Measuring Glide-Reflection Symmetry in Human Movements Using Elastic Shape Analysis

Qiao Wang, Chaitanya Potaraju, Pavan Turaga

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

Abstract

Human bodies and movements exhibit inherent symmetry. However, an important class of everyday movements, such as walking, does not maintain symmetry at every time instance. The symmetry in these movements is a spatiotemporal glide-reflection symmetry. The ability to measure this type of symmetry will provide us opportunities for various computer-aided applications including health monitoring, rehabilitation, and athletic training. In this paper we propose a method that uses the tools from elastic shape analysis to provide continuous symmetry scores which measure the degree of glide-reflection symmetry in movements. These scores can be updated online after each frame, and easily combined to drive comprehensible feedback. Our preliminary experiment demonstrates that our symmetry scores can well distinguish between a normal gait and simulated stroke and Parkinsonian gaits. Our results also suggest that using the Riemannian elastic metric provides better scores than Euclidean approaches.

Original languageEnglish (US)
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PublisherIEEE Computer Society
Pages709-716
Number of pages8
Volume2017-July
ISBN (Electronic)9781538607336
DOIs
StatePublished - Aug 22 2017
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: Jul 21 2017Jul 26 2017

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
CountryUnited States
CityHonolulu
Period7/21/177/26/17

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Measuring Glide-Reflection Symmetry in Human Movements Using Elastic Shape Analysis'. Together they form a unique fingerprint.

Cite this