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{178099,
        author = {S Rajesh and Vanka Ravi Teja and Muchakala Saileela and Vandavasi Megashyam and Yellu Bhavana and Katuru Sumanth},
        title = {Automatic Person-in-Water Detection for Marine Search and Rescue Operations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2157-2163},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178099},
        abstract = {Every year, numerous individuals face life-threatening situations at sea due to accidents, vessel capsizing, or adverse weather conditions. Quick and effective rescue operations are critical to save lives, but Manual observation methods (Helicopters or Rescue boats…etc.) often face challenges like poor visibility due to bad weather conditions, vast search areas, limited resources, prone to human errors due to fatigue. Autonomous drones can be a game changing option in Search and Rescue Operations in diverse scenarios with better precision. This approach provides a reliable, scalable, and efficient solution to save lives. In our proposed system, we used CNN-based YOLOv4, a high-speed and precise object detection model on the drone captured images to detect the person in water. We achieved an accuracy of over 95% on sample images},
        keywords = {Search and Rescue (SAR), YOLOv4, Deep Learning, Convolutional Neural Networks (CNN), MATLAB 2024b, Drone-based Detection, Computer Vision, Drowning Prevention, Real-time Monitoring, Surveillance System, Autonomous Rescue Systems, Emergency Response},
        month = {May},
        }