Single camera 3D human pose estimation: a review of current techniques

Yap Wooi Hen, Raveendran Paramesran

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

11 Citations (Scopus)

Abstract

Vision-based techniques to estimate 3D human pose from single camera are important in many applications like entertainment and games industries, sports science, gait analysis and video surveillance. While de-facto optical-based motion capture system is highly accurate in estimating 3D human pose, vision-based techniques offer better alternative because the latter are far cheaper and non-intrusive. In this paper, we review recent significant advances made in singlecamera 3D human pose estimation techniques. We discuss about challenges faced, typical image observations used, ways to address the challenges and highlighting limitations in state-ofthe-art. We conclude this paper with speculation of future research directions as well as open research problems.

Original languageEnglish
Title of host publicationInternational Conference for Technical Postgraduates 2009, TECHPOS 2009
DOIs
Publication statusPublished - 2009
Externally publishedYes
EventInternational Conference for Technical Postgraduates 2009 - Kuala Lumpur, Malaysia
Duration: 14 Dec 200915 Dec 2009
https://ieeexplore.ieee.org/xpl/conhome/5403229/proceeding (Proceedings)

Conference

ConferenceInternational Conference for Technical Postgraduates 2009
Abbreviated titleTECHPOS 2009
Country/TerritoryMalaysia
CityKuala Lumpur
Period14/12/0915/12/09
Internet address

Cite this