An Intelligent Drowning Detection and Alert System Using Image Processing and Wearable Biosensors

An Intelligent Drowning Detection and Alert System Using Image Processing and Wearable Biosensors

Shaahin G. Shirazi1 Seyed Mohammaad Javad Nabavi2

1) Electronics Department, Allameh Helli 1+1 Educational Complex, NODET (National Organization for Development of Exceptional Talents), Iran - Email:
2) Electronics Student, Allameh Helli 1+1 Educational Complex, NODET, Iran - Email:

IOI Code : AAHD-ABKCZH
Publication : National Conference on Information Technology, Nanotechnology, Artificial Intelligence and Technological Futures Studies(itnaf.ir)
Abstract :
    rowning is one of the leading causes of unintentional death in aquatic environments, claiming thousands of lives worldwide each year. Traditional monitoring methods based on lifeguard observation face significant challenges due to limited field of view, human fatigue, and delays in recognizing critical situations. This study presents a conceptual framework for an intelligent early drowning risk detection system based on the integration of image processing and wearable biosensors. In the computer vision module, video streams captured by surveillance cameras are analyzed using deep learning algorithms, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models, to identify abnormal motion patterns associated with potentially dangerous situations. Simultaneously, smart wristbands equipped with pulse oximetry sensors monitor swimmers’ physiological indicators such as heart rate and blood oxygen saturation (SpO₂). In the proposed architecture, the convergence of abnormal motion cues and significant changes in vital physiological parameters within a decision-making layer can serve as the basis for issuing early warnings. This multimodal approach is designed to reduce errors associated with single-source monitoring and can provide a foundation for the development of intelligent safety monitoring systems in swimming pools and other aquatic environments.

Keywords : drowning detection image processing computer vision wearable biosensors swimmer safety monitoring