Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network

Moy de Vitry, Matthew; Kramer, Simon; Wegner, Jan Dirk; Leitão, João P.

doi:https://doi.org/10.5194/hess-23-4621-2019

Articles | Volume 23, issue 11

https://doi.org/10.5194/hess-23-4621-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-23-4621-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 23, issue 11

Research article

|

15 Nov 2019

Research article |

| 15 Nov 2019

Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network

Matthew Moy de Vitry, Simon Kramer, Jan Dirk Wegner, and João P. Leitão

Supplement

https://doi.org/10.5194/hess-23-4621-2019-supplement

Data sets

Data for: Scalable Flood Level Trend Monitoring with Surveillance Cameras using a Deep Convolutional Neural Network M. Moy de Vitry https://doi.org/10.25678/000150

Model code and software

Data for: Scalable Flood Level Trend Monitoring with Surveillance Cameras using a Deep Convolutional Neural Network M. Moy de Vitry https://doi.org/10.25678/000150

Video supplement

Water level trend monitoring with a surveillance camera using a deep convolutional neural network M. Moy de Vitry and S. Kramer https://doi.org/10.5446/43637

Short summary

This work demonstrates a new approach to obtain flood level trend information from surveillance footage with minimal prior information. A neural network trained to detect flood water is applied to video frames to create a qualitative flooding metric (namely, SOFI). The correlation between the real water trend and SOFI was found to be 75 % on average (based on six videos of flooding under various circumstances). SOFI could be used for flood model calibration, to increase model reliability.