AI-Driven Vision-Based Drowning Detection System for Swimming Pools

This study presents an automated vision-based surveillance system that uses deep learning algorithms to identify drowning accidents in swimming pools. For real-time object detection and tracking, the suggested model makes use of Convolutional Neural Networks (CNNs) and YOLO (You Only Look Once). By analyzing video feeds, the system may spot odd behaviors and possible drowning situations, which can lead to alarms for quick assistance. The framework provides an affordable option for real-time pool surveillance in private as well as public environments, and it can be implemented with Raspberry Pi and camera modules. The outcomes demonstrate a high degree of accuracy in identifying drowning instances, offering an invaluable resource for improving pool safety and averting mishaps.