A Novel Approach to Measuring Urban Waterlogging Depth from Images Based on Mask Region-Based Convolutional Neural Network

Quickly obtaining accurate waterlogging depth data is vital in urban flood events, especially for emergency response and risk mitigation. In this study, a novel approach to measure urban waterlogging depth was developed using images from social networks and traffic surveillance video systems. The Mask region-based convolutional neural network (Mask R-CNN) model was used to detect tires in waterlogging, which were considered to be reference objects. Then, waterlogging depth was calculated using the height differences method and Pythagorean theorem. The results show that tires detected from images can been used as an effective reference object to calculate waterlogging depth. The Pythagorean theorem method performs better on images from social networks, and the height differences method performs well both on the images from social networks and on traffic surveillance video systems. Overall, the low-cost method proposed in this study can be used to obtain timely waterlogging warning information, and enhance the possibility of using existing social networks and traffic surveillance video systems to perform opportunistic waterlogging sensing.

[1]  Kenneth W. Chapman,et al.  Source and magnitude of error in an inexpensive image-based water level measurement system , 2013 .

[2]  P. Chaudhary,et al.  FLOOD-WATER LEVEL ESTIMATION FROM SOCIAL MEDIA IMAGES , 2019, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[3]  Sokwoo Rhee,et al.  StormSense: A New Integrated Network of IoT Water Level Sensors in the Smart Cities of Hampton Roads, VA. , 2018, Marine Technology Society journal.

[4]  Xiaolei Wang,et al.  Study on the Quality Control for Periodogram in the Determination of Water Level Using the GNSS-IR Technique , 2019, Sensors.

[5]  Jing Huang,et al.  Analysis of the Public Flood Risk Perception in a Flood-Prone City: The Case of Jingdezhen City in China , 2018, Water.

[6]  Yang Xiao,et al.  Real-time identification of urban rainstorm waterlogging disasters based on Weibo big data , 2018, Natural Hazards.

[7]  Chong-yu Xu,et al.  Simulation of Dualistic Hydrological Processes Affected by Intensive Human Activities Based on Distributed Hydrological Model , 2018, Journal of Water Resources Planning and Management.

[8]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[10]  V. Babovic,et al.  Advancing Opportunistic Sensing in Hydrology: A Novel Approach to Measuring Rainfall With Ordinary Surveillance Cameras , 2019, Water Resources Research.

[11]  F. Joseph Turk,et al.  Precipitation from Space: Advancing Earth System Science , 2013 .

[12]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[13]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[14]  Youngjoon Han,et al.  Embedded implementation of image-based water-level measurement system , 2011 .

[15]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[16]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Anke Xue,et al.  Automatic Estimation of Urban Waterlogging Depths from Video Images Based on Ubiquitous Reference Objects , 2019, Remote. Sens..

[18]  Huajun Chen,et al.  Social Media Meets Big Urban Data: A Case Study of Urban Waterlogging Analysis , 2016, Comput. Intell. Neurosci..

[19]  川野 秀一 An Introduction to Statistical Learning (with Applications in R), Gareth James,Daniela Witten,Trevor Hastie and Robert Tibshirani著, Springer, 2013年8月, 430pp., 価格 59.99〓, ISBN 978-1-4614-7137-0 , 2014 .

[20]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Bingshun He,et al.  Analysis of flash flood disaster characteristics in China from 2011 to 2015 , 2017, Natural Hazards.

[22]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Peng Wang,et al.  Microwave-Photonic Sensor for Remote Water-Level Monitoring Based on Chaotic Laser , 2014, Int. J. Bifurc. Chaos.

[24]  L. Ren,et al.  Applicability of the Revised Mean Absolute Percentage Errors (MAPE) Approach to Some Popular Normal and Non-normal Independent Time Series , 2009 .

[25]  M. R. Rasmussen,et al.  Field-Scale Monitoring of Urban Green Area Rainfall-Runoff Processes , 2019, Journal of Hydrologic Engineering.

[26]  X. Wen,et al.  A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset , 2016 .

[27]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[28]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Jingchao Jiang,et al.  Extraction of Urban Waterlogging Depth from Video Images Using Transfer Learning , 2018, Water.

[30]  Jiancheng Shi,et al.  The Future of Earth Observation in Hydrology. , 2017, Hydrology and earth system sciences.

[31]  P. Phukpattaranont,et al.  A self-calibration water level measurement using an interdigital capacitive sensor , 2014 .

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.