A Computer Vision System for Staff Gauge in River Flood Monitoring

Abstract

Rivers close to populated or strategically important areas can cause damages and safety risks to people in the event of a flood. Traditional river flood monitoring systems like radar and ultrasonic sensors may not be completely reliable and require frequent on-site human interventions for calibration. This time-consuming and resource-intensive activity has attracted the attention of many researchers looking for highly reliable camera-based solutions. In this article we propose an automatic Computer Vision solution for river’s water-level monitoring, based on the processing of staff gauge images acquired by a V-IoT device. The solution is based on two modules. The first is implemented on the edge in order to avoid power consumption due to the transmission of poor quality frames, and another is implemented on the Cloud server, where the frames acquired and sent by the V-IoT device are processed for water level extraction. The proposed system was tested on sample images relating to more than a year of acquisitions at a river site. The first module of the proposed solution achieved excellent performances in discerning bad quality frames from good quality ones. The second module achieved very good results too, especially for what it concerns night frames.

Discharge Monitoring in Open-Channels: An Operational Rating Curve Management Tool

“…To speed up the process of reading the hydrometric rods, a camera is installed in each control station that frames the rod in order to provide the reading to the Marche Region Functional Center. This reading can be obtained by an operator or, even better, by means of suitable computer vision algorithms that are able to autonomously extrapolate the water level [ 39 ].…”

Recent Advances in Internet of Things Solutions for Early Warning Systems: A Review

“…The sensors in the Perception Layer can be integrated with other sensors such as Global Positioning System (GPS) units. Smart camera systems can be used alone or alongside sensors that monitor hydraulic and meteorological quantities [ 56 ], but they require deeper data analyses and deep learning or image processing algorithms on the Application Layer (a comprehensive review on computer vision methods for flood monitoring by Arshad et al is reported in [ 20 ]). The presence of pre-existing weather stations or hydro-geological monitoring stations can facilitate the deployment of the EW system.…”

Research on Water-Level Recognition Method Based on Image Processing and Convolutional Neural Networks

“…Bai et al [17] established a multi-scale deep feature learning method for predicting the incoming flow in the Three Gorges reservoir area and confirmed the feasibility of the deep learning method for hydrological forecasting. Sabbatini et al [18] propose an automated CV solution capable of detecting and calculating river water levels with a frame captured by a V-IoT device as input, and a high degree of automation is achieved in the image acquisition and pre-processing stages, but the water level calculation stage is still not intelligent enough. Jafari et al [19] used a deep learning-based semantic segmentation technique to identify reference objects in videos and images to estimate the water level over time; RamKumar et al [20] used a feature matching algorithm to find the feature points corresponding between the captured image and the reference image, and then estimated and plotted the flood lines.…”