Extraction method for extracting key frames of virtual human motion data

A technology of motion data and key frames, applied in image data processing, instruments, calculations, etc., can solve problems such as the influence of interference between convergence speed dimensions

Active Publication Date: 2017-03-15
SOUTHEAST UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the most popular method is to use optimization-based methods, such as Liu et al. using genetic algorithms to extract key frames (Liu X, Hao A, Zhao D. Optimization-based key frame extraction formotion capture animation [J]. The visual computer, 2013 ,29(1):85-95.), this kind of optimization-based algorithm has strong search ability, but its convergence speed is easily affected by the interference between dimensions

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
  • Extraction method for extracting key frames of virtual human motion data
  • Extraction method for extracting key frames of virtual human motion data
  • Extraction method for extracting key frames of virtual human motion data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further explained below in conjunction with the drawings.

[0046] In order to quickly extract the key frames of the virtual human motion data, the present invention first makes full use of the information of the motion data itself to quantize the multi-dimensional data into one-dimensional data containing the overall motion change degree information, and then uses this information and generates an initial Key frame set, and finally through optimization method to make the obtained key frame the optimal key frame set. Specific implementation methods such as figure 1 As shown, including the following steps:

[0047] Step 101: Quantify the multi-dimensional motion data of the virtual human into one-dimensional data.

[0048] The original motion data is multi-dimensional data, and it is not easy to directly determine the key frame from these data. This method converts the original motion data into a one-dimensional data, which can more directly show...

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

The invention discloses an extraction method for extracting the key frames of virtual human motion data. The method comprises the steps of quantizing the original multi-dimensional joint motion data of a virtual human body into a one-dimensional data sequence; determining the set of initial key frames based on the motion activity information contained in the one-dimensional data sequence; and optimizing key frames in the set of initial key frames as optimal key frames. According to the technical scheme of the extraction method for extracting the key frames of virtual human motion data, the analysis of motion data and the optimization of motion data are combined, so that key frames, as few as possible, are quickly and reasonably extracted out of original motion data. In the animation of the virtual human body, a reconstructed motion sequence, obtained through the motion synthesizing and editing of key frames or the data interpolation at the key frames, is relatively good in performance.

Description

Technical field [0001] The invention relates to the field of virtual reality, in particular to the field of virtual human motion data processing, and is used for the motion expression of the virtual human in a virtual scene. Background technique [0002] With the development of multimedia technology and the Internet, people have put forward higher requirements for media content represented by movies and games. Among them, virtual reality technology based on computer animation technology has developed rapidly, and is now widely used in related fields such as film and television production, game development, medicine, education and training, and has become one of the hotspots of computer science research. Virtual human skeleton animation is a very popular technology in the field of modern computer animation. With the use of modern motion capture equipment, it is now easier to obtain three-dimensional data reflecting the true state of human motion. These data help to improve the rea...

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): G06T7/20
CPCG06T2207/10016
Inventor 秦文虎王建鹏孙立博
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap