摘要
Urban flooding is becoming a common and devastating hazard,which causes life loss and economic damage.Monitoring and understanding urban flooding in a highly localized scale is a challenging task due to the complicated urban landscape,intri-cate hydraulic process,and the lack of high-quality and resolution data.The emerging smart city technology such as monitoring cameras provides an unprecedented opportunity to address the data issue.However,estimating water ponding extents on land surfaces based on monitoring footage is unreliable using the tradi-tional segmentation technique because the boundary of the water ponding,under the influence of varying weather,background,and ilumination,is usually too fuzzy to identify,and the oblique angle and image distortion in the video monitoring data prevents geor-eferencing and object-based measurements.This paper presents a novel semi-supervised segmentation scheme for surface water extent recognition from the footage of an oblique monitoring camera.The semi-supervised segmentation algorithm was found suitable to determine the water boundary and the monoplotting method was successfully applied to georeference the pixels of the monitoring video for the virtual quantification of the local drainage process.The correlation and mechanism-based analysis demon-strate the value of the proposed method in advancing the under-standing of local drainage hydraulics.The workflow and created methods in this study have a great potential to study other street-level and earth surface processes.
基金
supported by the U.s.Department of Transportation,Offce of the Assistant Secretary for Research and Technology(OST-R),Grant No.69A3551847102
issued to Rutgers,The State University of New Jersey.The authors thank the kind support of Dr.Ting Wang from the NEC Labs in this work.
作者简介
CONTACT:Ruo-Qian Wang,Ph.D.,is an Assistant Professor at the Department of Civil and Environmental Engineering,Rutgers University.Prior to joining Rutgers University,he worked as a Lecturer at the University of Dundee,UK.He received his Ph.D.degree in Environmental Fluid Mechanics from Massachusetts Institute of Technology in 2014,his M.S.degree from Singapore Stanford Partnership,and his B.S.degree from Beihang University.He has conducted Postdoctoral research at MIT and University of California Berkeley during 2014 to 2017.Dr.Wang's research group focuses on developing numerical models to connect big data and decision-making in civil and environmental engineering systems rq.wang@rutgers.edu,Department of Civil and Environmental Engineering,Rutgers,The State University of New Jersey RWH 328E,500 Bartholomew Road,Piscataway,NJ,USA.ORCID:http://orcid.org/0000-0003-2052-8948;Yangmin Ding,Ph.D.,is a Researcher in the Department of Optical Networking&Sensing at NEC Labs America,Inc.He received his bachelor's degree in Civil Engineering from Changsha University of Science and Technology,his master's degree in Highway and Railway Engineering from Southeast University,and a Ph.D.degree in Civil and Environmental Engineering from Rutgers,the State University of New Jersey.His current research interests include dynamics and vibration,structural health monitoring,distributed fiber optic sensing,and machine learning.
