基于QR分解的高分辨率快速算法

A FAST HIGH RESOLUTION METHOD BASED ON QR DECOMPOSITION

以MUSIC为代表的一类基于特征分解的高分辨谱估计方法由于具有优越的分辨性能而受到人们的普遍重视。然而,做特征分解运算量大,工程实现较困难,使这类方法应用于实际有困难。利用阵列输出协方差矩阵的特殊结构,本文提出一种基于QR分解的高分辨谱估计方法及其改进形式。这种方法在多数情况下性能与MUSIC方法相近,而运算量和算法复杂性却大大降低。

Many high resolution methods such as MUSIC rely on a signal subspace decomposition, which is conventionally accomplished by an eigendecomposition. However an eigendecomposi-tion is very computationally intensive and difficult to implement. In this paper, by using the special structure of the covariance matrix, a fast high resolution method based on QR decomposition is presented. In most case, the performance of the new method is similar to those of MUSIC method, but the new method has smaller computational complexity and easier for parallel implementation.