Complex-valued Convolutional Neural Networks for Enhanced Radar Signal Denoising and Interference Mitigation

被引:27
作者
Fuchs, Alexander [1 ]
Rock, Johanna [1 ]
Toth, Mate [1 ,2 ]
Meissner, Paul [2 ]
Pernkopf, Franz [1 ]
机构
[1] Graz Univ Technol, Graz, Austria
[2] Infineon Technol Austria AG, Graz, Austria
来源
2021 IEEE RADAR CONFERENCE (RADARCONF21): RADAR ON THE MOVE | 2021年
关键词
D O I
10.1109/RadarConf2147009.2021.9455296
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
Autonomous driving highly depends on capable sensors to perceive the environment and to deliver reliable information to the vehicles' control systems. To increase its robustness, a diversified set of sensors is used, including radar sensors. Radar is a vital contribution of sensory information, providing high resolution range as well as velocity measurements. The increased use of radar sensors in road traffic introduces new challenges. As the so far unregulated frequency band becomes increasingly crowded, radar sensors suffer from mutual interference between multiple radar sensors. This interference must be mitigated in order to ensure a high and consistent detection sensitivity. In this paper, we propose the use of Complex-Valued Convolutional Neural Networks (CVCNNs) to address the issue of mutual interference between radar sensors. We extend previously developed methods to the complex domain in order to process radar data according to its physical characteristics. This not only increases data efficiency, but also improves the conservation of phase information during filtering, which is crucial for further processing, such as angle estimation. Our experiments show, that the use of CVCNNs increases data efficiency, speeds up network training and substantially improves the conservation of phase information during interference removal.
引用
收藏
页数:6
相关论文
共 26 条
[1]  
Bechter J., 2016, 2016 IEEE MTT S INT, P2
[2]  
Bechter J, 2017, EUROP RADAR CONF, P90, DOI 10.23919/EURAD.2017.8249154
[3]  
Bechter Jonathan, 2017, INT RADAR S P
[4]  
de Oliveira MLL, 2020, 2020 IEEE INTERNATIONAL RADAR CONFERENCE (RADAR), P630, DOI [10.1109/RADAR42522.2020.9114719, 10.1109/radar42522.2020.9114719]
[5]  
Fischer C., 2016, THESIS ULM U
[6]  
Fu S.-W., 2017, IEEE INT WORKS MACH, P1
[7]  
Fuchs J, 2020, 2020 IEEE INTERNATIONAL RADAR CONFERENCE (RADAR), P315, DOI [10.1109/RADAR42522.2020.9114641, 10.1109/radar42522.2020.9114641]
[8]   Enhanced Radar Imaging Using a Complex-Valued Convolutional Neural Network [J].
Gao, Jingkun ;
Deng, Bin ;
Qin, Yuliang ;
Wang, Hongqiang ;
Li, Xiang .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2019, 16 (01) :35-39
[9]   COMPLEX-DOMAIN BACKPROPAGATION [J].
GEORGIOU, GM ;
KOUTSOUGERAS, C .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1992, 39 (05) :330-334
[10]  
Hirose A, 2012, STUD COMPUT INTELL, V400, P1, DOI 10.1007/978-3-64227632-3