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

Higher-dimensional dynamic data processing method

A technology of dynamic data and processing methods, applied in image data processing, 3D image processing, instruments, etc., can solve problems such as inability to synthesize motion data

Inactive Publication Date: 2009-02-11
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can synthesize more realistic motion data, it cannot synthesize motion data that satisfies a certain motion constraint specified by the user. For example, the motion data that was originally just "walking" needs to be synthesized. then put down

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
  • Higher-dimensional dynamic data processing method
  • Higher-dimensional dynamic data processing method
  • Higher-dimensional dynamic data processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention uses a constrained Gaussian hidden variable model to analyze, synthesize and control high-dimensional dynamic data, and the specific implementation steps are further described below.

[0028] First, the high-dimensional data at time t , a non-linear mapping to the low-dimensional variable , where t is the time mark, indicating the time correlation between the data. D and d are the dimensions of the high-dimensional space and low-dimensional space, respectively. From the Gaussian process (Gaussian process):

[0029] p ( Y | X , A ) = 1 ( 2 π ) DN 2 | K | ...

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 provides a high-dimensional dynamic data processing method. Firstly, a low-dimensional variable corresponding to high-dimensional dynamic data is calculated; secondly, the map that lower-dimensional space spanned by the low-dimensional variable is mapped to the high-dimensional space where the high-dimensional data is positioned is calculated; finally, samples are acquired in the lower-dimensional space and are mapped to the high-dimensional space by utilizing the map to form new high-dimensional dynamic data. The high-dimensional dynamic data processing method obtains more vivid visual effect and can process dynamic textures in most natural scenes when being applied to the aspect of a dynamic texture image sequence, and can synthesize somatic movement data which is appointed and constrained by a user when being applied to the aspect for processing the three-dimensional human movement acquisition data.

Description

technical field [0001] The invention relates to a high-dimensional dynamic data processing method, in particular to the analysis, synthesis and control of dynamic texture image sequences and 3D human motion data. Background technique [0002] Dynamic data generally refers to a type of data that has a time series relationship between data units. Typical dynamic data include dynamic texture image sequences, 3D human motion data, etc. Due to the high dimensionality of these dynamic data, how to deal with these high-dimensional data has become a difficult point in various application problems. [0003] A dynamic texture image sequence refers to an image sequence that presents a statistical characteristic in time and space. Such as jumping flames, fluttering flags, etc. An image I whose length and width are m and n respectively m×n , which can be seen as R m×n A point in image space. The value of m×n is usually greater than 1000 (for example, for an image with a size of 35×...

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
IPC IPC(8): G06T11/00G06T15/00G06T15/04
Inventor 庞俊彪黄庆明蒋树强
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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