A Study on Radar Target Detection Based on Deep Neural Networks

被引:11
作者
Wang, Li [1 ]
Tang, Jun [1 ]
Liao, Qingmin [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
关键词
Sensor signals processing; convolutional neural network (CNN); deep learning; radar processing; target detector; CLASSIFICATION;
D O I
10.1109/LSENS.2019.2896072
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
Target detection is one of the most important radar applications widely used in practice. Target detection can be regarded as a kind of classification, which distinguishes whether the signal undertested consists of an echo from a target (target present) or just corresponds to the noise (target absent). The deep neural network (DNN) is a popular topic for classification and has successfully been applied in different fields of science. Recently, many researchers have proposed DNNs for radar applications. In this article, we analyze a possible application of DNN- for target detection in radar, DNN-based detectors are designed, and the performance of the detector is demonstrated by comparison with traditional target detectors.
引用
收藏
页数:4
相关论文
共 18 条
  • [11] Radar high-resolution range profiles target recognition based on stable dictionary learning
    Liu, Hong-wei
    Feng, Bo
    Chen, Bo
    Du, Lan
    [J]. IET RADAR SONAR AND NAVIGATION, 2016, 10 (02) : 228 - 237
  • [12] Mason E, 2017, IEEE RAD CONF, P1703, DOI 10.1109/RADAR.2017.7944481
  • [13] Mendis G. J., 2017, 2017 COGNITIVE COMMU
  • [14] Richards MA, 2005, FUNDAMENTALS RADAR S
  • [15] Deep Neural Network Initialization Methods for Micro-Doppler Classification With Low Training Sample Support
    Seyfioglu, Mehmet Saygin
    Gurbuz, Sevgi Zubeyde
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (12) : 2462 - 2466
  • [16] Simonyan K, 2015, Arxiv, DOI arXiv:1409.1556
  • [17] Szegedy C, 2015, PROC CVPR IEEE, P1, DOI 10.1109/CVPR.2015.7298594
  • [18] Wang C, 2017, INT CONF ACOUST SPEE, P2437, DOI 10.1109/ICASSP.2017.7952594