Real-time human action recognition using individual body part locations and local joints structure

Liqiang Du, Hong Chen, Shuli Mei, Qing Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

In this paper, we present a novel approach for real-time human action recognition using local joints structure and body part locations. Individual body part locations are global features that ignore the local structure information of the human body joints, which is also essential for accurate action recognition. To cope with this problem, we propose local joints structure as a complement, and combine the two features for posture description in our method. We then perform classification using a combination of dynamic time warping, Fourier temporal pyramid representation and linear SVM. Experiments results on three action datasets show that the proposed representation outperforms many existing skeletal representations.

Original languageEnglish
Title of host publicationProceedings - VRCAI 2016
Subtitle of host publication15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
Pages293-298
Number of pages6
ISBN (Electronic)9781450346924
DOIs
StatePublished - 3 Dec 2016
Externally publishedYes
Event15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2016 - Zhuhai, China
Duration: 3 Dec 20164 Dec 2016

Publication series

NameProceedings - VRCAI 2016: 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry
Volume1

Conference

Conference15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2016
Country/TerritoryChina
CityZhuhai
Period3/12/164/12/16

Keywords

  • Body part locations
  • Human action recognition
  • Local joints structure
  • SVMs

Fingerprint

Dive into the research topics of 'Real-time human action recognition using individual body part locations and local joints structure'. Together they form a unique fingerprint.

Cite this