Non-Contact Detection of Vital Signs with a Hybrid Feature Extraction Method using a UWB Radar Sensor

The ultra-wide band (UWB) radar sensor is widely used in Radar-based Life Detecting System for search and rescue due to its short detection time, high penetrating power and low energy consumption. However, performance of non-contact detection is limited in complex post-disaster environments due to the noise and clutter. In this paper, a hybrid feature extraction method based on Hilbert-Huang Transform (HHT), Fast Fourier Transform (FFT) and correlation analysis is proposed to obtain the echo signal features. Then a classification model based on support vector machine (SVM) is established to identify the respiratory information embedded in the echo signal. The experimental results show that the proposed method can accurately identify the location of human body through different obstacles.