一种未知信源数的高分辨DOA估计算法

Algorithm on High Resolution DOA Estimation without Sources Number

众多性能优良的超分辨波达方向(DOA)估计算法通常需要预先判定信源数目,然而,现有的信源数估计算法在有限采样快拍条件下,估计性能随着信噪比的降低而下降,错误概率也相应增加,最终导致DOA估计失败。该文提出一种超分辨的DOA估计算法,此算法不需要预判信源个数和进行特征值分解,同时在时变环境中,针对快拍数较少的情况下,依然保持较高的角度分辨能力,可以被认为是综合了Capon法和MUSIC法的优点。通过对实验数据和实测数据的计算机仿真及性能分析可得,与传统算法相比较,该算法有很好的鲁棒性和可行性。

Many of the super resolution DOA（Direction-Of-Arrival） estimation algorithms presume the number of signal sources. Since the sample snapshot is limited, however, the available algorithms on source number estimation may fail at lower SNR. In this paper, a novel algorithm for high resolution DOA estimation is proposed, which not only skips sources number estimation and EVD, but also behaves satisfactorily with a few snapshot, it may be viewed as a combination of merit of conventional Capon and MUSIC method. The algorithm＇s feasibility and robustness are analyzed and verified by the simulation and actual experiment data.