Toward Improved Real‐Time Rainfall Intensity Estimation Using Video Surveillance Cameras

• Published in: Water resources research Vol. 59; no. 8
• Main Authors: Zheng, Feifei, Yin, Hang, Ma, Yiyi, Duan, Huan‐Feng, Gupta, Hoshin, Savic, Dragan, Kapelan, Zoran
• Format: Journal Article
• Language: English
• Published: Washington John Wiley & Sons, Inc 01-08-2023
• Subjects: Algorithms; Artificial neural networks; Cameras; Casualties; Climate change; convolutional neural networks (CNNs); deep learning; Economic impact; Estimates; extraction of raindrop information; Extreme weather; Flood forecasting; Flooding; Floods; Gauges; Global climate; image decomposition; Imagery; Machine learning; Neural networks; Night; Night-time; Nighttime; Performance prediction; Precipitation; Radar; Rain gauges; Raindrops; Rainfall; Rainfall forecasting; Rainfall intensity; rainfall intensity estimation; Remote sensing; River discharge; Surveillance; surveillance camera imagery; urban flooding; Urban rainfall
• ISSN: 0043-1397; 1944-7973
• DOI: 10.1029/2023WR034831

Under global climate change, urban flooding occurs frequently, leading to huge economic losses and human casualties. Extreme rainfall is one of the direct and key causes of urban flooding, and accurate rainfall estimates at high spatiotemporal resolution are of great significance for real‐time urban flood forecasting. Using existing rainfall intensity measurement technologies, including ground rainfall gauges, ground‐based radar, and satellite remote sensing, it is challenging to obtain estimates of the desired quality and resolution. However, an approach based on processing distributed surveillance camera network imagery through machine learning algorithms to estimate rainfall intensities shows considerable promise. Here, we present a novel approach that first extracts raindrop information from the surveillance camera images (rather than using the raw imagery directly), followed by the use of convolutional neural networks to estimate rainfall intensity from the resulting raindrop information. Evaluation of the approach on 12 rainfall events under both daytime and nighttime conditions shows that generalization ability, and especially nighttime predictive performance, is significantly improved. This represents an important step toward achieving real‐time, high spatiotemporal resolution, measurement of urban rainfall at relatively low cost.
Key Points
A two‐stage algorithm is proposed to provide good quality rainfall intensity estimates using surveillance camera imagery
The generalization capability of the proposed algorithm is demonstrated under different imagery conditions
This work is an important step toward achieving real‐time, high spatiotemporal resolution of urban rainfall data at low cost