Flood Detection Using Real-Time Image Segmentation from Unmanned Aerial Vehicles on Edge-Computing Platform

Abstract

With the proliferation of unmanned aerial vehicles (UAVs) in different contexts and application areas, efforts are being made to endow these devices with enough intelligence so as to allow them to perform complex tasks with full autonomy. In particular, covering scenarios such as disaster areas may become particularly difficult due to infrastructure shortage in some areas, often impeding a cloud-based analysis of the data in near-real time. Enabling AI techniques at the edge is therefore fundamental so that UAVs themselves can both capture and process information to gain an understanding of their context, and determine the appropriate course of action in an independent manner. Towards this goal, in this paper, we take determined steps towards UAV autonomy in a disaster scenario such as a flood. In particular, we use a dataset of UAV images relative to different floods taking place in Spain, and then use an AI-based approach that relies on three widely used deep neural networks (DNNs) for semantic segmentation of images, to automatically determine the regions more affected by rains (flooded areas). The targeted algorithms are optimized for GPU-based edge computing platforms, so that the classification can be carried out on the UAVs themselves, and only the algorithm output is uploaded to the cloud for real-time tracking of the flooded areas. This way, we are able to reduce dependency on infrastructure, and to reduce network resource consumption, making the overall process greener and more robust to connection disruptions. Experimental results using different types of hardware and different architectures show that it is feasible to perform advanced real-time processing of UAV images using sophisticated DNN-based solutions.

Comparative Study of Real-Time Semantic Segmentation Networks in Aerial Images During Flooding Events

“…Various convolutional neural networks are applied for flood image semantic segmentation [72]. A comparative study of segmentation models on flooding events investigates the performance of multiple segmentation networks on the flooding dataset [77], [36]. Furthermore, water [54], and river segmentations with deep learning models are considered for flood monitoring [64].…”

“…As Figure 2 is shown, the semantic segmentation labels are categorized into nine classes. It includes building-flooded (3248 instances meaning there are 3248 objects within building-flooded category), building-non-flooded (3427 instances), road-flooded (495 instances), road-non-flooded (2155 instances), water (1374 instances), tree (19682 instances), vehicle (4535 instances), pool (1141 instances), and grass (19682 instances meaning 19682 segmentation regions containing grass) [75], [36]. FloodNet captures the diversity and complexity of segmenting aerial objects captured by drones.…”

PMNet: A Multi-branch and Multi-scale Semantic Segmentation Approach to Water Extraction from high-resolution remote sensing images with Edge-Cloud Computing

“…This approach can reduce network latency, improve real-time performance, and perform calculations close to the data source, thereby reducing the need for data transmission and storage. [27] optimized the target algorithm of the edge computing platform for GPU, only uploading the algorithm output to the cloud, and the segmentation task was performed on the local edge device. This method reduces the dependence on infrastructure and the consumption of network resources, and is more robust to connection interruptions, thus achieving efficient real-time processing.…”

Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting

“…Many studies in the fields such as medical care, manufacturing, and fault detection have developed sensors not only for monitoring but also implemented edge computing for applications that are close in proximity to the sources in case of need, e.g., [ 13 , 14 , 15 ]. In comparison with other applications, only a few studies have investigated edge computing in landslide- and flood-related applications [ 16 , 17 , 18 ]. People hesitate to apply edge computing in flood warning systems for the following possible reasons.…”