Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Rapid and accurate detection of maritime military targets is of great significance for maintaining national defense security. Few studies have used high-resolution optical images for the detailed classification of maritime military targets. This article, inspired by EfficientDet trackers, presents a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng Qin, Yulin Cai, Jia Liu, Puran Fan, Menghao Sun
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Attention mechanism data enhancement efficientdet network feature extraction feature fusion military target detection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/45faa9b0bbdb4011b8a10db895b96909
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:45faa9b0bbdb4011b8a10db895b96909
record_format	dspace
spelling	oai:doaj.org-article:45faa9b0bbdb4011b8a10db895b969092021-11-18T00:00:15ZMultilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images2151-153510.1109/JSTARS.2021.3123080https://doaj.org/article/45faa9b0bbdb4011b8a10db895b969092021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9591290/https://doaj.org/toc/2151-1535Rapid and accurate detection of maritime military targets is of great significance for maintaining national defense security. Few studies have used high-resolution optical images for the detailed classification of maritime military targets. This article, inspired by EfficientDet trackers, presents a method to classify military targets on the sea from high-resolution optical remote sensing images. In the first stage, a multilayer feature extraction network is constructed to extract various features. At the same time, residual connection and dilation convolution are introduced to prevent the deep network features from disappearing. Moreover, we use multilevel attention mechanism approaches to make more effective use of multilayer features. ReLU is introduced to replace the original swish activation function to reduce the computational cost in the pretreatment stage. After this, deep feature fusion networks and prediction networks are constructed to locate and distinguish different types of ships. Different types of ships use different degrees of data expansion methods to solve the problem of sample shortage and imbalance. The multiclassification method is used to solve low classification accuracy caused by little difference between civil and military ships. Experimental results suggested that the proposed method can accurately identify multiple types of military ships.Peng QinYulin CaiJia LiuPuran FanMenghao SunIEEEarticleAttention mechanismdata enhancementefficientdet networkfeature extractionfeature fusionmilitary target detectionOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11058-11069 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Attention mechanism data enhancement efficientdet network feature extraction feature fusion military target detection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Attention mechanism data enhancement efficientdet network feature extraction feature fusion military target detection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Peng Qin Yulin Cai Jia Liu Puran Fan Menghao Sun Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
description	Rapid and accurate detection of maritime military targets is of great significance for maintaining national defense security. Few studies have used high-resolution optical images for the detailed classification of maritime military targets. This article, inspired by EfficientDet trackers, presents a method to classify military targets on the sea from high-resolution optical remote sensing images. In the first stage, a multilayer feature extraction network is constructed to extract various features. At the same time, residual connection and dilation convolution are introduced to prevent the deep network features from disappearing. Moreover, we use multilevel attention mechanism approaches to make more effective use of multilayer features. ReLU is introduced to replace the original swish activation function to reduce the computational cost in the pretreatment stage. After this, deep feature fusion networks and prediction networks are constructed to locate and distinguish different types of ships. Different types of ships use different degrees of data expansion methods to solve the problem of sample shortage and imbalance. The multiclassification method is used to solve low classification accuracy caused by little difference between civil and military ships. Experimental results suggested that the proposed method can accurately identify multiple types of military ships.
format	article
author	Peng Qin Yulin Cai Jia Liu Puran Fan Menghao Sun
author_facet	Peng Qin Yulin Cai Jia Liu Puran Fan Menghao Sun
author_sort	Peng Qin
title	Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
title_short	Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
title_full	Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
title_fullStr	Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
title_full_unstemmed	Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images
title_sort	multilayer feature extraction network for military ship detection from high-resolution optical remote sensing images
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/45faa9b0bbdb4011b8a10db895b96909
work_keys_str_mv	AT pengqin multilayerfeatureextractionnetworkformilitaryshipdetectionfromhighresolutionopticalremotesensingimages AT yulincai multilayerfeatureextractionnetworkformilitaryshipdetectionfromhighresolutionopticalremotesensingimages AT jialiu multilayerfeatureextractionnetworkformilitaryshipdetectionfromhighresolutionopticalremotesensingimages AT puranfan multilayerfeatureextractionnetworkformilitaryshipdetectionfromhighresolutionopticalremotesensingimages AT menghaosun multilayerfeatureextractionnetworkformilitaryshipdetectionfromhighresolutionopticalremotesensingimages
_version_	1718425222027149312

Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Ejemplares similares