基于超宽带雷达及支持向量机的灾后人体呼吸信号识别方法与试验研究

Compared with conventional radar, the ultra-wideband (UWB) radar has the advantages of high distance resolution, small blind spot at close range, strong penetration, and high target recognition rate. Therefore, it has been widely used in post-disaster Radar-based Life Detecting System. In order to identify and locate the trapped person using UWB radar, a method based on signal multi-feature extraction and support vector machine model for human respiratory signal recognition is proposed in this paper. Firstly, we use empirical mode decomposition, variational mode decomposition, and Hilbert transformation to extract the micro-Doppler characteristics of echo signals use Fourier transformation to extract the spectrum characteristics and use correlation analysis to obtain the correlation characteristics. Then, the signals are classified by a support vector machine model based on these signal features. As a result, the respiratory signal can be identified and the position of the human body can be located. The experimental results obtained from different scenes show that the proposed method can effectively identify the human body which is shielded by brick walls and floor slabs, and the location of the human body can be determined at the same time.