EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Posture Estimation from Tactile Signals Using a Masked Forward Diffusion Model

Sanket Kachole iD, Bhagyashri Nayak, James Brouner iD, Ying Liu iD, Liucheng Guo iD, Dimitrios Makris iD

Sensors · 2025

DOI: 10.3390/s25164926 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Sanket Kachole und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Mathematics, Kingston University, London KT1 2EE, UK. Hauptthemen laut MEDLINE: Posture, Touch. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovate UK.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Utilizing tactile sensors embedded in intelligent mats is an attractive non-intrusive approach for human motion analysis. Interpreting tactile pressure 2D maps for accurate posture estimation poses significant challenges, such as dealing with data sparsity, noise interference, and the complexity of mapping pressure signals. Our approach introduces a novel dual-diffusion signal enhancement (DDSE) architecture that leverages tactile pressure measurements from an intelligent pressure mat for precise prediction of 3D body joint positions, using a diffusion model to enhance pressure data quality and a convolutional-transformer neural network architecture for accurate pose estimation. Additionally, we collected the pressure-to-posture inference technology (PPIT) dataset that relates pressure signals organized as a 2D array to Motion Capture data, and our proposed method has been rigorously evaluated on it, demonstrating superior accuracy in comparison to state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PostureTouchHumansNeural Networks, ComputerPressureAlgorithmsDiffusion

Stichwörter der Autor:innen

convolutional-transformer neural networkdiffusion modelsposture estimationtactile pressure maps

Autor:innen und Institutionen

  • School of Computer Science and Mathematics, Kingston University, London KT1 2EE, UK.
  • Department of Applied and Human Sciences, Kingston University, London KT1 2EE, UK.
  • Tangi0 Ltd. (TG0), 73-75 Upper Richmond Road, London SW15 2SR, UK.

ORCID-Profile: Sanket Kachole, James Brouner, Ying Liu, Liucheng Guo, Dimitrios Makris

Förderung

  • Innovate UK

Zitieren

APA

Kachole, S., Nayak, B., Brouner, J., Liu, Y., Guo, L., & Makris, D. (2025). Posture Estimation from Tactile Signals Using a Masked Forward Diffusion Model. Sensors. https://doi.org/10.3390/s25164926

Vancouver

Kachole S, Nayak B, Brouner J, Liu Y, Guo L, Makris D. Posture Estimation from Tactile Signals Using a Masked Forward Diffusion Model. Sensors. 2025. doi:10.3390/s25164926

BibTeX
@article{Kachole2025,
  author = {Kachole, Sanket and Nayak, Bhagyashri and Brouner, James and Liu, Ying and Guo, Liucheng and Makris, Dimitrios},
  title = {Posture Estimation from Tactile Signals Using a Masked Forward Diffusion Model},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25164926}
}
Kostenlos starten →