Method for restoring human-body videothree-dimensional movement based on sided shadow and end node

A technology of terminal nodes and three-dimensional motion, which is applied in the field of video human three-dimensional motion restoration, can solve problems such as complex functions, large amount of calculation of objective functions, and optimization process trapped in local minimum values
CN101075351AInactive Publication Date: 2007-11-21ZHEJIANG UNIV
0 Cites 20 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
ZHEJIANG UNIV
Publication Date
2007-11-21
Estimated Expiration
Not applicable Β· inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A method for restoring video human body 3-D movement based on side shadow and tail end node includes picking up side shadow from video, making tail end node detection on side shadow, seeking optimum attitude enabling to explain positions of side shadow and tail end node on the image through analog annealing algorithm and connecting attitude of each frame to form continuous 3-D movement sequence after post-treatment.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of multimedia human body three-dimensional animation, in particular to a video human body three-dimensional motion recovery method based on silhouettes and terminal nodes. Background technique

[0002] Video-based 3D reconstruction of human body motion has a wide range of applications. It can play a role in optical 3D human motion capture in many occasions, and it can also play a role in situations where many optical human body capture systems cannot be applied.

[0003] Currently, there are two main directions for 3D reconstruction of human pose / motion based on video / image sequences: one based on learning.

[0004] One is based on the direction of learning. The learning input of the method in this direction is a series of pose vectors and their corresponding 2D images (generally speaking, some features extracted from 2D images). Corresponding functions of 2D images and pose vectors are obtained by learning. Afterw...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More