Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

doi:10.23919/JSEE.2021.000115

Journal of Systems Engineering and Electronics ›› 2021, Vol. 32 ›› Issue (6): 1354-1363.doi: 10.23919/JSEE.2021.000115

收稿日期:2021-02-19 出版日期:2022-01-05 发布日期:2022-01-05

Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

Ying CHEN(), Xiang WANG*(), Zhitao HUANG()

¹ State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China

Received:2021-02-19 Online:2022-01-05 Published:2022-01-05
Contact: Xiang WANG E-mail:chenying_nudt@163.com;christopherwx@163.com;tald_paper@163.com
About author:|CHEN Ying was born in 1995. She is a Ph.D. student in the State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology. Her research interests are array signal processing and deep learning. E-mail: chenying_nudt@163.com||WANG Xiang was born in 1985. He received his B.S. and Ph.D. degrees in information and communication engineering in 2007 and 2013, respectively, from the College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, China. Currently, he is a lecturer in the National University of Defense Technology, Changsha, Hunan, China His research interests include blind signal separation and non-cooperative signal processing in radar and communication applications. E-mail: christopherwx@163.com||HUANG Zhitao was born in 1976. He received his B.S. and Ph.D. degrees in information and communication engineering in 1998 and 2003, respectively, from the College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, China. He is now a professor with the College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, China. His research interests include radar and communication signal processing, and array signal processing. E-mail: tald_paper@163.com
Supported by:
This work was supported by the Program for Innovative Research Groups of the Hunan Provincial Natural Science Foundation of China (2019JJ10004)

摘要/Abstract

Abstract:

Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival (DOA) estimation problem. These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions. This paper presents an effective DOA estimation approach based on a deep residual network (DRN) for the underdetermined case. We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays. We then provide the input feature to the trained DRN to construct the super resolution spectrum. The DRN learns the mapping relationship between the input feature and the spatial spectrum by training. The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency, independence of source sparseness and adaptive capacity to non-ideal conditions (e.g., low signal to noise ratio, short bit sequence). Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.

Key words: direction-of-arrival (DOA) estimation, underdetermined condition, deep residual network (DRN), time delay, covariance matrix

. [J]. Journal of Systems Engineering and Electronics, 2021, 32(6): 1354-1363.

Ying CHEN, Xiang WANG, Zhitao HUANG. Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network[J]. Journal of Systems Engineering and Electronics, 2021, 32(6): 1354-1363.

图/表 13

参考文献 32

1	VEEN B V, BUCKLEY K M Beamforming: a versatile approach to spatial filtering. IEEE ASSP Magazine, 2002, 5 (2): 4- 24.
2	LIU Z M, HUANG Z T, ZHOU Y Y An efficient maximum likelihood method for direction-of-arrival estimation via sparse Bayesian learning. IEEE Trans. on Wireless Communications, 2012, 11 (10): 1- 11. doi: 10.1109/TWC.2012.090312.111912
3	SCHMIDT R, SCHMIDT R O Multiple emitter location and signal parameter estimation. IEEE Trans. on Antennas and Propagation, 1986, 34 (3): 276- 280. doi: 10.1109/TAP.1986.1143830
4	ROY R, PAULRAJ A, KAILATH T ESPRIT—a subspace rotation approach to estimation of parameters of cisoids in noise. IEEE Trans. on Acoustics, Speech and Signal Processing, 1986, 34 (5): 1340- 1342. doi: 10.1109/TASSP.1986.1164935
5	YIN J H, CHEN T Q Direction-of-arrival estimation using a sparse representation of array covariance vectors. IEEE Trans. on Signal Processing, 2011, 59 (9): 4489- 4493. doi: 10.1109/TSP.2011.2158425
6	LIU Z M, HUANG Z T, ZHOU Y Y Sparsity-inducing direction finding for narrowband and wideband signals based on array covariance vectors. IEEE Trans. on Wireless Communications, 2013, 12 (8): 3896- 3907.
7	PORAT B, FRIEDLANDER B Direction finding algorithms based on high-order statistics. IEEE Trans. on Signal Processing, 1991, 39 (9): 2016- 2024. doi: 10.1109/78.134434
8	CHEVALIER P, FERREOL A, ALBERA L High-resolution direction finding from higher order statistics: the 2q-MUSIC algorithm. IEEE Trans. on Signal Processing, 2006, 54 (8): 2986- 2997. doi: 10.1109/TSP.2006.877661
9	LIU T H, MENDEL J M A subspace-based direction finding algorithm using fractional lower order statistics. IEEE Trans. on Signal Processing, 2001, 49 (8): 1605- 1613. doi: 10.1109/78.934131
10	RICKARD S, DIETRICH F. DOA estimation of many W-disjoint orthogonal sources from two mixtures using DUET. Proc. of the IEEE 10th Workshop on Statistical Signal and Array Processing, 2000: 311−314.
11	TADAION A A, DERAKHTIAN M, GAZOR S A fast multiple-source detection and localization array signal processing algorithm using the spatial filtering and ML approach. IEEE Trans. on Signal Processing, 2007, 55 (5): 1815- 1827. doi: 10.1109/TSP.2006.890819
12	ZHENG Z, LI G J, TENG Y L 2D DOA estimator for multiple coherently distributed sources using modified propagator. Circuits Systems & Signal Processing, 2012, 31 (1): 255- 270.
13	HAN P, WANG D M, CUI W J, et al Underdetermined direction of arrival estimation of non-circular signals via matrix completion in nested array. IEEE Access, 2019, 7, 183717- 183728. doi: 10.1109/ACCESS.2019.2960533
14	YADAV S K, GEORGE N V Underdetermined direction-of-arrival estimation using sparse circular arrays on a rotating platform. IEEE Signal Processing Letters, 2021, 28, 862- 866. doi: 10.1109/LSP.2021.3068713
15	HE W, MOTLICEK P, ODOBEZ J M. Deep neural networks for multiple speaker detection and localization. Proc. of the IEEE International Conference on Robotics and Automation, 2018: 74−79.
16	HUANG H J, YANG J, HUANG H, et al Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system. IEEE Trans. on Vehicular Technology, 2018, 67 (9): 8549- 8560. doi: 10.1109/TVT.2018.2851783
17	MA N, MAY T, BROWN G J Exploiting deep neural networks and head movements for robust binaural localization of multiple sources in Reverberant environments. IEEE Trans. on Audio Speech and Language Processing, 2017, 7 (19): 123- 132.
18	LIU Z M, ZHANG C W, YU P S Direction-of-arrival estimation based on deep neural networks with robustness to array imperfections. IEEE Trans. on Antennas and Propagation, 2018, 66 (12): 7315- 7327. doi: 10.1109/TAP.2018.2874430
19	ABEYWICKRAMA S, JAYASINGHE L, FU H. RF-based direction finding of UAVs using DNN. Proc. of the IEEE International Conference on Communication Systems, 2018: 903−912.
20	XIANG H H, CHEN B X, YANG M L Altitude measurement based on characteristics reversal by deep neural network for VHF radar. IET Radar, Sonar & Navigation, 2019, 13 (1): 98- 103.
21	XIANG H H, CHEN B X, YANG T Improved de-multipath neural network models with self-paced feature-to-feature learning for DOA estimation in multipath environment. IEEE Trans. on Vehicular Technology, 2020, 69 (5): 5068- 5078. doi: 10.1109/TVT.2020.2977894
22	XIANG H H, CHEN B X, YANG M L, et al A novel phase enhancement method for low-angle estimation based on supervised DNN learning. IEEE Access, 2019, 7 (4): 329- 336.
23	WU L L, LIU Z M, HUANG Z T Deep convolution network for direction of arrival estimation with sparse prior. IEEE Signal Processing Letters, 2019, 26 (11): 1688- 1692. doi: 10.1109/LSP.2019.2945115
24	GUO Y, ZHANG Z, HUANG Y Z DOA estimation method based on cascaded neural network for two closely spaced sources. IEEE Signal Processing Letters, 2020, 27 (1): 570- 574.
25	CHEN Y, WANG C, XIONG K L. Synchronized perturbation elimination and DOA estimation via signal selection mechanism and parallel deep capsule networks in multipath environment. Chinese Journal of Aeronautics, 2021. DOI: 10.1016/J.CJA.2021.01.016.
26	CONGEDO M, GOUY-PAILLER C, JUTTEN C On the blind source separation of human electroencephalogram by approximate joint diagonalization of second order statistics. Clinical Neurophysiology, 2008, 119 (12): 2677- 2686. doi: 10.1016/j.clinph.2008.09.007
27	LATHAUWER L D, CASTAING J Blind identification of underdetermined mixtures by simultaneous matrix diagonalization. IEEE Trans. on Signal Processing, 2008, 56 (3): 1096- 1105. doi: 10.1109/TSP.2007.908929
28	ZHU L W, WANG Y, WANG X, et al. Underdetermined direction-of-arrival estimation from second order statistics. Proc. of the 7th International Congress on Image and Signal Processing, 2014: 989−993.
29	CHEN Y, XIONG K L, HUANG Z T. Robust direction-of-arrival estimation via sparse representation and deep residual convolutional network for co-prime arrays. Proc. of the IEEE 3rd International Conference on Electronic Information and Communication Technology, 2020: 514−519.
30	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770−778.
31	SEGHOUANE A K Asymptotic bootstrap corrections of AIC for linear regression models. Signal Processing, 2010, 90 (1): 217- 224. doi: 10.1016/j.sigpro.2009.06.010
32	STOICA P, SELEN Y Model-order selection: a review of information criterion rules. IEEE Signal Processing Magazine, 2004, 21 (4): 36- 47. doi: 10.1109/MSP.2004.1311138

Parameter	$\boldsymbol{\bar R}$ -DRN	${\boldsymbol{\bar R}_r}$ -DRN	${\boldsymbol{\bar R}_{sp}}$ -DRN
Input dimension	$2 \times 36$	$1 \times 12$	$2 \times 121$
Total parameters	14 291	5 354	45 146
Training time	10 min 25 s	3 min 15 s	25 min 10 s

Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 32

相关文章 0

编辑推荐

Metrics

本文评价