Monocular reconstruction of human translation in motion sequence by MTA

  • Authors:
  • Li Zhang;Ling Li

  • Affiliations:
  • Curtin University of Technology, Perth, WA;Curtin University of Technology, Perth, WA

  • Venue:
  • Proceedings of the 5th international conference on Computer graphics and interactive techniques in Australia and Southeast Asia
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

A motion trend analysis method is proposed to reconstruct human motion from un-calibrated monocular video. In this paper, relocation of human subject is the main concern, which is one of the most difficult parts in motion reconstruction and critically affects the accuracy of human posture generation. Numerical studies are conducted on experiments from synthetic and real video data to demonstrate the correctness of the recovered human translation in the proposed system.