Contactless Heart Rate Measurement from Facial Video Using RGB Imaging

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

The invention describes a method for contactless measurement of a person's heart rate using a continuous RGB video sequence. By analyzing specific facial regions in the video, tracking facial movements, and extracting time-based signals from skin pixels, the system can accurately determine heart rate without any physical sensors or attachments.

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

• Remote health monitoring for hospitals or care facilities
• Home-based vital signs tracking for elderly or at-risk individuals
• Integration in consumer electronics like smartphones and webcams for fitness tracking
• Security or safety checks where touchless vital monitoring is needed (e.g., airports, workplaces)
• Telemedicine applications to assess patient vitals during virtual consultations

BenefitsContent extracted from patent full text and abstract with AI.

• Completely contactless—no need for straps or wearable devices
• Enhanced user comfort and hygiene
• Reduced cross-contamination risk between users
• Potential for continuous, unobtrusive health monitoring
• Integration with existing camera-equipped devices without special hardware

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The invention relates to a method for contactless determination of heart rate (17) of a person using a continuous RGB image sequence comprising the following steps: a. Acquisition of an RGB image sequence and transmission of the RGB image sequence to a processing unit, b. Selection of at least three regions in a face detected in the RGB image sequence of a person, whose orientation has been determined, c. Tracking of the face in parallel with step b, wherein each of the suitable pixels is compared in its intensity with the intensity of the respective neighboring pixels and both the displacement of the path length of each pixel by a determined height and width from one time step to the temporally subsequent time step, as well as to the temporally preceding time step are evaluated, d. Selection of suitable pixels in the selected regions on the basis of facial skin color and landmarks, while maintaining a distance of at least two pixels from a skin pixel to a non-skin pixel, e. Signal extraction by conversion of a spatial image signal from the RGB image sequence in the selected regions into a time signal, f. Signal processing and evaluation of the time signal, wherein the time signal forms a basis for the determination of heart rate.