View-invariant full-body gesture recognition via multilinear analysis of voxel data

Abstract

This paper presents a gesture recognition framework using voxel data obtained through visual hull reconstruction from multiple cameras. View-invariant pose descriptors are extracted by projecting voxel data onto a low dimensional pose coefficient space using multilinear analysis. Gestures are then treated as sequences of pose descriptors and represented by… (More)
DOI: 10.1109/ICDSC.2009.5289411

14 Figures and Tables

Topics

  • Presentations referencing similar topics