UAV-Assisted Real-Time Disaster Detection Using Optimized Transformer Model

2025-01-21

AI Summary

To address challenges in disaster response—including network instability, privacy leakage, processing latency, and resource constraints on edge devices—this paper proposes a lightweight edge-based real-time disaster detection framework tailored for unmanned aerial vehicles (UAVs). Methodologically: (1) we design a lightweight Transformer architecture optimized via post-training quantization and embedded-system deployment techniques; (2) we introduce DisasterEye, the first benchmark dataset integrating UAV-captured aerial imagery with ground-level real-world footage, enhancing generalization to realistic disaster scenarios. Experiments demonstrate that our framework achieves significantly reduced inference latency and over 40% memory footprint reduction on resource-constrained hardware, while maintaining high detection accuracy. To the best of our knowledge, this work is the first to enable end-to-end, privacy-preserving, real-time disaster recognition under offline, low-power edge conditions. It establishes a scalable technical paradigm for edge intelligence in emergency response systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Disaster recovery and management present significant challenges, particularly in unstable environments and hard-to-reach terrains. These difficulties can be overcome by employing unmanned aerial vehicles (UAVs) equipped with onboard embedded platforms and camera sensors. In this work, we address the critical need for accurate and timely disaster detection by enabling onboard aerial imagery processing and avoiding connectivity, privacy, and latency issues despite the challenges posed by limited onboard hardware resources. We propose a UAV-assisted edge framework for real-time disaster management, leveraging our proposed model optimized for real-time aerial image classification. The optimization of the model employs post-training quantization techniques. For real-world disaster scenarios, we introduce a novel dataset, DisasterEye, featuring UAV-captured disaster scenes as well as ground-level images taken by individuals on-site. Experimental results demonstrate the effectiveness of our model, achieving high accuracy with reduced inference latency and memory usage on resource-constrained devices. The framework's scalability and adaptability make it a robust solution for real-time disaster detection on resource-limited UAV platforms.

Problem

• Disaster Situation Recognition
• Network Connectivity
• Privacy Protection

Innovation

• Drone-Assisted System
• Disaster Image Recognition
• Resource-Constrained Devices