Copyright © 2026 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{197847,
        author = {Mrs. Dannuri Mounika and Podila shiva charan and Asritha Mamidi and Thummanapally Vibhu Sharma and Sriya Sarvade},
        title = {Hybrid AI-Based Real-Time Human Detection and Disaster Classification System Using YOLOv8 and InceptionV3},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6845-6852},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197847},
        abstract = {The increasing frequency and intensity of natural disasters demand intelligent systems capable of assisting in real-time rescue and monitoring operations. This research presents a hybrid artificial intelligence-based framework for real-time human detection and disaster classification using deep learning and computer vision techniques. The proposed system integrates YOLOv8 for high-speed human detection and InceptionV3 for accurate disaster classification. The system processes input from images or live video streams, detects human presence using bounding box localization, and classifies environmental conditions such as cyclone, earthquake, flood, and wildfire. Experimental evaluation demonstrates that the proposed model achieves detection accuracy exceeding 92% and classification accuracy of approximately 94%, with real-time processing capability of 20–30 FPS on standard hardware. Data augmentation techniques improve generalization by nearly 25%, while transfer learning reduces training time by 40%. The hybrid approach significantly reduces false positives and enhances reliability compared to standalone detection systems. The system is scalable and can be integrated with IoT devices, drones, and emergency response platforms. Overall, the proposed framework provides an efficient and practical solution for disaster management, surveillance, and smart monitoring applications.},
        keywords = {YOLOv8, InceptionV3, Human Detection, Disaster Classification, Computer Vision, Deep Learning, Real-Time Monitoring, Object Detection.},
        month = {April},
        }