Robust Radar Detection and Classification of Traffic Vehicles Based on Anchor-free CenterNet

被引:6
作者
Guo, Zuyuan [1 ]
Yi, Wei [1 ]
Wu, Yuanhang [1 ]
Luo, Tai [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Informat & Commun Engn, Chengdu, Sichuan, Peoples R China
来源
2021 6TH INTERNATIONAL CONFERENCE ON UK-CHINA EMERGING TECHNOLOGIES (UCET 2021) | 2021年
关键词
Range-Doppler; detection; classification; Center-Net; Anchor-free;
D O I
10.1109/UCET54125.2021.9674952
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Radar has been regarded as the enabling sensor technology to realize the intelligent transportation system. The current works in traffic radar mainly focus on detecting the target with fixed size. however, traffic scenarios consist of various targets with different sizes. Therefore, in this paper, we propose a CenterNet-based radar signal processing framework for detecting and classifying four types of traffic targets on the Range-Doppler map, and illustrate CenterNet can achieve higher detection rate, lower false alarm rate, and better classification performance with the help of the Anchor-free structure, shows the usability of CenterNet for radar detection and classification in traffic scenarios.
引用
收藏
页码:252 / 257
页数:6
相关论文
共 18 条
[11]  
Matsunami I, 2012, 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ICSPCS'2012)
[12]   Efficient non-maximum suppression [J].
Neubeck, Alexander ;
Van Gool, Luc .
18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS, 2006, :850-+
[13]   Range-Doppler Detection in Automotive Radar with Deep Learning [J].
Ng, Weichong ;
Wang, Guohua ;
Siddhartha ;
Lin, Zhiping ;
Dutta, Bhaskar Jyoti .
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[14]  
Paszke A, 2019, ADV NEUR IN, V32
[15]   LINEAR FMCW RADAR TECHNIQUES [J].
STOVE, AG .
IEE PROCEEDINGS-F RADAR AND SIGNAL PROCESSING, 1992, 139 (05) :343-350
[17]  
Winkler V, 2007, EUROP RADAR CONF, P165
[18]  
ZHOU X Y, 2019, arXiv