YOLO-DoA: A New Data-Driven Method of DoA Estimation Based on YOLO Neural Network Framework

被引:7
|
作者
Fan, Rong [1 ,2 ]
Si, Chengke [2 ]
Yi, Wenchuan [2 ]
Wan, Qun [1 ]
机构
[1] Univ Elect Sci Technol China, Sch Informat Commun Engn, Chengdu 611731, Peoples R China
[2] Tong Fang Elect Sci Technol Co Ltd, Jiujiang 332000, Peoples R China
基金
中国国家自然科学基金;
关键词
Direction-of-arrival estimation; Estimation; Feature extraction; Uninterruptible power systems; Convolutional neural networks; Tensors; Neck; Sensor signal processing; array signal processing; convolutional neural network (CNN); deep learning; direction-of-arrival (DoA) estimation; OF-ARRIVAL ESTIMATION; CHANNEL ESTIMATION; PERFORMANCE;
D O I
10.1109/LSENS.2023.3241080
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Direction-of-arrival (DoA) estimation is one of the most promising technologies in array signal processing. Existing data-driven methods for DoA estimation are usually implemented by classification networks, which suffer from insufficient utilization about features of sources and require spectral peak-search stage. In this letter, we reframe DoA estimation as a target detection problem and propose a novel DoA estimation approach on the basis of the you only look once v3 (YOLOv3) framework, namely YOLO-DoA. DoAs of sources with confidence scores are directly predicted from the spectrum proxy with YOLO-DoA and an end-to-end estimation is realized. By combining squeeze-and-excitation operation, cross stage partial connections, and an improved loss function for bounding box regression, the performance of YOLO-DoA is enhanced. Simulation results demonstrate that the proposed approach outperforms several state-of-the-art methods in terms of network size, computational cost, prediction time, and accuracy of DoA estimation.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] DOA Estimation Method based on Neural Network
    Ping, Zhang
    2015 10TH INTERNATIONAL CONFERENCE ON P2P, PARALLEL, GRID, CLOUD AND INTERNET COMPUTING (3PGCIC), 2015, : 828 - 831
  • [2] DOA estimation based on neural network for HFGWR
    School of Electronic Information, Wuhan University, Wuhan 430079, China
    Dianzi Yu Xinxi Xuebao, 2008, 2 (339-342):
  • [3] DEEP AUGMENTED MUSIC ALGORITHM FOR DATA-DRIVEN DOA ESTIMATION
    Merkofer, Julian P.
    Revach, Guy
    Shlezinger, Nir
    van Sloun, Ruud J. G.
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3598 - 3602
  • [4] DOA Estimation Method Based on Improved Deep Convolutional Neural Network
    Zhao, Fangzheng
    Hu, Guoping
    Zhan, Chenghong
    Zhang, Yule
    SENSORS, 2022, 22 (04)
  • [5] A New Neural Network DOA Estimation Technique Based on Subarray Beamforming
    Caylar, S.
    ICEAA: 2009 INTERNATIONAL CONFERENCE ON ELECTROMAGNETICS IN ADVANCED APPLICATIONS, VOLS 1 AND 2, 2009, : 732 - 734
  • [6] Graph Neural Network-Based DOA Estimation Method Exploring Training Data Association
    Liu, Ke
    Cui, Hengchen
    Ma, Junda
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2025, : 3641 - 3658
  • [7] A Gridless DOA Estimation Method Based on Convolutional Neural Network With Toeplitz Prior
    Wu, Xiaohuan
    Yang, Xu
    Jia, Xiaoyuan
    Tian, Feng
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 1247 - 1251
  • [8] NEURAL NETWORK-BASED COMPRESSION FRAMEWORK FOR DOA ESTIMATION EXPLOITING DISTRIBUTED ARRAY
    Pavel, Saidur R.
    Zhang, Yimin D.
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 4943 - 4947
  • [9] Super resolution DOA estimation based on deep neural network
    Wanli Liu
    Scientific Reports, 10
  • [10] Super resolution DOA estimation based on deep neural network
    Liu, Wanli
    SCIENTIFIC REPORTS, 2020, 10 (01)