上海交通大学学报(英文版) ›› 2011, Vol. 16 ›› Issue (5): 538-542.doi: 10.1007/s12204-011-1184-6

• 论文 • 上一篇    下一篇

Viewpoint Manipulation for Interactive Television by Using Human Pose
Estimation

 TONG Ming-lei (仝明磊)   

  1. (School of Computer and Information, Shanghai
    University of Electric Power, Shanghai 200090, China)
  • 收稿日期:2010-09-27 出版日期:2011-10-29 发布日期:2011-10-20
  • 通讯作者: TONG Ming-lei (仝明磊) E-mail:tongminglei@gmail.com
  • 基金资助:

    the Shanghai Municipal Education Commission Project (No.SDL10026)

Viewpoint Manipulation for Interactive Television by Using Human Pose
Estimation

 TONG Ming-lei (仝明磊)   

  1. (School of Computer and Information, Shanghai
    University of Electric Power, Shanghai 200090, China)
  • Received:2010-09-27 Online:2011-10-29 Published:2011-10-20
  • Contact: TONG Ming-lei (仝明磊) E-mail:tongminglei@gmail.com
  • Supported by:

    the Shanghai Municipal Education Commission Project (No.SDL10026)

摘要: Abstract:  In current interactive television
schemes, the viewpoints should be manipulated by the user. However,
there is no efficient method, to assist a user in automatically
identifying and tracking the optimum viewpoint when the user
observes the object of interest because many objects, most often
humans, move rapidly and frequently. This paper proposes a novel
framework for determining and tracking the virtual camera to best
capture the front of the person of interest (PoI). First, one PoI is
interactively chosen in a segmented 3D scene reconstructed by space
carving method. Second, key points of the human torso of the PoI are
detected by using a model-based method and the human's global motion
including rotation and translation is estimated by using a
close-formed method with 3 corresponding points. At the last step,
the front direction of PoI is tracked temporally by using the
unscented particle filter (UPF). Experimental results show that the
method can properly compute the front direction of the PoI and
robustly track the best viewpoints.

关键词: free viewpoint video, human pose estimation,
voxel space carving

Abstract: Abstract:  In current interactive television
schemes, the viewpoints should be manipulated by the user. However,
there is no efficient method, to assist a user in automatically
identifying and tracking the optimum viewpoint when the user
observes the object of interest because many objects, most often
humans, move rapidly and frequently. This paper proposes a novel
framework for determining and tracking the virtual camera to best
capture the front of the person of interest (PoI). First, one PoI is
interactively chosen in a segmented 3D scene reconstructed by space
carving method. Second, key points of the human torso of the PoI are
detected by using a model-based method and the human's global motion
including rotation and translation is estimated by using a
close-formed method with 3 corresponding points. At the last step,
the front direction of PoI is tracked temporally by using the
unscented particle filter (UPF). Experimental results show that the
method can properly compute the front direction of the PoI and
robustly track the best viewpoints.

Key words: free viewpoint video, human pose estimation,
voxel space carving

中图分类号: