Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection

Unmanned aerial vehicle (UAV) is one of the main means of information warfare, such as in battlefield cruises, reconnaissance, and military strikes. Rapid detection and accurate recognition of key targets in UAV images are the basis of subsequent military tasks. The UAV image has characteristics of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Long Sun, Jie Chen, Dazheng Feng, Mengdao Xing
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	drone video multi-target detection multiple focal lengths deep learning template matching Science Q
Acceso en línea:	https://doaj.org/article/d91d4eaeafc54342a916a15a32c57ee2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d91d4eaeafc54342a916a15a32c57ee2
record_format	dspace
spelling	oai:doaj.org-article:d91d4eaeafc54342a916a15a32c57ee22021-11-11T18:54:58ZParallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection10.3390/rs132143772072-4292https://doaj.org/article/d91d4eaeafc54342a916a15a32c57ee22021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4377https://doaj.org/toc/2072-4292Unmanned aerial vehicle (UAV) is one of the main means of information warfare, such as in battlefield cruises, reconnaissance, and military strikes. Rapid detection and accurate recognition of key targets in UAV images are the basis of subsequent military tasks. The UAV image has characteristics of high resolution and small target size, and in practical application, the detection speed is often required to be fast. Existing algorithms are not able to achieve an effective trade-off between detection accuracy and speed. Therefore, this paper proposes a parallel ensemble deep learning framework for unmanned aerial vehicle video multi-target detection, which is a global and local joint detection strategy. It combines a deep learning target detection algorithm with template matching to make full use of image information. It also integrates multi-process and multi-threading mechanisms to speed up processing. Experiments show that the system has high detection accuracy for targets with focal lengths varying from one to ten times. At the same time, the real-time and stable display of detection results is realized by aiming at the moving UAV video image.Long SunJie ChenDazheng FengMengdao XingMDPI AGarticledrone videomulti-target detectionmultiple focal lengthsdeep learningtemplate matchingScienceQENRemote Sensing, Vol 13, Iss 4377, p 4377 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	drone video multi-target detection multiple focal lengths deep learning template matching Science Q
spellingShingle	drone video multi-target detection multiple focal lengths deep learning template matching Science Q Long Sun Jie Chen Dazheng Feng Mengdao Xing Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
description	Unmanned aerial vehicle (UAV) is one of the main means of information warfare, such as in battlefield cruises, reconnaissance, and military strikes. Rapid detection and accurate recognition of key targets in UAV images are the basis of subsequent military tasks. The UAV image has characteristics of high resolution and small target size, and in practical application, the detection speed is often required to be fast. Existing algorithms are not able to achieve an effective trade-off between detection accuracy and speed. Therefore, this paper proposes a parallel ensemble deep learning framework for unmanned aerial vehicle video multi-target detection, which is a global and local joint detection strategy. It combines a deep learning target detection algorithm with template matching to make full use of image information. It also integrates multi-process and multi-threading mechanisms to speed up processing. Experiments show that the system has high detection accuracy for targets with focal lengths varying from one to ten times. At the same time, the real-time and stable display of detection results is realized by aiming at the moving UAV video image.
format	article
author	Long Sun Jie Chen Dazheng Feng Mengdao Xing
author_facet	Long Sun Jie Chen Dazheng Feng Mengdao Xing
author_sort	Long Sun
title	Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
title_short	Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
title_full	Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
title_fullStr	Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
title_full_unstemmed	Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection
title_sort	parallel ensemble deep learning for real-time remote sensing video multi-target detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d91d4eaeafc54342a916a15a32c57ee2
work_keys_str_mv	AT longsun parallelensembledeeplearningforrealtimeremotesensingvideomultitargetdetection AT jiechen parallelensembledeeplearningforrealtimeremotesensingvideomultitargetdetection AT dazhengfeng parallelensembledeeplearningforrealtimeremotesensingvideomultitargetdetection AT mengdaoxing parallelensembledeeplearningforrealtimeremotesensingvideomultitargetdetection
_version_	1718431674318979072

Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection

Ejemplares similares