EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PoseNet++: A multi-scale and optimized feature extraction network for high-precision human pose estimation

Chao Lv iD, Geyao Ma

PLOS One · 2025

DOI: 10.1371/journal.pone.0326232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Chao Lv und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Deep Learning, Posture, Image Processing, Computer-Assisted. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human pose estimation (HPE) has made significant progress with deep learning; however, it still faces challenges in handling occlusions, complex poses, and complex multi-person scenarios. To address these issues, we propose PoseNet++, a novel approach based on a 3-stacked hourglass architecture, incorporating three key innovations: the multi-scale spatial pyramid attention hourglass module (MSPAHM), coordinate-channel prior convolutional attention (C-CPCA), and the PinSK Bottleneck Residual Module (PBRM). MSPAHM enhances long-range channel dependencies, enabling the model to better capture structural relationships between limb joints, particularly under occlusion. C-CPCA combines coordinate attention (CA) and channel prior convolutional attention (CPCA) to prioritize keypoints’ regions and reduce the confusion in complex multi-person scenarios. The PBRM improves pose estimation accuracy by optimizing the receptive field and convolutional kernel selection, thus enhancing the network’s feature extraction capabilities in multi-scale and complex poses. On the MPII validation set, PoseNet++ improves the PCKh score by 3.3% relative to the baseline 3-stacked hourglass network, while reducing the number of model parameters and the number of floating-point operations by 60.3% and 53.1%, respectively. Compared with other mainstream human pose estimation models in recent years, PoseNet++ achieves the state-of-the-art performance on the MPII, LSP, COCO and CrowdPose datasets. At the same time, the model complexity of PoseNet++ is much lower than that of methods with similar accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPostureImage Processing, Computer-AssistedHumansAlgorithmsNeural Networks, Computer

Autor:innen und Institutionen

  • College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China.

ORCID-Profile: Chao Lv

Förderung

  • Department of Science and Technology of Jilin Province

Zitieren

APA

Lv, C., & Ma, G. (2025). PoseNet++: A multi-scale and optimized feature extraction network for high-precision human pose estimation. PLOS One. https://doi.org/10.1371/journal.pone.0326232

Vancouver

Lv C, Ma G. PoseNet++: A multi-scale and optimized feature extraction network for high-precision human pose estimation. PLOS One. 2025. doi:10.1371/journal.pone.0326232

BibTeX
@article{Lv2025,
  author = {Lv, Chao and Ma, Geyao},
  title = {PoseNet++: A multi-scale and optimized feature extraction network for high-precision human pose estimation},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0326232}
}
Kostenlos starten →