EUVIMEDEUVIMED entdecken
Crossref

A Comparative Study on Human Action Recognition Using Multiple Skeletal Features and Multiclass Support Vector Machine

Saiful Islam, Mohammad Farhad Bulbul, Md. Sirajul Islam

Machine Learning and Applications: An International Journal · 2018

DOI: 10.5121/mlaij.2018.5201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Applications: An International Journal, 2018. Verfasst von Saiful Islam und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a framework for human action recognition (HAR) by using skeletal features from depth video sequences. HAR has become a basis for applications such as health care, fall detection, human position tracking, video analysis, security applications, etc. Wehave used joint angle quaternion and absolute joint position to recognitionhuman action. We also mapped joint position on 𝑆𝐸(3) Lie algebra and fuse it with other features. This approach comprised of three steps namely (i) an automatic skeletal feature (absolute joint position and joint angle) extraction (ii) HAR by using multi-class Support Vector Machine and (iii) HAR by features fusion and decision fusion classification outcomes. The HAR methods are evaluated on two publicly available challenging datasets UTKinect-Action and Florence3D-Action datasets. The experimental results show that the absolute joint positionfeature is the best than other features and the proposed framework being highly promising compared to others existing methods.

Zitieren

APA

Islam, S., Bulbul, M. F., & Islam, M. S. (2018). A Comparative Study on Human Action Recognition Using Multiple Skeletal Features and Multiclass Support Vector Machine. Machine Learning and Applications: An International Journal. https://doi.org/10.5121/mlaij.2018.5201

Vancouver

Islam S, Bulbul MF, Islam MS. A Comparative Study on Human Action Recognition Using Multiple Skeletal Features and Multiclass Support Vector Machine. Machine Learning and Applications: An International Journal. 2018. doi:10.5121/mlaij.2018.5201

BibTeX
@article{Islam2018,
  author = {Islam, Saiful and Bulbul, Mohammad Farhad and Islam, Md. Sirajul},
  title = {A Comparative Study on Human Action Recognition Using Multiple Skeletal Features and Multiclass Support Vector Machine},
  journal = {Machine Learning and Applications: An International Journal},
  year = {2018},
  doi = {10.5121/mlaij.2018.5201}
}
Kostenlos starten →