2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter

Abstract In this paper, we consider the 2-D direction-of-arrival (DOA) tracking problem. The signals are captured by a uniform spherical array and therefore can be analyzed in the spherical harmonics domain. Exploiting the sparsity of source DOAs in the whole angular region, we propose a novel DOA t...

Full description

Bibliographic Details
Main Authors:	Qinghua Huang, Jingbiao Huang, Kai Liu, Yong Fang
Format:	Article
Language:	English
Published:	SpringerOpen 2018-04-01
Series:	EURASIP Journal on Advances in Signal Processing
Subjects:	2-D direction-of-arrival (DOA) tracking Spherical array Transition probabilities (TP) model Variational sparse Bayesian learning (VSBL) Kalman filter (KF)
Online Access:	http://link.springer.com/article/10.1186/s13634-018-0541-0

id	doaj-707cea8720bc4b93baaa56f6aa810caa
record_format	Article
spelling	doaj-707cea8720bc4b93baaa56f6aa810caa2020-11-25T00:26:00ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802018-04-012018111410.1186/s13634-018-0541-02-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filterQinghua Huang0Jingbiao Huang1Kai Liu2Yong Fang3Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai UniversityKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai UniversityKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai UniversityKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai UniversityAbstract In this paper, we consider the 2-D direction-of-arrival (DOA) tracking problem. The signals are captured by a uniform spherical array and therefore can be analyzed in the spherical harmonics domain. Exploiting the sparsity of source DOAs in the whole angular region, we propose a novel DOA tracking method to estimate the source locations and trace their trajectories by using the variational sparse Bayesian learning (VSBL) embedded with Kalman filter (KF). First, a transition probabilities (TP) model is used to build the state transition process, which assumes that each source moves to its adjacent grids with equal probability. Second, the states are estimated by KF in the variational E-step of the VSBL and the variances of the state noise and measurement noise are learned in the variational M-step of the VSBL. Finally, the proposed method is extended to deal with the off-grid tracking problem. Simulations show that the proposed method has higher accuracy than VSBL and KF methods.http://link.springer.com/article/10.1186/s13634-018-0541-02-D direction-of-arrival (DOA) trackingSpherical arrayTransition probabilities (TP) modelVariational sparse Bayesian learning (VSBL)Kalman filter (KF)
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Qinghua Huang Jingbiao Huang Kai Liu Yong Fang
spellingShingle	Qinghua Huang Jingbiao Huang Kai Liu Yong Fang 2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter EURASIP Journal on Advances in Signal Processing 2-D direction-of-arrival (DOA) tracking Spherical array Transition probabilities (TP) model Variational sparse Bayesian learning (VSBL) Kalman filter (KF)
author_facet	Qinghua Huang Jingbiao Huang Kai Liu Yong Fang
author_sort	Qinghua Huang
title	2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter
title_short	2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter
title_full	2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter
title_fullStr	2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter
title_full_unstemmed	2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter
title_sort	2-d doa tracking using variational sparse bayesian learning embedded with kalman filter
publisher	SpringerOpen
series	EURASIP Journal on Advances in Signal Processing
issn	1687-6180
publishDate	2018-04-01
description	Abstract In this paper, we consider the 2-D direction-of-arrival (DOA) tracking problem. The signals are captured by a uniform spherical array and therefore can be analyzed in the spherical harmonics domain. Exploiting the sparsity of source DOAs in the whole angular region, we propose a novel DOA tracking method to estimate the source locations and trace their trajectories by using the variational sparse Bayesian learning (VSBL) embedded with Kalman filter (KF). First, a transition probabilities (TP) model is used to build the state transition process, which assumes that each source moves to its adjacent grids with equal probability. Second, the states are estimated by KF in the variational E-step of the VSBL and the variances of the state noise and measurement noise are learned in the variational M-step of the VSBL. Finally, the proposed method is extended to deal with the off-grid tracking problem. Simulations show that the proposed method has higher accuracy than VSBL and KF methods.
topic	2-D direction-of-arrival (DOA) tracking Spherical array Transition probabilities (TP) model Variational sparse Bayesian learning (VSBL) Kalman filter (KF)
url	http://link.springer.com/article/10.1186/s13634-018-0541-0
work_keys_str_mv	AT qinghuahuang 2ddoatrackingusingvariationalsparsebayesianlearningembeddedwithkalmanfilter AT jingbiaohuang 2ddoatrackingusingvariationalsparsebayesianlearningembeddedwithkalmanfilter AT kailiu 2ddoatrackingusingvariationalsparsebayesianlearningembeddedwithkalmanfilter AT yongfang 2ddoatrackingusingvariationalsparsebayesianlearningembeddedwithkalmanfilter
_version_	1725346534881492992

2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter

Similar Items