EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pedestrian POSE estimation using multi-branched deep learning pose net

Muhammad Alyas Shahid, Mudassar Raza, Muhammad Sharif, Reem Alshenaifi, Seifedine Kadry iD

PLOS ONE · 24.01.2025 · 20 (1) · e0312177

DOI: 10.1371/journal.pone.0312177 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 24.01.2025. Verfasst von Muhammad Alyas Shahid und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, COMSATS University Islamabad, Wah Campus, Islamabad, Pakistan. Hauptthemen laut MEDLINE: Deep Learning, Pedestrians, Posture. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Majmaah University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In human activity-recognition scenarios, including head and entire body pose and orientations, recognizing the pose and direction of a pedestrian is considered a complex problem. A person may be traveling in one sideway while focusing his attention on another side. It is occasionally desirable to analyze such orientation estimates using computer-vision tools for automated analysis of pedestrian behavior and intention. This article uses a deep-learning method to demonstrate the pedestrian full-body pose estimation approach. A deep-learning-based pre-trained supervised model multi-branched deep learning pose net (MBDLP-Net) is proposed for estimation and classification. For full-body pose and orientation estimation, three independent datasets, an extensive dataset for body orientation (BDBO), PKU-Reid, and TUD Multiview Pedestrians, are used. Independently, the proposed technique is trained on dataset CIFAR-100 with 100 classes. The proposed approach is meticulously tested using publicly accessible BDBO, PKU-Reid, and TUD datasets. The results show that the mean accuracy for full-body pose estimation with BDBO and PKU-Reid is 0.95%, and with TUD multiview pedestrians is 0.97%. The performance results show that the proposed technique efficiently distinguishes full-body poses and orientations in various configurations. The efficacy of the provided approach is compared with existing pretrained, robust, and state-of-the-art methodologies, providing a comprehensive understanding of its advantages.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPedestriansPostureHumansAlgorithms

Autor:innen und Institutionen

  • Department of Computer Science, COMSATS University Islamabad, Wah Campus, Islamabad, Pakistan.
  • Namal University, Mianwali, Pakistan.
  • Department of Information Technology, College of Computer Sciences and Information Technology, Majmaah University, Majmaah, Saudi Arabia.
  • Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon.
  • Noroff University College, Kristiansand, Norway.

ORCID-Profile: Seifedine Kadry

Förderung

  • Majmaah University

Zitieren

APA

Shahid, M. A., Raza, M., Sharif, M., Alshenaifi, R., & Kadry, S. (2025). Pedestrian POSE estimation using multi-branched deep learning pose net. PLOS ONE, 20(1), e0312177. https://doi.org/10.1371/journal.pone.0312177

Vancouver

Shahid MA, Raza M, Sharif M, Alshenaifi R, Kadry S. Pedestrian POSE estimation using multi-branched deep learning pose net. PLOS ONE. 2025;20(1):e0312177. doi:10.1371/journal.pone.0312177

BibTeX
@article{Shahid2025,
  author = {Shahid, Muhammad Alyas and Raza, Mudassar and Sharif, Muhammad and Alshenaifi, Reem and Kadry, Seifedine},
  title = {Pedestrian POSE estimation using multi-branched deep learning pose net},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {1},
  pages = {e0312177},
  doi = {10.1371/journal.pone.0312177}
}
Kostenlos starten →