Cargando…

Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task

The real-time performance of ship detection is an important index in the marine remote sensing detection task. Due to the computing resources on the satellite being limited by the solar array size and the radiation-resistant electronic components, information extraction tasks are usually implemented...

Descripción completa

Detalles Bibliográficos
Autores principales: Xie, Fang, Lin, Baojun, Liu, Yingchun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9102707/
https://www.ncbi.nlm.nih.gov/pubmed/35591063
http://dx.doi.org/10.3390/s22093370
_version_ 1784707392043220992
author Xie, Fang
Lin, Baojun
Liu, Yingchun
author_facet Xie, Fang
Lin, Baojun
Liu, Yingchun
author_sort Xie, Fang
collection PubMed
description The real-time performance of ship detection is an important index in the marine remote sensing detection task. Due to the computing resources on the satellite being limited by the solar array size and the radiation-resistant electronic components, information extraction tasks are usually implemented after the image is transmitted to the ground. However, in recent years, the one-stage based target detector such as the You Only Look Once Version 5 (YOLOv5) deep learning framework shows powerful performance while being lightweight, and it provides an implementation scheme for on-orbit reasoning to shorten the time delay of ship detention. Optimizing the lightweight model has important research significance for SAR image onboard processing. In this paper, we studied the fusion problem of two lightweight models which are the Coordinate Attention (CA) mechanism module and the YOLOv5 detector. We propose a novel lightweight end-to-end object detection framework fused with a CA module in the backbone of a suitable position: YOLO Coordinate Attention SAR Ship (YOLO-CASS), for the SAR ship target detection task. The experimental results on the SSDD synthetic aperture radar (SAR) remote sensing imagery indicate that our method shows significant gains in both efficiency and performance, and it has the potential to be developed into onboard processing in the SAR satellite platform. The techniques we explored provide a solution to improve the performance of the lightweight deep learning-based object detection framework.
format Online
Article
Text
id pubmed-9102707
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91027072022-05-14 Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task Xie, Fang Lin, Baojun Liu, Yingchun Sensors (Basel) Article The real-time performance of ship detection is an important index in the marine remote sensing detection task. Due to the computing resources on the satellite being limited by the solar array size and the radiation-resistant electronic components, information extraction tasks are usually implemented after the image is transmitted to the ground. However, in recent years, the one-stage based target detector such as the You Only Look Once Version 5 (YOLOv5) deep learning framework shows powerful performance while being lightweight, and it provides an implementation scheme for on-orbit reasoning to shorten the time delay of ship detention. Optimizing the lightweight model has important research significance for SAR image onboard processing. In this paper, we studied the fusion problem of two lightweight models which are the Coordinate Attention (CA) mechanism module and the YOLOv5 detector. We propose a novel lightweight end-to-end object detection framework fused with a CA module in the backbone of a suitable position: YOLO Coordinate Attention SAR Ship (YOLO-CASS), for the SAR ship target detection task. The experimental results on the SSDD synthetic aperture radar (SAR) remote sensing imagery indicate that our method shows significant gains in both efficiency and performance, and it has the potential to be developed into onboard processing in the SAR satellite platform. The techniques we explored provide a solution to improve the performance of the lightweight deep learning-based object detection framework. MDPI 2022-04-28 /pmc/articles/PMC9102707/ /pubmed/35591063 http://dx.doi.org/10.3390/s22093370 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
Xie, Fang
Lin, Baojun
Liu, Yingchun
Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title_full Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title_fullStr Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title_full_unstemmed Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title_short Research on the Coordinate Attention Mechanism Fuse in a YOLOv5 Deep Learning Detector for the SAR Ship Detection Task
title_sort research on the coordinate attention mechanism fuse in a yolov5 deep learning detector for the sar ship detection task
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9102707/
https://www.ncbi.nlm.nih.gov/pubmed/35591063
http://dx.doi.org/10.3390/s22093370
work_keys_str_mv AT xiefang researchonthecoordinateattentionmechanismfuseinayolov5deeplearningdetectorforthesarshipdetectiontask
AT linbaojun researchonthecoordinateattentionmechanismfuseinayolov5deeplearningdetectorforthesarshipdetectiontask
AT liuyingchun researchonthecoordinateattentionmechanismfuseinayolov5deeplearningdetectorforthesarshipdetectiontask