EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks

Hongxia Wang, Yang Liu iD, Zhenkai Nie

PLOS One · 2025

DOI: 10.1371/journal.pone.0322722 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Hongxia Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Shenyang Ligong University, Shenyang, Liaoning, China. Hauptthemen laut MEDLINE: Pedestrians, Neural Networks, Computer, Walking. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nature Science Foundation of Liaoning Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate pedestrian trajectory prediction is crucial for applications such as autonomous driving and crowd surveillance. This paper proposes the OV-SKTGCNN model, an enhancement to the Social-STGCNN model, aimed at addressing its low prediction accuracy and limitations in dealing with forces between pedestrians. By rigorously dividing monocular and binocular overlapping visual regions and utilizing different influence factors, the model pedestrian interactions more realistically. The Kolmogorov-Arnold Networks (KANs) combined with Temporal Convolutional Networks (TCNs) greatly improve the ability to extract temporal features. Experimental results on the ETH and UCY datasets demonstrate that the model reduces the Final Displacement Error (FDE) by an average of 23% and the Average Displacement Error (ADE) by 18% compared to Social-STGCNN. The proposed OV-SKTGCNN model demonstrates improved prediction accuracy and better captures the subtleties of pedestrian movements.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PedestriansNeural Networks, ComputerWalkingHumansAlgorithmsModels, Theoretical

Autor:innen und Institutionen

  • School of Information Science and Engineering, Shenyang Ligong University, Shenyang, Liaoning, China.

ORCID-Profile: Yang Liu

Förderung

  • Nature Science Foundation of Liaoning Province

Zitieren

APA

Wang, H., Liu, Y., & Nie, Z. (2025). Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks. PLOS One. https://doi.org/10.1371/journal.pone.0322722

Vancouver

Wang H, Liu Y, Nie Z. Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks. PLOS One. 2025. doi:10.1371/journal.pone.0322722

BibTeX
@article{Wang2025,
  author = {Wang, Hongxia and Liu, Yang and Nie, Zhenkai},
  title = {Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0322722}
}
Kostenlos starten →