Non-contact health monitoring is emerging as a promising alternative to traditional, contact-based methods. It aims to improve diagnostic accuracy, patient comfort, and healthcare efficiency. Conventional techniques such as pulse oximeters, arterial blood pressure measurement or adhesive sensors for ECG can be invasive, uncomfortable, and impractical—especially for vulnerable groups like premature infants, the elderly, or burn patients. Skin irritation, movement restrictions, and compromised data quality due to sensor dislodgment are common challenges.
Advanced procedures like polysomnography are costly, require specialized staff, and are limited to controlled environments. Moreover, wired systems hinder patient mobility and complicate imaging processes, particularly in emergency care, where tangled cables can delay treatment or distort results.
Non-contact technologies—such as depth, infrared, and color cameras, radar, and microphones—offer a less intrusive alternative, enabling real-time, continuous monitoring across various settings, from hospitals to vehicles and homes. These systems support the growing demand for preventive healthcare and telemedicine by facilitating early detection of health deterioration through AI-driven data analysis.
However, current non-contact systems face limitations. Most are sensitive to motion, and physical activity introduces artifacts that reduce signal reliability. Thus, robust signal processing and machine learning models are needed to ensure accuracy in everyday conditions. While not yet ready for widespread daily use, ongoing research is rapidly advancing this field, bringing us closer to seamless, cost-effective, and unobtrusive healthcare monitoring
