Ship target detection of unmanned surface vehicle base on efficientdet

The autonomous navigation of unmanned surface vehicles (USV) depends mainly on effective ship target detection to the nearby water area. The difficulty of target detection for USV derives from the complexity of the external environment, such as the light reflection and the cloud or mist shield. Acco...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ronghui Li, Jinshan Wu, Liang Cao
Formato:	article
Lenguaje:	EN
Publicado:	Taylor & Francis Group 2021
Materias:	unmanned surface vehicle(usv) efficientdet target detection group normalization(gn) Control engineering systems. Automatic machinery (General) TJ212-225 Systems engineering TA168
Acceso en línea:	https://doaj.org/article/71901f79b4ce43dc8edef26aa8e1393d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:71901f79b4ce43dc8edef26aa8e1393d
record_format	dspace
spelling	oai:doaj.org-article:71901f79b4ce43dc8edef26aa8e1393d2021-11-04T15:51:53ZShip target detection of unmanned surface vehicle base on efficientdet2164-258310.1080/21642583.2021.1990159https://doaj.org/article/71901f79b4ce43dc8edef26aa8e1393d2021-10-01T00:00:00Zhttp://dx.doi.org/10.1080/21642583.2021.1990159https://doaj.org/toc/2164-2583The autonomous navigation of unmanned surface vehicles (USV) depends mainly on effective ship target detection to the nearby water area. The difficulty of target detection for USV derives from the complexity of the external environment, such as the light reflection and the cloud or mist shield. Accordingly, this paper proposes a target detection technology for USV on the basis of the EfficientDet algorithm. The ship features fusion is performed by Bi-directional Feature Pyra-mid Network (BiFPN), in which the pre-trained EfficientNet via ImageNet is taken as the backbone network, then the detection speed is increased by group normalization. Compared with the Faster-RCNN and Yolo V3, the ship target detection accuracy is greatly improved to 87.5% in complex environments. The algorithm can be applied to the identification of dynamic targets on the sea, which provides a key reference for the autonomous navigation of USV and the military threats assessment on the sea surface.Ronghui LiJinshan WuLiang CaoTaylor & Francis Grouparticleunmanned surface vehicle(usv)efficientdettarget detectiongroup normalization(gn)Control engineering systems. Automatic machinery (General)TJ212-225Systems engineeringTA168ENSystems Science & Control Engineering, Vol 0, Iss 0, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	unmanned surface vehicle(usv) efficientdet target detection group normalization(gn) Control engineering systems. Automatic machinery (General) TJ212-225 Systems engineering TA168
spellingShingle	unmanned surface vehicle(usv) efficientdet target detection group normalization(gn) Control engineering systems. Automatic machinery (General) TJ212-225 Systems engineering TA168 Ronghui Li Jinshan Wu Liang Cao Ship target detection of unmanned surface vehicle base on efficientdet
description	The autonomous navigation of unmanned surface vehicles (USV) depends mainly on effective ship target detection to the nearby water area. The difficulty of target detection for USV derives from the complexity of the external environment, such as the light reflection and the cloud or mist shield. Accordingly, this paper proposes a target detection technology for USV on the basis of the EfficientDet algorithm. The ship features fusion is performed by Bi-directional Feature Pyra-mid Network (BiFPN), in which the pre-trained EfficientNet via ImageNet is taken as the backbone network, then the detection speed is increased by group normalization. Compared with the Faster-RCNN and Yolo V3, the ship target detection accuracy is greatly improved to 87.5% in complex environments. The algorithm can be applied to the identification of dynamic targets on the sea, which provides a key reference for the autonomous navigation of USV and the military threats assessment on the sea surface.
format	article
author	Ronghui Li Jinshan Wu Liang Cao
author_facet	Ronghui Li Jinshan Wu Liang Cao
author_sort	Ronghui Li
title	Ship target detection of unmanned surface vehicle base on efficientdet
title_short	Ship target detection of unmanned surface vehicle base on efficientdet
title_full	Ship target detection of unmanned surface vehicle base on efficientdet
title_fullStr	Ship target detection of unmanned surface vehicle base on efficientdet
title_full_unstemmed	Ship target detection of unmanned surface vehicle base on efficientdet
title_sort	ship target detection of unmanned surface vehicle base on efficientdet
publisher	Taylor & Francis Group
publishDate	2021
url	https://doaj.org/article/71901f79b4ce43dc8edef26aa8e1393d
work_keys_str_mv	AT ronghuili shiptargetdetectionofunmannedsurfacevehiclebaseonefficientdet AT jinshanwu shiptargetdetectionofunmannedsurfacevehiclebaseonefficientdet AT liangcao shiptargetdetectionofunmannedsurfacevehiclebaseonefficientdet
_version_	1718444719647752192

Ship target detection of unmanned surface vehicle base on efficientdet

Ejemplares similares