Human motion estimation from a reduced marker set

Guodong Liu, Jingdan Zhang, Wei Wang, Leonard McMillan

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

39 Scopus citations


Motion capture data from human subjects exhibits considerable redundancy. In this paper, we propose novel methods for exploiting this redundancy. In particular, we set out to find a subset of motion-capture markers that are able to provide fast and high-quality predictions of the remaining markers. We then develop a model that uses this reduced marker set to predict the others. We demonstrate that this subset of original markers is sufficient to capture subtle variations in human motion. We take a data-driven modeling approach to learn piecewise local linear models from a marker-based training set. We first divide motion sequences into segments of low dimensionality. We then retrieve a feature vector from each of the motion segments and use these feature vectors as modeling primitives to cluster the segments into a hierarchy of local linear models via a divisive clustering method. The selection of an appropriate linear model for reconstruction of a full-body pose is determined automatically via a classifier driven by a reduced marker set. After offline training, our method can quickly reconstruct full-body human motion using a reduced marker set without storing and searching the large database. We also demonstrate our method's ability to generalize over a variety of motions from multiple subjects.

Original languageEnglish (US)
Title of host publicationProceedings I3d 2006 - ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
PublisherAssociation for Computing Machinery
Number of pages8
ISBN (Print)159593295X, 9781595932952
StatePublished - 2006
EventI3d 2006 - ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games - Redwood City, CA, United States
Duration: Mar 14 2006Mar 17 2006

Publication series

NameProceedings of the Symposium on Interactive 3D Graphics


OtherI3d 2006 - ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
Country/TerritoryUnited States
CityRedwood City, CA

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Human motion estimation from a reduced marker set'. Together they form a unique fingerprint.

Cite this