High Resolution Direction of Arrival Estimation Based on Covariance Fitting Estimation of Signal Parameters by Rotational Invariance Technique Algorithm

Spare representation based direction of arrival (DOA) estimation algorithms have the merits of high resolution and good adaptability to coherent signals, while they suffer from the shortages of depending on prior information and off-grid problem. In order to get high DOA estimation resolution and avoid the shortcomings of spare representation algorithms, covariance fitting estimation of signal parameters by rotational invariance technique (ESPRIT) algorithm is proposed in this paper. Firstly, covariance fitting criterion is converted into a semi-definite programming problem solved by convex optimization. As a result, a signal covariance matrix which is closer to theoretical value is obtained. Then, eigen decomposition of the estimated signal covariance matrix is conducted and the number of signals is estimated through the differences between eigenvalues of signal subspace and noise subspace. Finally, rotational invariance technique of signal subspace is used to estimate DOA. Simulation experiments have proved the validity of the method. Compared with traditional ESPRIT algorithm, the proposed algorithm has higher DOA estimation resolution and is slightly affected by coherent signals. It is also superior to spare representation algorithms for independence of prior information and avoidance of the off-grid problem. © 2017, Shanghai Jiao Tong University Press. All right reserved.