空间非平稳噪声下的信源数估计算法

Estimation of the Number of Signal Source in Spatially Nonstationary Noise

针对空间非平稳噪声环境下信源数估计问题,分析了利用特征向量正交性估计信源数方法存在的不足,并讨论了常见对角矩阵在消除非平稳噪声时存在的问题,提出了一种新的信源数估计算法。该算法先利用特殊构造的对角矩阵进行变换消除非平稳噪声影响,然后将Bootstrap和假设检验理论相结合估计信源数。该算法无需噪声分布模型假设,在低信噪比下有较好的估计性能,有一定实用价值。

A new estimation method of signal source number under the circumstances of spatially non-stationary noise was proposed on the basis of analyzing lack of a method with orthogonality of eigenvector and discussing the existing problem in eliminating the noise with common diagonally matrix. A transform-based covariance differencing algorithm was used to eliminate the noise, and then the number of signal source was determined by combining hypothesis testing with Bootstrap techniques. The algorithm has better estimation performance at low SNR and without assuming noise distribution model, and practical value to a certain extent.