复合高斯噪声中知识辅助的贝叶斯Rao检测方法  

Knowledge-aided Bayesian Rao detection approach in compound Gaussian noise

作　　者：高永婵[1] 廖桂生[1] 朱圣棋[1] 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,陕西西安710071

出　　处：《西安电子科技大学学报》2013年第6期46-51,173,共7页Journal of Xidian University

基　　金：国家自然科学基金资助项目(61101249;61231017);国家973重点基础研究发展计划资助项目(2011CB707001);长江学者和创新团队发展计划资助项目(IRT0954)

摘　　要：在复合高斯噪声中进行目标检测通常使用渐进最大似然协方差矩阵,但其受训练样本数量的影响较大,并且忽略了协方差矩阵的先验分布.针对该问题,提出了知识辅助的贝叶斯Rao检测器.将复合高斯噪声下协方差矩阵建模为随机矩阵,其先验分布满足复值逆Wishart分布,然后辅助该先验分布,推导了协方差矩阵的最大后验估计,并基于该最大后验协方差矩阵提出Rao检测器.最后,通过蒙特卡洛仿真评估了复合高斯噪声中知识辅助的贝叶斯Rao检测器的检测性能.在复合高斯噪声背景下,当训练样本较少时,文中方法的检测性能优于传统的非贝叶斯检测器.An asymptotically likelihood covariance matrix is usually used to detect a target in compound Gaussian noise. However, it is influenced greatly by the training sample support, and it ignores the prior distribution of the eovariance matrix. For this problem, this paper proposes the knowledge-aided Bayesian Rao detection. The covariance matrix in compound Gaussian noise is modeled as a random matrix, the prior distribution of which satisfies the complex inverse Wishart distribution. With prior distribution, the maximum a-posterior estimation of the covariance matrix is derived. Then, Rao detection is obtained based on the maximum a-posterior estimation. Finally, the performance of the knowledge-aided Bayesian Rao detection approach is evaluated by Monte Carlo simulation. The simulation results show that the detection performance of the proposed approach outperforms the traditional detection approaches when the number of training samples is small in a complex Gaussian noise scenario.

关 键 词：复合高斯噪声 Rao检测 协方差矩阵 先验分布 

分 类 号：TN957.51[电子电信—信号与信息处理]