雷达式生命探测仪中人体数量识别技术的研究

针对雷达式生命探测仪穿墙检测到人体的呼吸信号的非平稳特性,采用短时傅里叶变换、频谱图,对单人、多人的呼吸信号进行分析,并通过奇异值分解有效地提取特征矢量进行模式识别,能够成功地识别单人和多人.实验结果表明,基于短时傅里叶变换的奇异值分解法能够稳定、有效地提取特征矢量,从而达到对雷达式生命探测仪中人体数量的较准确地识别.

Study on the Technology to Recognize the Number of the People by Means of Life-Detector Based on Radar

To recognize the number of the people using the life-detector based on radar when penetrating the wall, a respiration signal identification method based on short time fourier transform (STFT) is presented in this paper. To fully utilize the nonstationary character of the respiration signal, STFT is employed to get the signal's time-frequency representation. Singular value decomposition (SVD) is then used in the spectrogram to extract feature vector for pattern identification. Single people and multi-people can be identified from the respiration sensed by the life-detector based on radar. Experimental results show that the method based on STFT and SVD is stable and efficient to identify the number of the people.