Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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

Inactive Publication Date: 2007-11-21
ZHEJIANG UNIV
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First, most of these methods project a complete human body patch model back to a 2D plane and then compare it with the 2D image, which will inevitably lead to a huge amount of calculation of the objective function, making the process of 3D reconstruction very inefficient; The function of the pose vector to the 2D image is very complicated, causing the optimization process to be easily trapped in a local minimum
[0006] In addition, most human motion 3D restoration methods are difficult to solve the problem of error accumulation and transmission
If the reconstruction result of a certain frame is wrong, the reconstruction results of the next frame will be wrong, and it is difficult to automatically recover from the error

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for restoring human-body videothree-dimensional movement based on sided shadow and end node
  • Method for restoring human-body videothree-dimensional movement based on sided shadow and end node
  • Method for restoring human-body videothree-dimensional movement based on sided shadow and end node

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] It is necessary to perform 3D restoration on a fencing video of the 2004 Athens Olympic Games, as shown in Figure 6, a frame in the video and the restored 3D movement posture in this frame. Below in conjunction with the concrete technical scheme described above illustrate the steps that this example implements, as follows:

[0077] (1) Using the previously described color model based on the separation of chromaticity and brightness, extract the silhouette of each frame in the video. Specifically, assuming that the camera is fixed and the background color model is known (generally, it can be obtained by taking several frames of pure background images), for a frame of image to be extracted from the silhouette, compare its color with the color of the corresponding pixel of the background model pixel by pixel, If the difference between the two is greater than a certain threshold, the pixel in the frame is considered to be the foreground. Note that when comparing two colors...

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

PUM

No PUM Login to View More

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.

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T15/70G06T13/40
Inventor 庄越挺肖俊陈成吴飞
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com