Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery

Using high-resolution remote sensing images to automatically identify individual trees is of great significance to forestry ecological environment monitoring. Urban plantation has realistic demands for single tree management such as catkin pollution, maintenance of famous trees, landscape constructi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yueyuan Zheng, Gang Wu
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	single shot multibox detector Urban forest tree detection tree location high-resolution remote sensing image Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/6d5b8a7fd9ad4f61848794f0cd9a1f7c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6d5b8a7fd9ad4f61848794f0cd9a1f7c
record_format	dspace
spelling	oai:doaj.org-article:6d5b8a7fd9ad4f61848794f0cd9a1f7c2021-12-01T18:58:03ZSingle Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery2296-665X10.3389/fenvs.2021.755587https://doaj.org/article/6d5b8a7fd9ad4f61848794f0cd9a1f7c2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenvs.2021.755587/fullhttps://doaj.org/toc/2296-665XUsing high-resolution remote sensing images to automatically identify individual trees is of great significance to forestry ecological environment monitoring. Urban plantation has realistic demands for single tree management such as catkin pollution, maintenance of famous trees, landscape construction, and park management. At present, there are problems of missed detection and error detection in dense plantations and complex background plantations. This paper proposes a single tree detection method based on single shot multibox detector (SSD). Optimal SSD is obtained by adjusting feature layers, optimizing the aspect ratio of a preset box, reducing parameters and so on. The optimal SSD is applied to single tree detection and location in campuses, orchards, and economic plantations. The average accuracy based on SSD is 96.0, 92.9, and 97.6% in campus green trees, lychee plantations, and palm plantations, respectively. It is 11.3 and 37.5% higher than the latest template matching method and chan-vese (CV) model method, and is 43.1 and 54.2% higher than the traditional watershed method and local maximum method. Experimental results show that SSD has a strong potential and application advantage. This research has reference significance for the application of an object detection framework based on deep learning in agriculture and forestry.Yueyuan ZhengGang WuFrontiers Media S.A.articlesingle shot multibox detectorUrban foresttree detectiontree locationhigh-resolution remote sensing imageEnvironmental sciencesGE1-350ENFrontiers in Environmental Science, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	single shot multibox detector Urban forest tree detection tree location high-resolution remote sensing image Environmental sciences GE1-350
spellingShingle	single shot multibox detector Urban forest tree detection tree location high-resolution remote sensing image Environmental sciences GE1-350 Yueyuan Zheng Gang Wu Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
description	Using high-resolution remote sensing images to automatically identify individual trees is of great significance to forestry ecological environment monitoring. Urban plantation has realistic demands for single tree management such as catkin pollution, maintenance of famous trees, landscape construction, and park management. At present, there are problems of missed detection and error detection in dense plantations and complex background plantations. This paper proposes a single tree detection method based on single shot multibox detector (SSD). Optimal SSD is obtained by adjusting feature layers, optimizing the aspect ratio of a preset box, reducing parameters and so on. The optimal SSD is applied to single tree detection and location in campuses, orchards, and economic plantations. The average accuracy based on SSD is 96.0, 92.9, and 97.6% in campus green trees, lychee plantations, and palm plantations, respectively. It is 11.3 and 37.5% higher than the latest template matching method and chan-vese (CV) model method, and is 43.1 and 54.2% higher than the traditional watershed method and local maximum method. Experimental results show that SSD has a strong potential and application advantage. This research has reference significance for the application of an object detection framework based on deep learning in agriculture and forestry.
format	article
author	Yueyuan Zheng Gang Wu
author_facet	Yueyuan Zheng Gang Wu
author_sort	Yueyuan Zheng
title	Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
title_short	Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
title_full	Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
title_fullStr	Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
title_full_unstemmed	Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery
title_sort	single shot multibox detector for urban plantation single tree detection and location with high-resolution remote sensing imagery
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/6d5b8a7fd9ad4f61848794f0cd9a1f7c
work_keys_str_mv	AT yueyuanzheng singleshotmultiboxdetectorforurbanplantationsingletreedetectionandlocationwithhighresolutionremotesensingimagery AT gangwu singleshotmultiboxdetectorforurbanplantationsingletreedetectionandlocationwithhighresolutionremotesensingimagery
_version_	1718404635931181056

Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery

Ejemplares similares