Against the background of Ambient Assisted Living, this article proposes a new kind of unobtrusive, non-stigmatizing and continuous acquisition of vital signs as respiratory rate and related features on the basis of ultra-wide-band radar sensing. Through the runtime analysis of the reflection data, surrogating mechanical signals e.g. the excursion of the thorax are detected and linked with physiological values like the breathing rate. After a brief introduction to the application context including an explanation of specific user demands and restrictions of current solutions of the telemedicine, physical fundamentals of measurement and the utilized electronics, the applied principles of spatial and temporal data mining are described. Finally, experiments including real measurements with the subsequent discussion of the measurement results provide an outlook to the capabilities of our approach and grant information about open issues and the steps in research.