Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{170732,
        author = {Bollu Jagadeesh and Mr.K. Mohan Krishna and Dr. Ramachandran Vedantam},
        title = {Real-Time Disaster Classification Using UAV Imagery and Efficient Net for Resource-Constrained Environments},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1458-1462},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170732},
        abstract = {Disaster management is essential for mitigating the effects of natural and human-made catastrophes on people and the environment. Rapid and precise assessment of disaster-affected areas is crucial for effective response and recovery efforts. Unmanned Aerial Vehicles (UAVs), equipped with high-resolution imaging systems, have proven to be indispensable for capturing real-time aerial views of disaster zones. However, efficiently processing these images for accurate disaster classification remains a significant challenge. This paper introduces an advanced disaster monitoring framework that utilizes Efficient-Net, a cutting-edge deep learning architecture, to classify UAV-acquired images based on different disaster scenarios. By fine-tuning a pretrained Efficient-Net model specifically for disaster detection, the system achieves remarkable accuracy in categorizing images into classes such as damaged infrastructure, fires, water-related disasters, human casualties, and non-critical conditions. The proposed solution is optimized to balance computational efficiency with real-time performance, making it suitable for deployment in environments with limited resources. Comprehensive evaluations on a disaster-specific image dataset demonstrate the model's superior accuracy and faster processing speeds compared to existing methods. This study emphasizes the potential of Efficient-Net to enhance UAV-based disaster monitoring systems by improving their scalability and real-time operational capabilities.},
        keywords = {Disaster Management, UAV Imagery, Efficient-Net, Deep Learning, Disaster Classification, Real-Time Monitoring, Resource-Constrained Systems, Aerial Image Processing},
        month = {December},
        }