摘要
针对生命探测雷达回波信号的非线性、非平稳性和难以获得大量实验样本的实际问题,提出了一种基于EEMD奇异值和支持向量机的多人识别方法。通过对雷达回波信号进行EEMD分解,将信号自适应分解为若干个本征模态函数(IMF),然后对特征向量矩阵进行奇异值分解求出特征向量,最后将特征向量输入支持向量机的分类器进行模式识别,判断墙体后面的人体数量。实验结果表明,所提出的方法识别速度快,识别率高,可有效应用于生命探测雷达的人体数量识别,具有广阔的应用前景。
For the life detection radar echo signal is nonlinear and non-stationary, and its difficult to obtain a large number of experimental samples in fact, a multi people recognition method is proposed, which is based on EEMD singular values and sup ports vector machine. The radar echo signal is decomposed self-adaptively into several intrinsic mode function （IMF） and then the feature vector matrix is decomposed into feature vectors by singular value. And finally the feature vectors have been input a support vector machine classifier for pattern recognition, to determine the amount of body behind the wall. The experimental results show that the method proposed in this paper has high recognition speed and high recognition rate, and can be effectively used in human number recognition of life detection radar. It has broad application prospects.
出处
《电子技术应用》
北大核心
2014年第5期122-125,共4页
Application of Electronic Technique
基金
国家自然科学基金项目(61162007)
广西自然科学基金项目(2013GXNSFAA019323)
关键词
生命探测雷达
整体平均经验模态分解
奇异值分解
支持向量机
the life detection radar
ensemble empirical mode decomposition
singular value decomposition
support vector machine
