EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MythPose: Enhanced Detection of Complex Poses in Thangka Figures

Yukai Xian iD, Te Shen, Yurui Lee, Ping Lan iD, Qijun Zhao, Liang Yan

Sensors · 2025

DOI: 10.3390/s25164983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Yukai Xian und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Tibet University, Lhasa 850000, China. Hauptthemen laut MEDLINE: Paintings, Image Processing, Computer-Assisted, Posture. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lhasa science and technology plan project, 2025 High-Level talent training project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thangka is a unique form of painting in Tibet, which holds rich cultural significance and artistic value. In Thangkas, in addition to the standard human form, there are also figures with multiple limbs. Existing human pose estimation methods are not well suited for keypoint detection of figures in Thangka paintings. This paper builds upon YOLOv11-Pose and introduces the Mamba structure to enhance the model’s ability to capture global features. A feature fusion module is employed to integrate both shallow and deep features, and a KAL loss function is proposed to alleviate the interference between keypoints of different body parts. In this study, a dataset of 6208 Thangka images is collected and annotated for Thangka keypoint detection, and data augmentation techniques are used to enhance the generalization of the dataset. Experimental results show that MythPose achieves 89.13% mAP@0.5, 92.51% PCK, and 87.22% OKS in human pose estimation tasks on Thangka images, outperforming the baseline model. This research not only provides a reference for the digital preservation of Thangka art but also offers insights for pose estimation tasks in other similar artworks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PaintingsImage Processing, Computer-AssistedPostureHumansTibetAlgorithms

Stichwörter der Autor:innen

MythPoseThangkaYOLOdeep learninghuman pose estimation

Autor:innen und Institutionen

  • School of Information Science and Technology, Tibet University, Lhasa 850000, China.
  • School of Humanities, Tibet University, Lhasa 850000, China.
  • College of Computer Science, Sichuan University, Chengdu 610065, China.

ORCID-Profile: Yukai Xian, Ping Lan

Förderung

  • Lhasa science and technology plan project
  • 2025 High-Level talent training project

Zitieren

APA

Xian, Y., Shen, T., Lee, Y., Lan, P., Zhao, Q., & Yan, L. (2025). MythPose: Enhanced Detection of Complex Poses in Thangka Figures. Sensors. https://doi.org/10.3390/s25164983

Vancouver

Xian Y, Shen T, Lee Y, Lan P, Zhao Q, Yan L. MythPose: Enhanced Detection of Complex Poses in Thangka Figures. Sensors. 2025. doi:10.3390/s25164983

BibTeX
@article{Xian2025,
  author = {Xian, Yukai and Shen, Te and Lee, Yurui and Lan, Ping and Zhao, Qijun and Yan, Liang},
  title = {MythPose: Enhanced Detection of Complex Poses in Thangka Figures},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25164983}
}
Kostenlos starten →