"This thesis presents a real-time noncontact system that can monitor an infant's respiration and detect apnea when it occurs. For infants, bedside monitoring of respiratory signals using non-contact sensors is desirable at the hospital and for in-home care. Traditional approach employs acoustic sensors which can hardly detect infant breathing due to low SNR. In this thesis, a novel method is introduced by using a ultra-wideband (UWB) radar that obtains breathing signal from an infant's weak chest vibration. Furthermore, advanced signal processing techniques are proposed to monitor the breathing signal and to detect apnea. Since an infant may move in the crib, a location algorithm is applied periodically to track the current location of the infant's chest. An apnea warning is issued when the respiration is absent for a pre-defined period of time."

Non-contact life detection is a significant component of both civilian and military rescue applications. As a consequence, this interest has resulted in a very active area of research. The primary goal of this research is reliable detection of a human breathing signal. Additional goals of this research are to carry out detection under realistic conditions, to distinguish between two targets, to determine human breathing rate and estimate the posture. Range gating and Singular Value Decomposition (SVD) have been used to remove clutter in order to detect human breathing under realistic conditions. However, the information of the target range or what principal component contains target information may be unknown. DFT and Short Time Fourier Transform (STFT) algorithms have been used to detect the human breathing and discriminate between two targets. However, the algorithms result in many false alarms because they detect breathing when no target exists. The unsatisfactory performance of the DFT-based estimators in human breathing rate estimation is due to the fact that the second harmonic of the breathing signal has higher magnitude than the first harmonic. Human posture estimation has been performed by measuring the distance of the chest displacements from the ground. This requires multiple UWB receivers and a more complex system. In this thesis, monostatic UWB radar is used. Initially, the SVD method was combined with the skewness test to detect targets, discriminate between two targets, and reduce false alarms. Then, a novel human breathing rate estimation algorithm was proposed using zero-crossing method. Subsequently, a novel method was proposed to distinguish between human postures based on the ratios between different human breathing frequency harmonics magnitudes. It was noted that the ratios depend on the abdomen displacements and higher harmonic ratios were observed when the human target was sitting or standing. The theoretical analysis shows that the distribution of the skewness values of the correlator output of the target and the clutter signals in a single range-bin do not overlap. The experimental results on human breathing detection, breathing rate, and human posture estimation show that the proposed methods improve performance in human breathing detection and rate estimation.

This thesis presents significant advancements in the field of driver’s chest localization and breathing detection using FMCW radar. It introduces a neural network model for predicting the 3D location of the driver’s chest and a novel algorithm for detecting breathing patterns and localizing the chest position. These scientific breakthroughs contribute to the development of an adaptive safety system for level 3 and above autonomous driving within the IFAS project (FKZ 19A19009E).