Synergistic Attention for Ship Instance Segmentation in SAR Images

This paper takes account of the fact that there is a lack of consideration for imaging methods and target characteristics of synthetic aperture radar (SAR) images among existing instance segmentation methods designed for optical images. Thus, we propose a method for SAR ship instance segmentation ba...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Danpei Zhao, Chunbo Zhu, Jing Qi, Xinhu Qi, Zhenhua Su, Zhenwei Shi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	synergistic attention ship instance segmentation SAR images feature extraction feature fusion Science Q
Acceso en línea:	https://doaj.org/article/775750857d774efda9098f850b2c8c30
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:775750857d774efda9098f850b2c8c30
record_format	dspace
spelling	oai:doaj.org-article:775750857d774efda9098f850b2c8c302021-11-11T18:55:01ZSynergistic Attention for Ship Instance Segmentation in SAR Images10.3390/rs132143842072-4292https://doaj.org/article/775750857d774efda9098f850b2c8c302021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4384https://doaj.org/toc/2072-4292This paper takes account of the fact that there is a lack of consideration for imaging methods and target characteristics of synthetic aperture radar (SAR) images among existing instance segmentation methods designed for optical images. Thus, we propose a method for SAR ship instance segmentation based on the synergistic attention mechanism which not only improves the performance of ship detection with multi-task branches but also provides pixel-level contours for subsequent applications such as orientation or category determination. The proposed method—SA R-CNN—presents a synergistic attention strategy at the image, semantic, and target level with the following module corresponding to the different stages in the whole process of the instance segmentation framework. The global attention module (GAM), semantic attention module (SAM), and anchor attention module (AAM) were constructed for feature extraction, feature fusion, and target location, respectively, for multi-scale ship targets under complex background conditions. Compared with several state-of-the-art methods, our method reached 68.7 AP in detection and 56.5 AP in segmentation on the HRSID dataset, and showed 91.5 AP in the detection task on the SSDD dataset.Danpei ZhaoChunbo ZhuJing QiXinhu QiZhenhua SuZhenwei ShiMDPI AGarticlesynergistic attentionship instance segmentationSAR imagesfeature extractionfeature fusionScienceQENRemote Sensing, Vol 13, Iss 4384, p 4384 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	synergistic attention ship instance segmentation SAR images feature extraction feature fusion Science Q
spellingShingle	synergistic attention ship instance segmentation SAR images feature extraction feature fusion Science Q Danpei Zhao Chunbo Zhu Jing Qi Xinhu Qi Zhenhua Su Zhenwei Shi Synergistic Attention for Ship Instance Segmentation in SAR Images
description	This paper takes account of the fact that there is a lack of consideration for imaging methods and target characteristics of synthetic aperture radar (SAR) images among existing instance segmentation methods designed for optical images. Thus, we propose a method for SAR ship instance segmentation based on the synergistic attention mechanism which not only improves the performance of ship detection with multi-task branches but also provides pixel-level contours for subsequent applications such as orientation or category determination. The proposed method—SA R-CNN—presents a synergistic attention strategy at the image, semantic, and target level with the following module corresponding to the different stages in the whole process of the instance segmentation framework. The global attention module (GAM), semantic attention module (SAM), and anchor attention module (AAM) were constructed for feature extraction, feature fusion, and target location, respectively, for multi-scale ship targets under complex background conditions. Compared with several state-of-the-art methods, our method reached 68.7 AP in detection and 56.5 AP in segmentation on the HRSID dataset, and showed 91.5 AP in the detection task on the SSDD dataset.
format	article
author	Danpei Zhao Chunbo Zhu Jing Qi Xinhu Qi Zhenhua Su Zhenwei Shi
author_facet	Danpei Zhao Chunbo Zhu Jing Qi Xinhu Qi Zhenhua Su Zhenwei Shi
author_sort	Danpei Zhao
title	Synergistic Attention for Ship Instance Segmentation in SAR Images
title_short	Synergistic Attention for Ship Instance Segmentation in SAR Images
title_full	Synergistic Attention for Ship Instance Segmentation in SAR Images
title_fullStr	Synergistic Attention for Ship Instance Segmentation in SAR Images
title_full_unstemmed	Synergistic Attention for Ship Instance Segmentation in SAR Images
title_sort	synergistic attention for ship instance segmentation in sar images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/775750857d774efda9098f850b2c8c30
work_keys_str_mv	AT danpeizhao synergisticattentionforshipinstancesegmentationinsarimages AT chunbozhu synergisticattentionforshipinstancesegmentationinsarimages AT jingqi synergisticattentionforshipinstancesegmentationinsarimages AT xinhuqi synergisticattentionforshipinstancesegmentationinsarimages AT zhenhuasu synergisticattentionforshipinstancesegmentationinsarimages AT zhenweishi synergisticattentionforshipinstancesegmentationinsarimages
_version_	1718431652896571392

Synergistic Attention for Ship Instance Segmentation in SAR Images

Ejemplares similares