Quantification of vital signs

Vital signs are an important indicator of a person's state of health. Without these vital functions life is not possible. A disturbance can result in serious illnesses. Conventional methods such as ECG or pulse oximetry have the disadvantage of being contact-based. In addition to low comfort when worn this poses a problem for people with sensitive skin, such as newborns or the elderly. One solution is optical contactless vital sign measurement. Fraunhofer IMS is researching the most accurate and fastest possible detection of these vital signs in different wavelength ranges and quantifies them using machine learning methods.


The following vital signs are scientifically investigated:

 GUI respiration rate.
© Fraunhofer IMS
Graphical user interface (GUI) for optical determination of the respiration rate
  • Heart rate
  • Respiration rate
  • oxygen saturation
  • blood pressure
  • blood glucose

Various methods from image processing and signal processing are used to perform contactless vital sign measurement with different optical sensors. In particular, the use of neural networks for detection represents an important research focus. Together with partners from industry and medicine we are transferring our visions of health monitoring with the help of contactless vital parameter measurement to series production readiness.

There is a wide range of possible applications for a contactless vital sign measurement:

  • Screening in hospitals
  • Access controls to exclude people with symptoms of disease
  • Health monitoring in the field of Ambient Assisted Living (AAL)
  • Training monitoring in rehabilitation
  • Driver monitoring on the road to autonomous driving
  • Marketing research
  • Sleep lab

One application, access control in hospitals, will be described in more detail below:

One of the most effective measures to contain the current COVID-19 pandemic is social distance and isolation of infected people. Particularly at the entrance to hospitals, where many sick and debilitated people congregate, physical separation of SARS-CoV-2 infected people from other patients, doctors, and nurses is essential.

Since the evaluation of laboratory tests to detect the virus still takes far too long, the main symptoms of COVID-19, fever and shortness of breath, must be analyzed to identify potentially infected patients. While fever can be measured easily and contactless with an infrared camera, there has been no comparably simple measurement system for analyzing the respiratory rate so far.

Person recorded by a camera
© Fraunhofer IMS
Optical sensors enable contactless screening of patients, staff and visitors in hospitals

Therefore, a system based on image processing was developed that can accurately determine the respiratory rate via a commercially available RGB camera. Intelligent image processing analyzes the movement of the chest and filters out the signal of respiratory movement. Arriving patients stand in front of the camera for 30 seconds, and the attending hospital staff can then make an assessment of the patient based on the displayed frequency value (and supplementary body temperature).

During the measurement a safety distance of at least two meters can be maintained without any problems. The measurement is completely contactless, so that contamination of equipment is eliminated and the risk of infection for personnel is significantly reduced. In addition, wearing a mouth/nose protection is possible and does not restrict the measurement.

Videos or personal data are not transmitted, as the system operates locally and without connection to the hospital infrastructure or the Internet, and recorded images are deleted immediately after evaluation. The described system for respiratory rate measurement is currently being evaluated in clinical studies.

Contactless Vital Parameter Measurement@embedded world 2022

Our Colleague Johannes Kühnel shows you our demonstrator.

Click here to watch the video with subtitles on YouTube.  

Our technologies - Innovations for your products

Person Recognition

Special feature extraction is used to enable the recognition of persons on small embedded systems.

Motion Analysis

The motion analysis allows the detection of anomalies and thus enables, for example, fall prevention.


Contactless measurement

Reduced risk of infection and relief for medical staff thanks to innovative contactless measurement technology

Our technology areas - Our technologies for your development

Communication and Networking

Communication interfaces allow data exchange with other devices and connection to networks

User Interfaces

User interfaces as interface between device and user allow the configuration and operation of a product

Machine Learning for Embedded Systems

Artificial intelligence on resource-limited systems can be used to extract higher quality information from raw sensor data

Computer Vision

Computer Vision methods extract the maximum amount of information from image data


Embedded Software and Artificial Intelligence (Home)

Here you can get back to the overview page of the core competence Embedded Software and Artificial Intelligence (ESA).