Journal cover Journal topic
Hydrology and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.256 IF 4.256
  • IF 5-year value: 4.819 IF 5-year
    4.819
  • CiteScore value: 4.10 CiteScore
    4.10
  • SNIP value: 1.412 SNIP 1.412
  • SJR value: 2.023 SJR 2.023
  • IPP value: 3.97 IPP 3.97
  • h5-index value: 58 h5-index 58
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 99 Scimago H
    index 99
Discussion papers
https://doi.org/10.5194/hess-2018-570
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-2018-570
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 15 Feb 2019

Research article | 15 Feb 2019

Review status
This discussion paper is a preprint. A revision of the manuscript is under review for the journal Hydrology and Earth System Sciences (HESS).

Scalable Flood Level Trend Monitoring with Surveillance Cameras using a Deep Convolutional Neural Network

Matthew Moy de Vitry1,2, Simon Kramer2, Jan Dirk Wegner2, and João P. Leitão1 Matthew Moy de Vitry et al.
  • 1Eawag: Swiss Federal Institute of Aquatic Science and Technology, Überlandstrasse 133, 8600 Dübendorf, Switzerland
  • 2ETHZ: Swiss Federal Institute of Technology Zurich, Wolfgang-Pauli-Strasse 15, 8093 Zurich, Switzerland

Abstract. 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 is 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 (SOFI) as a proxy for water level fluctuations visible from a surveillance camera’s viewpoint. To demonstrate the approach, we trained the DCNN on 1281 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 on average a 75 % correlation to the actual water level fluctuation. By retraining the DCNN with a few frames from a given video, performance for that video is further increased to 85 %. The results suggest that the approach can be used with almost any surveillance footage without the need for on-site camera calibration, making it cheap, highly scalable, and retroactively applicable to archived surveillance footage.

Matthew Moy de Vitry et al.
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for Authors/Editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Matthew Moy de Vitry et al.
Matthew Moy de Vitry et al.
Viewed  
Total article views: 307 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
229 76 2 307 3 6
  • HTML: 229
  • PDF: 76
  • XML: 2
  • Total: 307
  • BibTeX: 3
  • EndNote: 6
Views and downloads (calculated since 15 Feb 2019)
Cumulative views and downloads (calculated since 15 Feb 2019)
Viewed (geographical distribution)  
Total article views: 249 (including HTML, PDF, and XML) Thereof 249 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 21 May 2019
Publications Copernicus
Download
Short summary
This work demonstrates a new approach to provide flood level trend information at scale by leveraging surveillance cameras. A deep convolutional neural network (DCNN) trained on images from news websites is used to measure flooding qualitatively. Evaluated on six surveillance videos of differing quality, the correlation between real and predicted water trend was found to be 75 % on average. If the DCNN is retrained with a few of the video frames, the average correlation is increased to 85 %.
This work demonstrates a new approach to provide flood level trend information at scale by...
Citation