Ship detection in optical remote sensing images plays a significant role in a wide range of civilian and military tasks. However, it is still a challenging issue owing to complex environmental interferences and a large variety of target scales and positions. To overcome these limitations, we propose a supervised multi-scale attention-guided detection framework, which can effectively detect ships of different scales both in complex pure ocean and port scenes. Specifically, a multi-scale supervision module is first proposed to adjust the semantic consistency of different feature levels, obtaining extracted features with small semantic gaps. Next, an attention-guided module is used to aggregate context information from both the spatial and channel dimensions by calculating map correlations, adaptively enhancing the feature representation. Moreover, to preserve the attribute and spatial relationship of the optimized features, we adopt a capsule-based module as the classifier and obtain satisfactory classification performance. Experimental results conducted on two public high-quality datasets demonstrate that the proposed method obtains state-of-the-art performance in comparison with several advanced methods.

Supervised Multi-Scale Attention-Guided Ship Detection in Optical Remote Sensing Images / Hu, Jianming; Zhi, Xiyang; Jiang, Shikai; Tang, Hao; Zhang, Wei; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 60:(2022), pp. 563051401-563051414. [10.1109/TGRS.2022.3206306]

Supervised Multi-Scale Attention-Guided Ship Detection in Optical Remote Sensing Images

Tang, Hao;Bruzzone, Lorenzo
2022-01-01

Abstract

Ship detection in optical remote sensing images plays a significant role in a wide range of civilian and military tasks. However, it is still a challenging issue owing to complex environmental interferences and a large variety of target scales and positions. To overcome these limitations, we propose a supervised multi-scale attention-guided detection framework, which can effectively detect ships of different scales both in complex pure ocean and port scenes. Specifically, a multi-scale supervision module is first proposed to adjust the semantic consistency of different feature levels, obtaining extracted features with small semantic gaps. Next, an attention-guided module is used to aggregate context information from both the spatial and channel dimensions by calculating map correlations, adaptively enhancing the feature representation. Moreover, to preserve the attribute and spatial relationship of the optimized features, we adopt a capsule-based module as the classifier and obtain satisfactory classification performance. Experimental results conducted on two public high-quality datasets demonstrate that the proposed method obtains state-of-the-art performance in comparison with several advanced methods.
2022
Hu, Jianming; Zhi, Xiyang; Jiang, Shikai; Tang, Hao; Zhang, Wei; Bruzzone, Lorenzo
Supervised Multi-Scale Attention-Guided Ship Detection in Optical Remote Sensing Images / Hu, Jianming; Zhi, Xiyang; Jiang, Shikai; Tang, Hao; Zhang, Wei; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 60:(2022), pp. 563051401-563051414. [10.1109/TGRS.2022.3206306]
File in questo prodotto:
File Dimensione Formato  
Pre-print-TGRS3206306.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.03 MB
Formato Adobe PDF
3.03 MB Adobe PDF Visualizza/Apri
Supervised_Multi-Scale_Attention-Guided_Ship_Detection_in_Optical_Remote_Sensing_Images.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.98 MB
Formato Adobe PDF
4.98 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/401496
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 9
  • OpenAlex ND
social impact