A deep learning technique-based automatic monitoring method for experimental urban road inundation

Reports indicate that high-cost, insecurity, and difficulty in complex environments hinder the traditional urban road inundation monitoring approach. This work proposed an automatic monitoring method for experimental urban road inundation based on the YOLOv2 deep learning framework. The proposed met...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hao Han, Jingming Hou, Ganggang Bai, Bingyao Li, Tian Wang, Xuan Li, Xujun Gao, Feng Su, Zhaofeng Wang, Qiuhua Liang, Jiahui Gong
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	deep learning technique experimental urban road inundation inundation area yolov2 model Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/5d590c7ea31d433e84cc85b3ed3e699d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5d590c7ea31d433e84cc85b3ed3e699d
record_format	dspace
spelling	oai:doaj.org-article:5d590c7ea31d433e84cc85b3ed3e699d2021-11-05T17:48:53ZA deep learning technique-based automatic monitoring method for experimental urban road inundation1464-71411465-173410.2166/hydro.2021.156https://doaj.org/article/5d590c7ea31d433e84cc85b3ed3e699d2021-07-01T00:00:00Zhttp://jh.iwaponline.com/content/23/4/764https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734Reports indicate that high-cost, insecurity, and difficulty in complex environments hinder the traditional urban road inundation monitoring approach. This work proposed an automatic monitoring method for experimental urban road inundation based on the YOLOv2 deep learning framework. The proposed method is an affordable, secure, with high accuracy rates in urban road inundation evaluation. The automatic detection of experimental urban road inundation was carried out under both dry and wet conditions on roads in the study area with a scale of a few m2. The validation average accuracy rate of the model was high with 90.1% inundation detection, while its training average accuracy rate was 96.1%. This indicated that the model has effective performance with high detection accuracy and recognition ability. Besides, the inundated water area of the experimental inundation region and the real road inundation region in the images was computed, showing that the relative errors of the measured area and the computed area were less than 20%. The results indicated that the proposed method can provide reliable inundation area evaluation. Therefore, our findings provide an effective guide in the management of urban floods and urban flood-warning, as well as systematic validation data for hydrologic and hydrodynamic models. HIGHLIGHTS First experimental urban road inundation automatic detection study using YOLOv2.; Proposed an inundation area computation method based on a deep learning technique.; Good performance on an experimental urban road inundation detection was tested.;Hao HanJingming HouGanggang BaiBingyao LiTian WangXuan LiXujun GaoFeng SuZhaofeng WangQiuhua LiangJiahui GongIWA Publishingarticledeep learning techniqueexperimental urban road inundationinundation areayolov2 modelInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 4, Pp 764-781 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning technique experimental urban road inundation inundation area yolov2 model Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
spellingShingle	deep learning technique experimental urban road inundation inundation area yolov2 model Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 Hao Han Jingming Hou Ganggang Bai Bingyao Li Tian Wang Xuan Li Xujun Gao Feng Su Zhaofeng Wang Qiuhua Liang Jiahui Gong A deep learning technique-based automatic monitoring method for experimental urban road inundation
description	Reports indicate that high-cost, insecurity, and difficulty in complex environments hinder the traditional urban road inundation monitoring approach. This work proposed an automatic monitoring method for experimental urban road inundation based on the YOLOv2 deep learning framework. The proposed method is an affordable, secure, with high accuracy rates in urban road inundation evaluation. The automatic detection of experimental urban road inundation was carried out under both dry and wet conditions on roads in the study area with a scale of a few m2. The validation average accuracy rate of the model was high with 90.1% inundation detection, while its training average accuracy rate was 96.1%. This indicated that the model has effective performance with high detection accuracy and recognition ability. Besides, the inundated water area of the experimental inundation region and the real road inundation region in the images was computed, showing that the relative errors of the measured area and the computed area were less than 20%. The results indicated that the proposed method can provide reliable inundation area evaluation. Therefore, our findings provide an effective guide in the management of urban floods and urban flood-warning, as well as systematic validation data for hydrologic and hydrodynamic models. HIGHLIGHTS First experimental urban road inundation automatic detection study using YOLOv2.; Proposed an inundation area computation method based on a deep learning technique.; Good performance on an experimental urban road inundation detection was tested.;
format	article
author	Hao Han Jingming Hou Ganggang Bai Bingyao Li Tian Wang Xuan Li Xujun Gao Feng Su Zhaofeng Wang Qiuhua Liang Jiahui Gong
author_facet	Hao Han Jingming Hou Ganggang Bai Bingyao Li Tian Wang Xuan Li Xujun Gao Feng Su Zhaofeng Wang Qiuhua Liang Jiahui Gong
author_sort	Hao Han
title	A deep learning technique-based automatic monitoring method for experimental urban road inundation
title_short	A deep learning technique-based automatic monitoring method for experimental urban road inundation
title_full	A deep learning technique-based automatic monitoring method for experimental urban road inundation
title_fullStr	A deep learning technique-based automatic monitoring method for experimental urban road inundation
title_full_unstemmed	A deep learning technique-based automatic monitoring method for experimental urban road inundation
title_sort	deep learning technique-based automatic monitoring method for experimental urban road inundation
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/5d590c7ea31d433e84cc85b3ed3e699d
work_keys_str_mv	AT haohan adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT jingminghou adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT ganggangbai adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT bingyaoli adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT tianwang adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT xuanli adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT xujungao adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT fengsu adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT zhaofengwang adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT qiuhualiang adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT jiahuigong adeeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT haohan deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT jingminghou deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT ganggangbai deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT bingyaoli deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT tianwang deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT xuanli deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT xujungao deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT fengsu deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT zhaofengwang deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT qiuhualiang deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation AT jiahuigong deeplearningtechniquebasedautomaticmonitoringmethodforexperimentalurbanroadinundation
_version_	1718444102888980480

A deep learning technique-based automatic monitoring method for experimental urban road inundation

Ejemplares similares