arXiv · 2611.13638
picoEmergencyNet : Attention-Enhanced Ultra-Small Deep Learning Model for Aerial Image Classification in Emergency Monitoring
Abstract
Real-time disaster recognition from aerial imagery requires deep learning models that operate under strict memory, compute, and latency constraints. While recent approaches achieve high accuracy, their computational cost limits deployment on resource-constrained UAV platforms. This work introduces picoEmergencyNet, an ultra-lightweight convolutional neural network designed for aerial image disaster classification. The proposed architecture combines depthwise dilated convolutions with efficient channel attention and channel shuffling to enable multi-scale feature extraction at minimal computational cost. picoEmergencyNet has 23k parameters and 7M FLOPs, requiring only 0.1 MB of model storage. Evaluated on the AIDER and AIDERv2 disaster datasets, it achieves up to 96.1% accuracy, matching or exceeding state-of-the-art lightweight models that are orders of magnitude larger. Deployment experiments on the NVIDIA Jetson AGX Orin show that, without hardware-specific optimizations, picoEmergencyNet achieves 258 FPS on GPU and 46 FPS on CPU with a 7x lower activation memory footprint compared to competing models. These results demonstrate that careful architectural specialization, rather than model scaling, enables highly efficient and accurate TinyML-ready disaster recognition for real-time UAV-based emergency monitoring.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Christos Kyrkou. 2026-11-10. picoEmergencyNet : Attention-Enhanced Ultra-Small Deep Learning Model for Aerial Image Classification in Emergency Monitoring. https://doi.org/10.1109/ijcnn69854.2026.11729718. https://searcharxiv.com/abs/2611.13638
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.