Human action recognition using multiple views: a comparative perspective on recent developments

  • Authors:
  • Michael B. Holte;Cuong Tran;Mohan M. Trivedi;Thomas B. Moeslund

  • Affiliations:
  • Aalborg Universtity, Aalborg, Denmark;University of California, San Diego, San Diego, CA, USA;University of California, San Diego, San Diego, CA, USA;Aalborg Universtity, Aalborg, Denmark

  • Venue:
  • J-HGBU '11 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a review and comparative study of recent multi-view 2D and 3D approaches for human action recognition. The approaches are reviewed and categorized due to their nature. We report a comparison of the most promising methods using two publicly available datasets: the INRIA Xmas Motion Acquisition Sequences (IXMAS) and the i3DPost Multi-View Human Action and Interaction Dataset. Additionally, we discuss some of the shortcomings of multi-view camera setups and outline our thoughts on future directions of 3D human action recognition.