Radar-based Single Target Vital Sensing

Simple SummaryContent extracted from patent full text and abstract with AI.

This patent describes a radar-based system and method for non-invasively monitoring vital signs (such as heartbeat and respiration rate) of a single human target using a millimeter-wave radar sensor. The system transmits radar signals, receives their reflections from the human body, processes the resulting digital data using neural networks to filter out poor-quality signals, and then applies advanced signal processing (including ellipse fitting, adaptive filtering, and denoising) to accurately estimate vital signs from subtle body movements—without any physical contact or wearable sensors.

Use CasesContent extracted from patent full text and abstract with AI.

• Continuous patient vital sign monitoring in hospitals and clinics, especially for bedridden or critical care patients
• Sleep quality monitoring at home without wearable devices
• Driver monitoring in vehicles to detect fatigue or health emergencies
• Elderly care at home or in assisted living facilities to provide unobtrusive health monitoring
• Fitness and wellbeing monitoring in consumer electronics such as smart TVs, laptops, or mobile phones
• Contactless health screening in public places or workplaces, especially for infection control (e.g., temperature, pulse)
• Veterinary monitoring for animals
• Smart home devices for monitoring the health of residents

BenefitsContent extracted from patent full text and abstract with AI.

• Non-invasive and contactless: No need for sensors or attachments on the body, improving comfort and compliance
• Continuous, real-time monitoring: Enables timely detection of health issues or emergencies
• High accuracy: Utilizes neural networks to filter out motion artifacts and low-quality data, improving signal reliability
• Robust to noise: Advanced filtering and compensation techniques reduce interference from ambient movements or signal noise
• Privacy-friendly: Unlike cameras, radar-based measurement does not capture visual images, preserving user privacy
• Adaptable: Can be integrated into various devices and environments (e.g., hospital beds, vehicles, consumer electronics)
• Automatic quality control: Intelligent data classification to ensure only high-quality data are used, reducing false alarms
• Energy-efficient: Disables processing when no person is detected, saving power and computational resources

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

In an embodiment, a method includes: generating a target displacement signal indicative of a movement of a human target based on raw digital data generated by a millimeter-wave radar sensor; and estimating a vital sign of the human target based on the target displacement signal, where generating the target displacement signal includes: generating target in-phase (I) and quadrature (Q) (I/Q) data associated with the human target based on the raw digital data, classifying the target I/Q data as high quality data or as low quality data using a first neural network, when the target I/Q data is classified as low quality data, discarding the target I/Q data, when the target I/Q data is classified as high quality data, performing ellipse fitting on the target I/Q data to generate compensated I/Q data, and generating the target displacement signal based on the compensated I/Q data.