, we employed an effective deep learning framework, namely random patches network (RPNet), for classification. Then, to alleviate the over-smoothness and misclassifications of RPNet, the misclassified pixels with a lower fuzzy membership degree were rectified by other shallow learning classifiers, using the proposed decision fusion algorithm. The effectiveness of the proposed method was tested in two areas of Europe. The results show that RPNet outperforms other traditional classification methods, and the decision fusion framework further improves the accuracy compared with the results of a single classifier. Our experiments predict a promising prospect for efficiently mapping seafloor habitats through deep learning and multi-classifier combinations, even with few field samples. |
| first_indexed | 2024-03-09T10:05:57Z |
| format | Article |
| id | doaj.art-ecc7726fca8245fc96ae1cd3bc37db96 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:05:57Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ecc7726fca8245fc96ae1cd3bc37db962023-12-01T23:08:26ZengMDPI AGRemote Sensing2072-42922022-08-011415370810.3390/rs14153708MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning ModelJiaxin Wan0Zhiliang Qin1Xiaodong Cui2Fanlin Yang3Muhammad Yasir4Benjun Ma5Xueqin Liu6Acoustic Science and Technology Laboratory, Harbin Engineering University, Harbin 150001, ChinaAcoustic Science and Technology Laboratory, Harbin Engineering University, Harbin 150001, ChinaCollege of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaAcoustic Science and Technology Laboratory, Harbin Engineering University, Harbin 150001, ChinaAcoustic Science and Technology Laboratory, Harbin Engineering University, Harbin 150001, ChinaHigh-precision habitat mapping can contribute to the identification and quantification of the human footprint on the seafloor. As a representative of seafloor habitats, seabed sediment classification is crucial for marine geological research, marine environment monitoring, marine engineering construction, and seabed biotic and abiotic resource assessment. Multibeam echo-sounding systems (MBES) have become the most popular tool in terms of acoustic equipment for seabed sediment classification. However, sonar images tend to consist of obvious noise and stripe interference. Furthermore, the low efficiency and high cost of seafloor field sampling leads to limited field samples. The factors above restrict high accuracy classification by a single classifier. To further investigate the classification techniques for seabed sediments, we developed a decision fusion algorithm based on voting strategies and fuzzy membership rules to integrate the merits of deep learning and shallow learning methods. First, in order to overcome the influence of obvious noise and the lack of training samples, we employed an effective deep learning framework, namely random patches network (RPNet), for classification. Then, to alleviate the over-smoothness and misclassifications of RPNet, the misclassified pixels with a lower fuzzy membership degree were rectified by other shallow learning classifiers, using the proposed decision fusion algorithm. The effectiveness of the proposed method was tested in two areas of Europe. The results show that RPNet outperforms other traditional classification methods, and the decision fusion framework further improves the accuracy compared with the results of a single classifier. Our experiments predict a promising prospect for efficiently mapping seafloor habitats through deep learning and multi-classifier combinations, even with few field samples.https://www.mdpi.com/2072-4292/14/15/3708seabed sediment classificationmultibeam echo-sounding systemdeep learningrandom patches networkdecision fusion |
| spellingShingle | Jiaxin Wan Zhiliang Qin Xiaodong Cui Fanlin Yang Muhammad Yasir Benjun Ma Xueqin Liu MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model Remote Sensing seabed sediment classification multibeam echo-sounding system deep learning random patches network decision fusion |
| title | MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model |
| title_full | MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model |
| title_fullStr | MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model |
| title_full_unstemmed | MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model |
| title_short | MBES Seabed Sediment Classification Based on a Decision Fusion Method Using Deep Learning Model |
| title_sort | mbes seabed sediment classification based on a decision fusion method using deep learning model |
| topic | seabed sediment classification multibeam echo-sounding system deep learning random patches network decision fusion |
| url | https://www.mdpi.com/2072-4292/14/15/3708 |
| work_keys_str_mv | AT jiaxinwan mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT zhiliangqin mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT xiaodongcui mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT fanlinyang mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT muhammadyasir mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT benjunma mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel AT xueqinliu mbesseabedsedimentclassificationbasedonadecisionfusionmethodusingdeeplearningmodel |