Towards recognizing Tai Chi - an initial experiment using wearable sensors

Kai Kunze, Michael Barry, Ernst A. Heinz, Paul Lukowicz, Dennis Majoe, Jürg Gutknecht

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

27 Citations (Scopus)

Abstract

Inexpensive wearable sensors are well-suited for the automatic recognition of many activities occuring in everyday life. But what about fast and involved movements such as those occuring in athletic sports? We tackle this question by studying the feasibility of using body-worn gyroscopes and acceleration sensors to recognize Tai Chi movements. To this end, we conducted an initial experiment with eight sensors each affixed to four different persons who repeatedly performed three distinct Tai Chi movements. The resulting data confirm that standard thresholding and pattern-matching techniques should suffice to automate the analysis and recognition of the movements. Moreover, the data also seem to allow for distinguishing between certain levels of expertise and quality in executing the movements.

Original languageEnglish
Title of host publicationIFAWC 2006 - 3rd International Forum on Applied Wearable Computing 2006, Proceedings
EditorsOtthein Herzog, Holger Kenn, Michael Lawo, Paul Lukowicz, Gerhard Troster
PublisherVDE Verlag GmbH
Pages183-188
Number of pages6
ISBN (Electronic)3800729547, 9783800729548
Publication statusPublished - 2006
Externally publishedYes
Event3rd International Forum on Applied Wearable Computing 2006, IFAWC 2006 - Bremen, Germany
Duration: 2006 Mar 152006 Mar 16

Publication series

NameIFAWC 2006 - 3rd International Forum on Applied Wearable Computing 2006, Proceedings

Conference

Conference3rd International Forum on Applied Wearable Computing 2006, IFAWC 2006
CountryGermany
CityBremen
Period06/3/1506/3/16

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Towards recognizing Tai Chi - an initial experiment using wearable sensors'. Together they form a unique fingerprint.

Cite this