Visual Sensing for Urban Flood Monitoring

Abstract

With the increasing climatic extremes, the frequency and severity of urban flood events have intensified worldwide. In this study, image-based automated monitoring of flood formation and analyses of water level fluctuation were proposed as value-added intelligent sensing applications to turn a passive monitoring camera into a visual sensor. Combined with the proposed visual sensing method, traditional hydrological monitoring cameras have the ability to sense and analyze the local situation of flood events. This can solve the current problem that image-based flood monitoring heavily relies on continuous manned monitoring. Conventional sensing networks can only offer one-dimensional physical parameters measured by gauge sensors, whereas visual sensors can acquire dynamic image information of monitored sites and provide disaster prevention agencies with actual field information for decision-making to relieve flood hazards. The visual sensing method established in this study provides spatiotemporal information that can be used for automated remote analysis for monitoring urban floods. This paper focuses on the determination of flood formation based on image-processing techniques. The experimental results suggest that the visual sensing approach may be a reliable way for determining the water fluctuation and measuring its elevation and flood intrusion with respect to real-world coordinates. The performance of the proposed method has been confirmed; it has the capability to monitor and analyze the flood status, and therefore, it can serve as an active flood warning system.

A performance analysis for real-time flood monitoring using image-based processing

“…It"s vital to monitor the state of the flood for saving life and minimizing the losses. There are many methods can be used for the flood monitoring, but in the literature review from the reference [1][2][3][4][5][6][7][8][9], the image-based methods: region growing, canny edge detection and normalized cuts are better than the others based on the achievability and timeliness. These image-based methods will be made a simulation on MATLAB in the beginning and the method which has the best performance will be kept and improved.…”

“…In the reference, the related papers are [1,5] and [7]. Paper [1] proposed a method can detect the flash flood with the fast processing speed based on the stationary surveillance cameras, which can be used to the urban areas.…”

“…The proposed method includes mean-shift and region growing, which can be used in bad weather condition such as rainy. The region growing method can partition the pixels into meaningful parts based on the seed [7] aimed to monitor the flood with a specific area automatically. The images are captured from the CCTV and infrared camera.…”

“…While the region growing method can group the pixels into different parts according to the similarity of them, which is based on the seed point and grow rules. The graph-based segmentation is a popular trend in the image segmentation area for recent years, which can partition one graph into many sub-graphs that each graph represents the interested meaningful object [7]. In order to find the most suitable method for flood monitoring, the three image-based methods will be compared on the MATLAB.…”

Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning

“…Greater local details can give more information about the severity, extent, and depth of floodwater on specific road segments. Video and surveillance-*This study was supported by the Mid-Atlantic Transportation Sustainability Center (MATS UTC), Region 3 UTC funded by USDOT 1 based methods have also been studied to detect flood or water level changes [4,5]. Water segmentation in images and videos is a related problem to flood detection.…”