Near-field source localization algorithm using parallel factor analysis

被引：0

作者：

National Key Laboratory for Underwater Information Process and Control, Xi'an 710075, China ^{[1
]}

不详 ^{[2
]}

不详 ^{[3
]}

机构：

来源：

Tien Tzu Hsueh Pao | 2007年 / 10卷 / 1909-1915期

关键词：

Algorithms - Array processing - Computer simulation - Direction of arrival - Estimation - Least squares approximations - Mathematical models - Matrix algebra - Sensors - Two dimensional;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

An estimation algorithm for frequency, range, and two-dimensional (2-D) direction-of-arrival (DOA) of each near-field narrowband source is presented. Firstly, we propose a new cross-array; secondly, we compute some cumulants using the properly chosen sensor outputs, and form five Toeplitz matrices by re-using these cumulants, and construct the parallel factor (PARAFAC) analysis model in the cumulant domain; thirdly, we analyze the uniqueness of the model's low-rank decomposition, and estimate the source parameters via the decomposition. In comparison with the conventional methods, the proposed method efficiently uses the array aperture, and doesn't require pairing parameters. Finally, the simulation results are presented to validate the performance of the proposed method.

引用