Summary
International Conference on Emerging Technologies for Communications
2020
Session Number:P1
Session:
Number:P1-3
A Consideration on Accuracy Improvement in DOA Estimation of Two Targets with Deep Learning
Yuya KASE, Toshihiko NISHIMURA, Takeo OHGANE, Yasutaka OGAWA, Takanori SATO, Daisuke KITAYAMA, Yoshihisa KISHIYAMA,
pp.-
Publication Date:2020/12/2
Online ISSN:2188-5079
DOI:10.34385/proc.63.P1-3
PDF download
Summary:
In our previous studies on on-grid direction of arrival estimation using deep learning, it was shown that the estimation sometimes fails when a signal arrives at an angle near the grid border. In this paper, we propose a method of combining two DNNs, of which grids are staggered, in order to avoid the above problem. Simulation results show that the proposed method improves the estimation accuracy of the signal on the grid border.