Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera

Abstract

The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities.

Water Level Fluctuation Using Surveillance Camera

“…In summary, the implementation of the proposed technique will provide invaluable information, especially in water region detection and monitoring the fluctuation of the river, which can be useful in decision making or coordinating flood relief operations. A similar study to identify water regions from surveillance images has been performed using deep learning semantic segmentation (Muhadi et al, 2021). Future work can be done by adopting different neural network architectures to find out which architecture performs well for water-related problems.…”

Synthetic Generation and Detection of Crown-of-Thorns Starfish Instances retrival in Underwater Image

“…This paper proposes estimating water levels using surveillance cameras and deep learning-based semantic segmentation. The DeepLabv3+ model demonstrates greater precision, allowing cost-effective real-time monitoring for flood management [32].This paper identifies extreme low tides (nsLAs) as a severe hazard to Reunion Island's coral reefs, resulting in a 50% loss of coral cover. The comprehensive method highlights the depth dependence of coral death, underlining the need for proactive reef protection actions [33].This paper describes a spatial technique for monitoring coral reef health at the fine scale that employs hyperspectral and multispectral data.…”

Three-Dimensional Convolutional Neural Network on Multi-Temporal Synthetic Aperture Radar Images for Urban Flood Potential Mapping in Jakarta

“…Therefore, this research will propose mapping the potential flood areas using the DNN algorithm. DNN is based on Artificial Neural Network and generally consists of an input layer, with more than one hidden layer and one output layer [52]. Figure 6 shows the conceptual structure of the DNN model used for flood vulnerability mapping.…”