Abstract

Flood depth monitoring is crucial for flood warning systems and damage control, especially in the event of an urban flood. Existing gauge station data and remote sensing data still has limited spatial and temporal resolution and coverage. Therefore, to expand flood depth data source taking use of online image resources in an efficient manner, an automated, low-cost, and real-time working frame called FloodMask was developed to obtain flood depth from online images containing flooded traffic signs. The method was built on the deep learning framework of Mask R-CNN (regional convolutional neural network), trained by collected and manually annotated traffic sign images. Following further the proposed image processing frame, flood depth data were retrieved more efficiently than manual estimations. As the main results, the flood depth estimates from images (without any mirror reflection and other inference problems) have an average error of 0.11 m, when compared to human visual inspection measurements. This developed method can be further coupled with street CCTV cameras, social media photos, and on-board vehicle cameras to facilitate the development of a smart city with a prompt and efficient flood monitoring system. In future studies, distortion and mirror reflection should be tackled properly to increase the quality of the flood depth estimates.

Highlights

  • Why do we assume that the images we use only contain signs that stand still? In this study, we focus on the basic feasibility of the method and its possibility to produce flood depth data, which means extreme cases of flood events occurring in urban areas are not considered

  • No such quantitative method was proposed for the collection of flood depth data

  • One of the strengths of this study is that it represents an investigation of the potential to apply machine learning algorithms and computer vision in the field of hydrological data acquisition

Read more

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Flood is a natural disaster that brings major loss to human society and the environment [1]. Various flood models have been established for flood monitoring and forecasting [2,3,4]. The state of art of hydrological modeling is that no existing model can forecasts flash flood in a reliable way [2]. Due to the requirement of large data input for models and booming data collection approaches, more efficient and automated data processing ways are in demand. Sophisticated large-scale analysis of flooding has been established by the existing precipitation forecast systems, but an accurate and instant platform is in demand for subdivision river areas [5,6]

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.