基于多维特征融合的舰船目标识别技术研究  

Ship Target Identification Method Based on Multi-dimensional Signal Feature Fusion

作　　者：赵小龙[1] 祝佳磊[1] 刘勇勇[1] 赵震[1] 

机构地区：[1]中国人民解放军61541部队

出　　处：《军事通信技术》2016年第1期48-51,73,共5页Journal of Military Communications Technology

摘　　要：针对海上通信目标个体识别能力不强的问题,提出了一种基于多维信号特征融合的提取方法。首先分别在时域、频域和高阶谱域对截获的海上通信目标射频信号提取其多维特征,然后将提取的特征进行融合,运用支持向量机分类器对个体进行分类识别,并利用粒子群优化算法对支持向量机分类器参数进行优化。实验结果表明,采用基于多维信号特征融合的通信目标识别方法,可以达到良好的识别效果。Given the hard identification of the maritime communication target,a method based on multi-dimensional signal feature fusion was proposed.Firstly,the multi-dimensional features of RF signals were extracted from time domain,frequency domain and high order spectrum domain respectively,and then the features were fused.Finally,the individual was classified by Support Vector Machine（SVM）classifier based on Particle Swarm Optimization（PSO）algorithm.Experiment demonstrates that the method based on multi-dimensional signal feature fusion of communication target identification could achieve a good effect.

关 键 词：多维特征融合 舰船目标 识别 

分 类 号：TN971[电子电信—信号与信息处理]