BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images

Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhongzhen Sun, Xiangguang Leng, Yu Lei, Boli Xiong, Kefeng Ji, Gangyao Kuang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	bi-directional feature fusion angular classification arbitrary-oriented ship detection high-resolution (HR) synthetic aperture radar (SAR) Science Q
Acceso en línea:	https://doaj.org/article/358571f5763145a193017d08c92a37de
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:358571f5763145a193017d08c92a37de
record_format	dspace
spelling	oai:doaj.org-article:358571f5763145a193017d08c92a37de2021-11-11T18:50:07ZBiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images10.3390/rs132142092072-4292https://doaj.org/article/358571f5763145a193017d08c92a37de2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4209https://doaj.org/toc/2072-4292Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and dense arrangement, posing enormous challenges to detect ships quickly and accurately. To address these issues above, a novel YOLO-based arbitrary-oriented SAR ship detector using bi-directional feature fusion and angular classification (BiFA-YOLO) is proposed in this article. First of all, a novel bi-directional feature fusion module (Bi-DFFM) tailored to SAR ship detection is applied to the YOLO framework. This module can efficiently aggregate multi-scale features through bi-directional (top-down and bottom-up) information interaction, which is helpful for detecting multi-scale ships. Secondly, to effectively detect arbitrary-oriented and densely arranged ships in HR SAR images, we add an angular classification structure to the head network. This structure is conducive to accurately obtaining ships’ angle information without the problem of boundary discontinuity and complicated parameter regression. Meanwhile, in BiFA-YOLO, a random rotation mosaic data augmentation method is employed to suppress the impact of angle imbalance. Compared with other conventional data augmentation methods, the proposed method can better improve detection performance of arbitrary-oriented ships. Finally, we conduct extensive experiments on the SAR ship detection dataset (SSDD) and large-scene HR SAR images from GF-3 satellite to verify our method. The proposed method can reach the detection performance with precision = 94.85%, recall = 93.97%, average precision = 93.90%, and F1-score = 0.9441 on SSDD. The detection speed of our method is approximately 13.3 ms per 512 × 512 image. In addition, comparison experiments with other deep learning-based methods and verification experiments on large-scene HR SAR images demonstrate that our method shows strong robustness and adaptability.Zhongzhen SunXiangguang LengYu LeiBoli XiongKefeng JiGangyao KuangMDPI AGarticlebi-directional feature fusionangular classificationarbitrary-oriented ship detectionhigh-resolution (HR)synthetic aperture radar (SAR)ScienceQENRemote Sensing, Vol 13, Iss 4209, p 4209 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	bi-directional feature fusion angular classification arbitrary-oriented ship detection high-resolution (HR) synthetic aperture radar (SAR) Science Q
spellingShingle	bi-directional feature fusion angular classification arbitrary-oriented ship detection high-resolution (HR) synthetic aperture radar (SAR) Science Q Zhongzhen Sun Xiangguang Leng Yu Lei Boli Xiong Kefeng Ji Gangyao Kuang BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
description	Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and dense arrangement, posing enormous challenges to detect ships quickly and accurately. To address these issues above, a novel YOLO-based arbitrary-oriented SAR ship detector using bi-directional feature fusion and angular classification (BiFA-YOLO) is proposed in this article. First of all, a novel bi-directional feature fusion module (Bi-DFFM) tailored to SAR ship detection is applied to the YOLO framework. This module can efficiently aggregate multi-scale features through bi-directional (top-down and bottom-up) information interaction, which is helpful for detecting multi-scale ships. Secondly, to effectively detect arbitrary-oriented and densely arranged ships in HR SAR images, we add an angular classification structure to the head network. This structure is conducive to accurately obtaining ships’ angle information without the problem of boundary discontinuity and complicated parameter regression. Meanwhile, in BiFA-YOLO, a random rotation mosaic data augmentation method is employed to suppress the impact of angle imbalance. Compared with other conventional data augmentation methods, the proposed method can better improve detection performance of arbitrary-oriented ships. Finally, we conduct extensive experiments on the SAR ship detection dataset (SSDD) and large-scene HR SAR images from GF-3 satellite to verify our method. The proposed method can reach the detection performance with precision = 94.85%, recall = 93.97%, average precision = 93.90%, and F1-score = 0.9441 on SSDD. The detection speed of our method is approximately 13.3 ms per 512 × 512 image. In addition, comparison experiments with other deep learning-based methods and verification experiments on large-scene HR SAR images demonstrate that our method shows strong robustness and adaptability.
format	article
author	Zhongzhen Sun Xiangguang Leng Yu Lei Boli Xiong Kefeng Ji Gangyao Kuang
author_facet	Zhongzhen Sun Xiangguang Leng Yu Lei Boli Xiong Kefeng Ji Gangyao Kuang
author_sort	Zhongzhen Sun
title	BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
title_short	BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
title_full	BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
title_fullStr	BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
title_full_unstemmed	BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images
title_sort	bifa-yolo: a novel yolo-based method for arbitrary-oriented ship detection in high-resolution sar images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/358571f5763145a193017d08c92a37de
work_keys_str_mv	AT zhongzhensun bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages AT xiangguangleng bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages AT yulei bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages AT bolixiong bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages AT kefengji bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages AT gangyaokuang bifayoloanovelyolobasedmethodforarbitraryorientedshipdetectioninhighresolutionsarimages
_version_	1718431694626750464

BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images

Ejemplares similares