EUVIMEDEUVIMED entdecken
Crossref

Informer-Based Joint Tracking and Trajectory Prediction of Maneuvering Radar Targets

Shihua Zhao, Cao Zeng, Minti Liu

IEEE Sensors Journal · 15.01.2026 · 26 (2) · 2471-2481

DOI: 10.1109/jsen.2025.3636604 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.01.2026. Verfasst von Shihua Zhao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tracking radar targets over extended time horizons remains challenging due to highly nonlinear and maneuverable motion patterns that lead to cumulative prediction errors. This work addresses the joint estimation of current states and future trajectory prediction for radar targets under incomplete and noisy measurements. We develop a rigorous error-theoretic framework that formally analyzes error propagation mechanisms in sequential prediction, demonstrating that incremental state prediction effectively suppresses systematic bias and cumulative error growth compared to absolute prediction. Guided by these theoretical insights, we propose principled design strategies including feature augmentation with Doppler and kinematic information and increased network capacity. We instantiate this theory-guided approach within the informer architecture, leveraging its efficient sequence-to-sequence capability to mitigate error accumulation while achieving O(L log L) complexity, and propose this informer-based radar maneuvering target tracking (MTT) and predicting framework (InforMTP). A synthetic dataset with randomized motion patterns and multimode dynamics is constructed to validate the framework. Experimental results demonstrate that the proposed method consistently achieves tighter error bounds and substantially outperforms the model-based and hybrid baselines in both prediction accuracy and convergence speed, particularly under complex maneuvering scenarios. The source code is available at: https://github.com/poem-flower/InforMTP.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhao, S., Zeng, C., & Liu, M. (2026). Informer-Based Joint Tracking and Trajectory Prediction of Maneuvering Radar Targets. IEEE Sensors Journal, 26(2), 2471-2481. https://doi.org/10.1109/jsen.2025.3636604

Vancouver

Zhao S, Zeng C, Liu M. Informer-Based Joint Tracking and Trajectory Prediction of Maneuvering Radar Targets. IEEE Sensors Journal. 2026;26(2):2471-2481. doi:10.1109/jsen.2025.3636604

BibTeX
@article{Zhao2026,
  author = {Zhao, Shihua and Zeng, Cao and Liu, Minti},
  title = {Informer-Based Joint Tracking and Trajectory Prediction of Maneuvering Radar Targets},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {2471--2481},
  doi = {10.1109/jsen.2025.3636604}
}
Kostenlos starten →