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

Sayma Nasrin Shompa

doi:10.59890/ijist.v3i9.172

Authors

Sayma Nasrin Shompa International Islamic University Chittagong

DOI:

https://doi.org/10.59890/ijist.v3i9.172

Keywords:

UAVs, Deep Learning, Emergency Response, Disaster Management, Embedded Systems, Real-time Processing, Lightweight CNN, Scene Recognition, Transfer Learning, Dataset Augmentation, Edge AI.

Abstract

In remote areas during emergencies and disasters, Unmanned Aerial Vehicles (UAVs) with camera sensors are essential for improving Perception of the Situation. This study Probes the use of UAVs with on-board Rooted deep learning systems for real-time Remotely piloted aerial scene Sorting in order to identify disasters like fires, floods, and collapsed buildings. We Illustrate earlier approaches and present the Aerial Image Database for Catastrophe Response (AIDER). Furthermore, we introduce a new light CNN model that Obtains a roughly threefold performance increase on embedded platforms with a small memory footprint and minimal Veracity loss (less than 2%). These results greatly advance the Review of using UAVs for real-time Emergency event recognition.

References

R. Gupta et al., "XBD: A Dataset for Assessing Building Damage from Satellite Imagery," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), 2019. Source https://www.academia.edu/78860908/xBD_A_Dataset_for_Assessing_Building_Damage_from_Satellite_Imagery

K. Muhammad et al., "Edge-AI Driven Framework for Dual-Sensor Wildfire Surveillance," IEEE Sensors J., vol. 22, no. 15, pp. 14567–14575, 2022. https://doi.org/10.1109/JSEN.2022.3182770

P. Zhang et al., "A Hybrid Fast Inference Approach with Distributed Neural Networks for Edge Computing-Enabled UAV Swarm," Phys. Commun., vol. 56, 2023, Art. no. 101029. https://doi.org/10.1016/j.phycom.2023.101029

S. H. Asahi et al., "AI-based Drone-Assisted Human Rescue in Disaster Environments: Challenges and Opportunities," arXiv:2301.07492, 2023. Source https://arxiv.org/abs/2301.07492

J. Lin et al., "Real-Time Embedded AI for UAV Disaster Response: A Jetson AGX Benchmark Study," in Proc. IEEE ICUAS, 2023. https://ieeexplore.ieee.org/document/10169875

Y. Bai et al., "Binary Neural Networks for UAV Real-Time Inference," IEEE Trans. Aerosp. Electron. Syst., vol. 58, no. 4, pp. 2875–2886, 2022. https://ieeexplore.ieee.org/document/9775493

M. Tan and Q. Le, "EfficientNetV2: Smaller Models and Faster Training," in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 10096–10106.https://proceedings.mlr.press/v139/tan21a.html

S. Gupta et al., "TransFlood: Transformer-CNN Fusion for Flood Extent Mapping," IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 15, pp. 1882–1892, 2022. https://ieeexplore.ieee.org/document/9711343

M. B. Bejiga et al., "A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery," Remote Sens., vol. 9, no. 2, 2017. https://doi.org/10.3390/rs9020100

G. Cheng et al., "When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs," IEEE Trans. Geosci. Remote Sens., vol. 56, no. 5, pp. 2811–2821, 2018.https://doi.org/10.1109/TGRS.2017.2776201

F. Chollet, "Keras," GitHub, 2015. Source https://github.com/keras-team/keras

K. He et al., "Deep Residual Learning for Image Recognition," arXiv:1512.03385, 2015. Source https://arxiv.org/abs/1512.03385

F. Hohman et al., "Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers," IEEE Trans. Vis. Comput. Graphics, vol. 25, no. 8, pp. 2674–2692, 2018.https://doi.org/10.1109/TVCG.2018.2830113

M. Hossain and S. M. N. Sulaiman, "A Review on Evaluation Metrics for Data Classification Evaluations," Int. J. Data Min. Knowl. Manag. Process, vol. 5, no. 2, pp. 1–11, 2015.https://airccse.org/journal/ijdkp/papers/5215ijdkp01.pdf

A. G. Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv:1704.04861, 2017. Source https://arxiv.org/abs/1704.04861

A. Kamilaris and F. X. Prenafeta-Boldú, "Disaster Monitoring Using Unmanned Aerial Vehicles and Deep Learning," in Proc. Environ. Inform. Manage. (EnviroInfo), Luxembourg, 2017. https://publications.jrc.ec.europa.eu/repository/handle/JRC108939

S. Kim et al., "Forest Fire Monitoring System Based on Aerial Image," in *Proc. 3rd Int. Conf. Inf. Commun. Technol. Disaster Manag. (ICT-DM), 2016, pp. 1–6. https://doi.org/10.1109/ICT-DM.2016.7857215

C. Kyrkou et al., "Optimized Vision-Directed Deployment of UAVs for Rapid Traffic Monitoring," in Proc. IEEE Int. Conf. Consum. Electron. (ICCE), 2018, pp. 1–6. https://doi.org/10.1109/ICCE.2018.8326204

M. Lin et al., "Network in Network," arXiv:1312.4400, 2013. Source https://arxiv.org/abs/1312.4400

E. Maggiori et al., "Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification," IEEE Trans. Geosci. Remote Sens., vol. 55, no. 2, pp. 645–657, 2017.

T. D. Nguyen et al., "Applications of Online Deep Learning for Crisis Response Using Social Media Information," arXiv:1610.01030, 2016. Source https://arxiv.org/abs/1610.01030

A. S. Razavian et al., "CNN Features Off-the-Shelf: An Astounding Baseline for Recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, 2014, pp. 512–519.https://ieeexplore.ieee.org/document/6909475

R. R. Selvaraju et al., "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 618–626.https://ieeexplore.ieee.org/document/8237336

A. Vetrivel et al., "Disaster Damage Detection from UAV Imagery Using Deep Learning," Remote Sens., vol. 10, no. 2, p. 239, 2018.https://www.mdpi.com/2072-4292/10/2/239

K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," arXiv:1409.1556, 2014. Source https://arxiv.org/abs/1409.1556

M. Tan and Q. Le, "EfficientNetV2: Smaller Models and Faster Training," in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 10096–10106. https://proceedings.mlr.press/v139/tan21a.html

Y. Wang et al., "A Retrospective Evaluation of Energy-Efficient Object Detection Solutions on Embedded Devices," in Proc. Design, Autom. Test Europe Conf. Exhibition (DATE), 2018, pp. 709–714. https://ieeexplore.ieee.org/document/8342126

Y. Wang et al., "Large: Learning Latent Relationships with Adaptive Graph Embedding for Aerial Scene Classification," IEEE Trans. Geosci. Remote Sens., vol. 56, no. 2, pp. 621–634, 2018. https://ieeexplore.ieee.org/document/8022925

Y. Zhao et al., "Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery," Sensors, vol. 18, no. 3, 2018. https://www.mdpi.com/1424-8220/18/3/712

"DJI Matrice 100," DJI, 2023. [Online]. Available: https://www.dji.com/matrice100

E. Bañuelos et al., "UAV-Based Flood Mapping and Emergency Response," Remote Sens., vol. 12, no. 3, p. 515, 2020. https://doi.org/10.3390/rs12030515

X. Chen et al., "Multi-scale Attention Networks for Aerial Disaster Scene Classification," IEEE Trans. Geosci. Remote Sens., vol. 62, 2024, Art. no. 5103312. https://doi.org/10.1109/TGRS.2024.5103312

M. R. Shafqat et al., "UAV-Edge Fusion: Real-Time Multispectral Fusion on UAV Edge Hardware for Emergency Monitoring," IEEE Internet Things J., vol. 11, no. 1, pp. 219–230, 2024. https://doi.org/10.1109/JIOT.2023.3339823

A. Ben Hamida et al., "A Comprehensive Review of Deep Learning-Based Methods for Image Captioning: Datasets, Metrics, Models and Challenges," Electronics, vol. 10, no. 13, p. 1549, 2021. https://doi.org/10.3390/electronics10131549

S. Ibrahem and M. Ethel, "Aerial Image Classification for Disaster Response Using Vision Transformers," arXiv:2503.02465, 2025. Source https://arxiv.org/abs/2503.02465

T. Bouabdellah et al., "A Deep Learning-Based Approach for Real-Time Wildfire Detection Using UAV Imagery," Drones, vol. 7, no. 7, p. 436, 2023. Source https://www.sciopen.com/article/10.14067/j.cnki.1673-923x.2024.03.003?issn=1673-923K

K. V. S. R. Anjaneyulu et al., "UAV-Based Real-Time Forest Fire Detection Using Deep Learning," Remote Sens., vol. 16, no. 5, p. 879, 2024. Source https://www.frontiersin.org/journals/forests-and-global-change/articles/10.3389/ffgc.2023.1134942/full