• Mrs.Nita Meshram
• Chinmay N.M.
• Divya Lakshmi J.H.
• Eshwar Sai Chandra
• Gautham Narkodu

The issue of drowning incidents poses a critical challenge to water safety, underscoring the imperative for advanced technologies to swiftly and accurately detect such occurrences. This research introduces a real-time drowning detection system leveraging computer vision and deep learning methodologies. The system integrates the You Only Look Once (YOLO) object detection algorithm to identify objects within video frames, prioritizing potential drowning scenarios. Additionally, a customized Convolutional Neural Network (CNN) model is utilized to categorize individuals' swimming status as either "drowning" or "normal" based on their actions captured in the video footage. Functioning in real-time, the system continuously analyzes video frames from a specified source, delivering visual feedback through the depiction of bounding boxes around detected objects and the annotation of their predicted swimming status.

You Only Look Once (YOLO), Convolutional Neural Network (CNN).

"AUTOMATIC VISUAL SURVEILLANCE SYSTEM TO DETECT DROWNING INCIDENTS IN SWIMMING POOLS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.155-159, May-2024, Available :http://www.jetir.org/papers/JETIRGG06026.pdf

"AUTOMATIC VISUAL SURVEILLANCE SYSTEM TO DETECT DROWNING INCIDENTS IN SWIMMING POOLS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. pp155-159, May-2024, Available at : http://www.jetir.org/papers/JETIRGG06026.pdf