Eye of Horus: a vision-based framework for real-time water level measurement
-
Published:2023-11-15
Issue:22
Volume:27
Page:4135-4149
-
ISSN:1607-7938
-
Container-title:Hydrology and Earth System Sciences
-
language:en
-
Short-container-title:Hydrol. Earth Syst. Sci.
Author:
Erfani Seyed Mohammad HassanORCID, Smith CorinneORCID, Wu Zhenyao, Shamsabadi Elyas Asadi, Khatami Farboud, Downey Austin R. J., Imran Jasim, Goharian Erfan
Abstract
Abstract. Heavy rains and tropical storms often result in floods, which are expected to increase in frequency and intensity. Flood prediction models and inundation mapping tools provide decision-makers and emergency responders with crucial information to better prepare for these events. However, the performance of models relies on the accuracy and timeliness of data received from in situ gaging stations and remote sensing; each of these data sources has its limitations, especially when it comes to real-time monitoring of floods. This study presents a vision-based framework for measuring water levels and detecting floods using computer vision and deep learning (DL) techniques. The DL models use time-lapse images captured by surveillance cameras during storm events for the semantic segmentation of water extent in images. Three different DL-based approaches, namely PSPNet, TransUNet, and SegFormer, were applied and evaluated for semantic segmentation. The predicted masks are transformed into water level values by intersecting the extracted water edges, with the 2D representation of a point cloud generated by an Apple iPhone 13 Pro lidar sensor. The estimated water levels were compared to reference data collected by an ultrasonic sensor. The results showed that SegFormer outperformed other DL-based approaches by achieving 99.55 % and 99.81 % for intersection over union (IoU) and accuracy, respectively. Moreover, the highest correlations between reference data and the vision-based approach reached above 0.98 for both the coefficient of determination (R2) and Nash–Sutcliffe efficiency. This study demonstrates the potential of using surveillance cameras and artificial intelligence for hydrologic monitoring and their integration with existing surveillance infrastructure.
Funder
National Science Foundation
Publisher
Copernicus GmbH
Subject
General Earth and Planetary Sciences,General Engineering,General Environmental Science
Reference68 articles.
1. Alsdorf, D. E., Rodríguez, E., and Lettenmaier, D. P.: Measuring surface water from space, Rev. Geophys., 45, RG2002, https://doi.org/10.1029/2006RG000197, 2007. a 2. Badrinarayanan, V., Handa, A., and Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling, arXiv [preprint], https://doi.org/10.48550/arXiv.1505.07293, 2015. a 3. Bradski, G.: The OpenCV Library, Dr. Dobb's Journal of Software Tools, https://opencv.org/ (last access: 4 November 2023), 2000. a 4. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., and Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation, arXiv [preprint], https://doi.org/10.48550/arXiv.2102.04306, 2021. a, b 5. Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A. L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE T. Pattern Anal. Mach. Intel., 40, 834–848, 2017. a
|
|