Cargando…
Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images
Forward-looking sonar is a technique widely used for underwater detection. However, most sonar images have underwater noise and low resolution due to their acoustic properties. In recent years, the semantic segmentation model U-Net has shown excellent segmentation performance, and it has great poten...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9653894/ https://www.ncbi.nlm.nih.gov/pubmed/36366169 http://dx.doi.org/10.3390/s22218468 |
_version_ | 1784828793997754368 |
---|---|
author | Zhao, Dongdong Ge, Weihao Chen, Peng Hu, Yingtian Dang, Yuanjie Liang, Ronghua Guo, Xinxin |
author_facet | Zhao, Dongdong Ge, Weihao Chen, Peng Hu, Yingtian Dang, Yuanjie Liang, Ronghua Guo, Xinxin |
author_sort | Zhao, Dongdong |
collection | PubMed |
description | Forward-looking sonar is a technique widely used for underwater detection. However, most sonar images have underwater noise and low resolution due to their acoustic properties. In recent years, the semantic segmentation model U-Net has shown excellent segmentation performance, and it has great potential in forward-looking sonar image segmentation. However, forward-looking sonar images are affected by noise, which prevents the existing U-Net model from segmenting small objects effectively. Therefore, this study presents a forward-looking sonar semantic segmentation model called Feature Pyramid U-Net with Attention (FPUA). This model uses residual blocks to improve the training depth of the network. To improve the segmentation accuracy of the network for small objects, a feature pyramid module combined with an attention structure is introduced. This improves the model’s ability to learn deep semantic and shallow detail information. First, the proposed model is compared against other deep learning models and on two datasets, of which one was collected in a tank environment and the other was collected in a real marine environment. To further test the validity of the model, a real forward-looking sonar system was devised and employed in the lake trials. The results show that the proposed model performs better than the other models for small-object and few-sample classes and that it is competitive in semantic segmentation of forward-looking sonar images. |
format | Online Article Text |
id | pubmed-9653894 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96538942022-11-15 Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images Zhao, Dongdong Ge, Weihao Chen, Peng Hu, Yingtian Dang, Yuanjie Liang, Ronghua Guo, Xinxin Sensors (Basel) Article Forward-looking sonar is a technique widely used for underwater detection. However, most sonar images have underwater noise and low resolution due to their acoustic properties. In recent years, the semantic segmentation model U-Net has shown excellent segmentation performance, and it has great potential in forward-looking sonar image segmentation. However, forward-looking sonar images are affected by noise, which prevents the existing U-Net model from segmenting small objects effectively. Therefore, this study presents a forward-looking sonar semantic segmentation model called Feature Pyramid U-Net with Attention (FPUA). This model uses residual blocks to improve the training depth of the network. To improve the segmentation accuracy of the network for small objects, a feature pyramid module combined with an attention structure is introduced. This improves the model’s ability to learn deep semantic and shallow detail information. First, the proposed model is compared against other deep learning models and on two datasets, of which one was collected in a tank environment and the other was collected in a real marine environment. To further test the validity of the model, a real forward-looking sonar system was devised and employed in the lake trials. The results show that the proposed model performs better than the other models for small-object and few-sample classes and that it is competitive in semantic segmentation of forward-looking sonar images. MDPI 2022-11-03 /pmc/articles/PMC9653894/ /pubmed/36366169 http://dx.doi.org/10.3390/s22218468 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zhao, Dongdong Ge, Weihao Chen, Peng Hu, Yingtian Dang, Yuanjie Liang, Ronghua Guo, Xinxin Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title | Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title_full | Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title_fullStr | Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title_full_unstemmed | Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title_short | Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images |
title_sort | feature pyramid u-net with attention for semantic segmentation of forward-looking sonar images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9653894/ https://www.ncbi.nlm.nih.gov/pubmed/36366169 http://dx.doi.org/10.3390/s22218468 |
work_keys_str_mv | AT zhaodongdong featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT geweihao featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT chenpeng featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT huyingtian featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT dangyuanjie featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT liangronghua featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages AT guoxinxin featurepyramidunetwithattentionforsemanticsegmentationofforwardlookingsonarimages |