EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Radar UAV/Bird Trajectory Feature Classification Based on TCN-Transformer and the PC-TimeGAN Data Augmentation Framework

Fei Tong, Kun Zhang, Guisheng Liao, Lin Li iD, Jingwei Xu iD, Keting Jiang

Sensors · 20.04.2026 · 26 (8) · 2528

DOI: 10.3390/s26082528 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.04.2026. Verfasst von Fei Tong und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Radar Signal Processing, Xidian University, Xi'an 710071, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 14th Five-Year Plan Applied Innovation Pre-Research Project: "XXX UAV Target Detection and Recognition Technology, 14th Five-Year Plan Equipment Development Applied Innovation Pre-Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of scarce unmanned aerial vehicle (UAV) track samples, severe class imbalance, and high motion similarity between UAVs and birds in low-altitude radar recognition, this paper proposes a trajectory classification method integrating a TCN-Transformer model with a physics-constrained TimeGAN (PC-TimeGAN) data augmentation framework. Specifically, the PC-TimeGAN generates high-quality, kinematically compliant UAV trajectories to alleviate data scarcity and class imbalance. A multi-scale TCN-Transformer is then constructed to comprehensively extract features, utilizing multi-kernel dilated convolutions for local temporal correlations and self-attention mechanisms for global temporal dependencies, thereby improving the discrimination between UAV and bird trajectories with similar motion patterns. Furthermore, a joint loss function combining Focal Loss and Triplet Loss is employed to optimize the decision boundaries and feature space, enhancing model robustness and generalization. Experiments on a measured dataset demonstrate that, under the 15-dimensional input setting, the proposed method achieves a UAV recall of 80.00%, an FAR of 3.15%, a precision of 64.00%, and an F1-score of 0.7111. Compared to baseline methods (e.g., SVM, LSTM, GRU, Transformer, and 1D-CNN), the proposed approach significantly improves UAV recall under limited trajectory information while keeping the false-alarm rate of misclassifying birds as UAVs low. Ultimately, this method markedly enhances the comprehensive performance of rapid track-level target classification for low-altitude surveillance radars.

Schlagwörter

Stichwörter der Autor:innen

TimeGANTransformerUAV/bird classificationfew-shot learninglow-altitude surveillance radar

Autor:innen und Institutionen

  • National Key Laboratory of Radar Signal Processing, Xidian University, Xi'an 710071, China.
  • School of Automation, Northwestern Polytechnical University, Xi'an 710129, China.

ORCID-Profile: Lin Li, Jingwei Xu

Förderung

  • 14th Five-Year Plan Applied Innovation Pre-Research Project: "XXX UAV Target Detection and Recognition Technology
  • 14th Five-Year Plan Equipment Development Applied Innovation Pre-Research Project

Zitieren

APA

Tong, F., Zhang, K., Liao, G., Li, L., Xu, J., & Jiang, K. (2026). Radar UAV/Bird Trajectory Feature Classification Based on TCN-Transformer and the PC-TimeGAN Data Augmentation Framework. Sensors, 26(8), 2528. https://doi.org/10.3390/s26082528

Vancouver

Tong F, Zhang K, Liao G, Li L, Xu J, Jiang K. Radar UAV/Bird Trajectory Feature Classification Based on TCN-Transformer and the PC-TimeGAN Data Augmentation Framework. Sensors. 2026;26(8):2528. doi:10.3390/s26082528

BibTeX
@article{Tong2026,
  author = {Tong, Fei and Zhang, Kun and Liao, Guisheng and Li, Lin and Xu, Jingwei and Jiang, Keting},
  title = {Radar UAV/Bird Trajectory Feature Classification Based on TCN-Transformer and the PC-TimeGAN Data Augmentation Framework},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2528},
  doi = {10.3390/s26082528}
}
Kostenlos starten →