Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles

Abstract

Unmanned Aerial Vehicles (UAVs), equipped with camera sensors can facilitate enhanced situational awareness for many emergency response and disaster management applications since they are capable of operating in remote and difficult to access areas. In addition, by utilizing an embedded platform and deep learning UAVs can autonomously monitor a disaster stricken area, analyze the image in real-time and alert in the presence of various calamities such as collapsed buildings, flood, or fire in order to faster mitigate their effects on the environment and on human population. To this end, this paper focuses on the automated aerial scene classification of disaster events from on-board a UAV. Specifically, a dedicated Aerial Image Database for Emergency Response (AIDER) applications is introduced and a comparative analysis of existing approaches is performed. Through this analysis a lightweight convolutional neural network (CNN) architecture is developed, capable of running efficiently on an embedded platform achieving ∼ 3× higher performance compared to existing models with minimal memory requirements with less than 2% accuracy drop compared to the state-ofthe-art. These preliminary results provide a solid basis for further experimentation towards real-time aerial image classification for emergency response applications using UAVs.

FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding

“…Aerial scene understanding datasets are helpful for urban management, city planning, infrastructure maintenance, damage assessment after natural disasters, and high definition maps for self-driving cars. Existing aerial datasets, however, are limited mainly to classification [5], [6] or semantic segmentation [5], [7] of few individual classes such as roads or buildings. Most of these datasets do not address the unique challenges in understanding post-disaster scenarios as a task for disaster damage assessment.…”

ERA: A Data Set and Deep Learning Benchmark for Event Recognition in Aerial Videos [Software and Data Sets]

“…In [7], the authors build an aerial image dataset, termed as AIDER, for emergency response applications. This dataset only involves four disaster events, namely fire/smoke, flood, collapsed building/rubble, and traffic accident, and a normal case.…”

“…Both the UCLA Aerial Event dataset [4] and the Okutama-Action dataset [5] are small in todays terms for aerial video understanding, and their data are gathered in well-controlled environments and only focus on several human-centric events. Besides, the AIDER dataset [7] is an image dataset with only 5 classes for disaster event classification. In contrast, our ERA is a relatively large-scale UAV video content understanding dataset, aiming to recognize generic dynamic events from an aerial view.…”

DeepBrain: Experimental Evaluation of Cloud-Based Computation Offloading and Edge Computing in the Internet-of-Drones for Deep Learning Applications

“…In [ 9 ], the authors investigated the problem of vehicle tracking from aerial images. The authors in [ 10 ] proposed CNN architectures to automate the classification of aerial scenes of disaster events, such as fires, earthquakes, floods, and accidents. The works mentioned above demonstrate the recent trend in coupling UAS applications with deep learning algorithms.…”