Combining 3D joints Moving Trend and Geometry property for human action recognition

Bangli Liu, Hui Yu, Xiaolong Zhou, Honghai Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

359 Downloads (Pure)

Abstract

Depth image based human action recognition has attracted many attentions due to the popularity of the depth sensors. However, accurate recognition still remains a challenge because of various object appearances, poses and video sequences. In this paper, a novel skeleton joints descriptor based on 3D Moving Trend and Geometry (3DMTG) property is proposed for human action recognition. Specifically, a histogram of 3D moving directions between consecutive frames for each joint is constructed to represent the 3D moving trend feature in spatial domain. The geometry information of joints in each frame is modelled by the relative motion with the initial status. The proposed feature descriptor is evaluated on two popular datasets. The experimental results demonstrate the superior performance of our method over the state-of-the-art methods, especially the higher recognition rates for complex actions.
Original languageEnglish
Title of host publicationIEEE Systems, Man, and Cybernetics Magazine
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)978-1509018970
ISBN (Print)978-1509018987
DOIs
Publication statusPublished - 9 Feb 2017
Event2016 IEEE International Conference on Systems, Man, and Cybernetics - Budapest, Hungary
Duration: 9 Oct 201612 Oct 2016

Conference

Conference2016 IEEE International Conference on Systems, Man, and Cybernetics
Abbreviated titleSMC 2016
Country/TerritoryHungary
CityBudapest
Period9/10/1612/10/16

Keywords

  • human action recognition
  • 3D moving trend
  • geometry property
  • three-dimensional displays
  • geometry
  • market research
  • feature extraction
  • histograms
  • skeleton
  • trajectory

Fingerprint

Dive into the research topics of 'Combining 3D joints Moving Trend and Geometry property for human action recognition'. Together they form a unique fingerprint.

Cite this