Approximatley 40 tragic deaths of small children locked in vehicles occur in the US each year due to the extreme heat or cold inside the parked vehicle. If the vehicle is able to detect the presence of a child (or any other life such e.g. a pet) it can either alert the owner or adjust the climate control in order to avoid these tragic accidents.

This thesis focuses on using the ultra-wideband (UWB) nodes used for the keyless entry systems of the vehicle as radar sensors in order to detect the presence of life inside the vehicle. This promises several benefits such as costs savings, immunity to different illumination conditions and the possibility to detect a child even if it is under a blanket. However, due to the harsh radio environment and rich scattering inside the vehicle powerfull signal processing techniques must be applied in order to seperate the target signal (such as the chest movement due to respiratory action) from unwanted clutter. Several classical signal processign algorithms as well as data-driven machine learning algorithms will be evaluated and their respective performance compaired agianst each other in order to achieve the best detection accuracy.