Cargando…

Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection

Submarine garbage is constantly destroying the marine ecological environment and polluting the ocean. It is critical to use detection methods to quickly locate and identify submarine garbage. The background of submarine garbage images is much more complex than that of natural scene images, with obje...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Hui, Guo, Xinwei, Guo, Guihai, Cao, Yizhi, Hu, Xinglei, Yue, Pujie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10522724/
https://www.ncbi.nlm.nih.gov/pubmed/37752172
http://dx.doi.org/10.1038/s41598-023-42896-3
_version_ 1785110414882766848
author Zheng, Hui
Guo, Xinwei
Guo, Guihai
Cao, Yizhi
Hu, Xinglei
Yue, Pujie
author_facet Zheng, Hui
Guo, Xinwei
Guo, Guihai
Cao, Yizhi
Hu, Xinglei
Yue, Pujie
author_sort Zheng, Hui
collection PubMed
description Submarine garbage is constantly destroying the marine ecological environment and polluting the ocean. It is critical to use detection methods to quickly locate and identify submarine garbage. The background of submarine garbage images is much more complex than that of natural scene images, with object deformation and missing contours putting higher demands on the detection network. To solve the problem of low accuracy under complex backgrounds, full stage networks with auxiliary focal loss and multi-attention module are proposed for submarine garbage object detection based on YOLO. To maximize the gradient combination, a hierarchical fusion feature mechanism and a segmentation and merging strategy are used in this paper to optimize the difference in gradient combination to obtain full-stage features. Then the criss-cross attention module is used to precisely extract multi-scale features of small object dense regions while removing noise information from complex backgrounds. Finally, the auxiliary focal loss function addresses the issue of unbalanced positive and negative samples, focusing on the learning of difficult samples while improving overall detection precision. Based on comparative experiments and ablation experiments, the FSA networks achieved state-of-the-art performance, and is applicable to the real-time object detection of submarine garbage in complex backgrounds.
format Online
Article
Text
id pubmed-10522724
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-105227242023-09-28 Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection Zheng, Hui Guo, Xinwei Guo, Guihai Cao, Yizhi Hu, Xinglei Yue, Pujie Sci Rep Article Submarine garbage is constantly destroying the marine ecological environment and polluting the ocean. It is critical to use detection methods to quickly locate and identify submarine garbage. The background of submarine garbage images is much more complex than that of natural scene images, with object deformation and missing contours putting higher demands on the detection network. To solve the problem of low accuracy under complex backgrounds, full stage networks with auxiliary focal loss and multi-attention module are proposed for submarine garbage object detection based on YOLO. To maximize the gradient combination, a hierarchical fusion feature mechanism and a segmentation and merging strategy are used in this paper to optimize the difference in gradient combination to obtain full-stage features. Then the criss-cross attention module is used to precisely extract multi-scale features of small object dense regions while removing noise information from complex backgrounds. Finally, the auxiliary focal loss function addresses the issue of unbalanced positive and negative samples, focusing on the learning of difficult samples while improving overall detection precision. Based on comparative experiments and ablation experiments, the FSA networks achieved state-of-the-art performance, and is applicable to the real-time object detection of submarine garbage in complex backgrounds. Nature Publishing Group UK 2023-09-26 /pmc/articles/PMC10522724/ /pubmed/37752172 http://dx.doi.org/10.1038/s41598-023-42896-3 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Zheng, Hui
Guo, Xinwei
Guo, Guihai
Cao, Yizhi
Hu, Xinglei
Yue, Pujie
Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title_full Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title_fullStr Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title_full_unstemmed Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title_short Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
title_sort full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10522724/
https://www.ncbi.nlm.nih.gov/pubmed/37752172
http://dx.doi.org/10.1038/s41598-023-42896-3
work_keys_str_mv AT zhenghui fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection
AT guoxinwei fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection
AT guoguihai fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection
AT caoyizhi fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection
AT huxinglei fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection
AT yuepujie fullstagenetworkswithauxiliaryfocallossandmultiattentionmoduleforsubmarinegarbageobjectdetection