气候变化领域集成服务门户(CCPortal): Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network

CCPortal

DOI	10.5194/hess-23-4621-2019
	Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network
	Moy De Vitry M.; Kramer S.; Dirk Wegner J.; Leitao J.P.
发表日期	2019
ISSN	1027-5606
起始页码	4621
结束页码	4634
卷号	23 期号:11
英文摘要	In many countries, urban flooding due to local, intense rainfall is expected to become more frequent because of climate change and urbanization. Cities trying to adapt to this growing risk are challenged by a chronic lack of surface flooding data that are needed for flood risk assessment and planning. In this work, we propose a new approach that exploits existing surveillance camera systems to provide qualitative flood level trend information at scale. The approach uses a deep convolutional neural network (DCNN) to detect floodwater in surveillance footage and a novel qualitative flood index (namely, the static observer flooding index - SOFI) as a proxy for water level fluctuations visible from a surveillance camera's viewpoint. To demonstrate the approach, we trained the DCNN on 1218 flooding images collected from the Internet and applied it to six surveillance videos representing different flooding and lighting conditions. The SOFI signal obtained from the videos had a 75 % correlation to the actual water level fluctuation on average. By retraining the DCNN with a few frames from a given video, the correlation is increased to 85 % on average. The results confirm that the approach is versatile, with the potential to be applied to a variety of surveillance camera models and flooding situations without the need for on-site camera calibration. Thanks to this flexibility, this approach could be a cheap and highly scalable alternative to conventional sensing methods.. © 2019 All rights reserved.
语种	英语
scopus关键词	Cameras; Climate change; Convolution; Deep neural networks; Monitoring; Network security; Neural networks; Risk assessment; Security systems; Water levels; Camera calibration; Convolutional neural network; Flood risk assessments; Intense rainfalls; Lighting conditions; Surveillance cameras; Surveillance video; Water-level fluctuation; Floods; artificial neural network; climate change; flood; flood control; flooding; rainfall; risk assessment; urban area; water level
来源期刊	Hydrology and Earth System Sciences
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/159568
作者单位	Moy De Vitry, M., Department of Urban Water Management, Eawag - Swiss Federal Institute of Aquatic Science and Technology, Dübendorf, 8600, Switzerland, Institute of Environmental Engineering, ETH Zurich, Zürich, 8093, Switzerland; Kramer, S., Institute of Environmental Engineering, ETH Zurich, Zürich, 8093, Switzerland; Dirk Wegner, J., EcoVision Lab, Photogrammetry and Remote Sensing Group, ETH Zurich, Zürich, 8093, Switzerland; Leitao, J.P., Department of Urban Water Management, Eawag - Swiss Federal Institute of Aquatic Science and Technology, Dübendorf, 8600, Switzerland
推荐引用方式 GB/T 7714	Moy De Vitry M.,Kramer S.,Dirk Wegner J.,et al. Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network[J],2019,23(11).
APA	Moy De Vitry M.,Kramer S.,Dirk Wegner J.,&Leitao J.P..(2019).Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network.Hydrology and Earth System Sciences,23(11).
MLA	Moy De Vitry M.,et al."Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network".Hydrology and Earth System Sciences 23.11(2019).