EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RadarTCN: Lightweight Online Classification Network for Automotive Radar Targets Based on TCN

Yuan Li, Mengmeng Zhang, Hongyuan Jing iD, Zhi Liu

Sensors · 28.04.2024 · 24 (9) · 2813

DOI: 10.3390/s24092813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.04.2024. Verfasst von Yuan Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Control Engineering, North China University of Technology, Beijing 100144, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Nova Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automotive radar is one of the key sensors for intelligent driving. Radar image sequences contain abundant spatial and temporal information, enabling target classification. For existing radar spatiotemporal classifiers, multi-view radar images are usually employed to enhance the information of the target and 3D convolution is employed for spatiotemporal feature extraction. These models consume significant hardware resources and are not applicable to real-time applications. In this paper, RadarTCN, a novel lightweight network, is proposed that achieves high-accuracy online target classification using single-view radar image sequences only. In RadarTCN, 2D convolution and 3D-TCN are employed to extract spatiotemporal features sequentially. To reduce data dimensionality and computational complexity, a multi-layer max pooling down-sampling method is designed in a 2D convolution module. Meanwhile, the 3D-TCN module is improved through residual pruning and causal convolution is introduced for leveraging the performance of online target classification. The experimental results demonstrate that RadarTCN can achieve high-precision online target recognition for both range-angle and range-Doppler map sequences. Compared to the reference models on the CARRADA dataset, RadarTCN exhibits better classification performance, with fewer parameters and lower computational complexity.

Schlagwörter

Stichwörter der Autor:innen

TCNautomotive radar imagerange-Dopplerrange-angletarget classification

Autor:innen und Institutionen

  • School of Electrical and Control Engineering, North China University of Technology, Beijing 100144, China.
  • School of Information, North China University of Technology, Beijing 100104, China.
  • College of Robotics, Beijing Union University, Beijing 100101, China.

ORCID-Profile: Hongyuan Jing

Förderung

  • Beijing Nova Program

Zitieren

APA

Li, Y., Zhang, M., Jing, H., & Liu, Z. (2024). RadarTCN: Lightweight Online Classification Network for Automotive Radar Targets Based on TCN. Sensors, 24(9), 2813. https://doi.org/10.3390/s24092813

Vancouver

Li Y, Zhang M, Jing H, Liu Z. RadarTCN: Lightweight Online Classification Network for Automotive Radar Targets Based on TCN. Sensors. 2024;24(9):2813. doi:10.3390/s24092813

BibTeX
@article{Li2024,
  author = {Li, Yuan and Zhang, Mengmeng and Jing, Hongyuan and Liu, Zhi},
  title = {RadarTCN: Lightweight Online Classification Network for Automotive Radar Targets Based on TCN},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {9},
  pages = {2813},
  doi = {10.3390/s24092813}
}
Kostenlos starten →