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

Motion capture data segmentation method based on metric mds and improved oblique space distance

A space distance and data segmentation technology, applied in image data processing, image analysis, instruments, etc., can solve the problems of high complexity, high-dimensional data processing and analysis time-consuming and labor-intensive, and achieve high stability and accurate segmentation point set effect

Active Publication Date: 2018-02-13
DALIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Human body motion capture data is a kind of multi-dimensional data with high complexity, and most of the motion capture data are non-linear. It is time-consuming and laborious to directly process and analyze high-dimensional data. In order to reduce the difficulty of segmentation and maintain the original data Under the premise of topological structure and correlation, the present invention proposes a motion capture data segmentation method based on metric MDS and improved oblique space distance

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
  • Motion capture data segmentation method based on metric mds and improved oblique space distance
  • Motion capture data segmentation method based on metric mds and improved oblique space distance
  • Motion capture data segmentation method based on metric mds and improved oblique space distance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0074] The embodiments of the present invention are implemented on the premise of the technical solutions of the present invention, and detailed implementation methods and specific operation processes are given, but the protection scope of the present invention is not limited to the following embodiments.

[0075] Example The example is to select a group of sports (13_30.bvh) containing six sports types from the CMU database for verification. Such as figure 2 and image 3 shown, where image 3 The six graphs represent the six motion types of "jump", "side turn", "kick", "squat", "jog" and "stand".

[0076] Step 1: Read the motion sequence numbered 13-30 in the CMU database, a total of 2465 frames, each frame of 96-dimensional CHHANNELS data, use the metric MDS dimensionality reduction method to reduce its dimensionality, and obtain a characteristic curve reflecting the essence of motion, as Figure 4 shown.

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 human motion capture data segmentation method based on metric MDS and improved oblique space distance, including the following steps: S1: Perform multi-dimensional scale analysis on the original sequence to realize the mapping from high-dimensional original data to low-dimensional space; S2: In low-dimensional Draw a specified window in the space, and calculate the improved oblique spatial distance between the data in the specified window and each frame of the previous segment; S3: The final segmentation point set is obtained by performing similarity detection on the improved oblique spatial distance, and an independent Semantic motion fragments. On the premise of maintaining the correlation and topology of the original data, this method greatly improves the accuracy of data segmentation.

Description

technical field [0001] The invention relates to a human motion capture data segmentation method based on metric MDS and improved oblique space distance, which belongs to the technical field of computer image processing. Background technique [0002] In recent years, with the development of human motion capture technology, the application field of computer animation is also expanding. We use motion capture equipment to efficiently and quickly obtain realistic 3D human motion data, and apply the obtained data to various field. Human body motion is usually composed of multiple motions, and is complex and changeable. Therefore, it is not only complicated but also time-consuming and labor-intensive to directly process long-sequence motion capture data. Therefore, long motion sequences need to be segmented into segments with independent semantics for later reuse. [0003] Finding the segmentation features between different actions is the key to segmenting human motion sequences....

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 Patents(China)
IPC IPC(8): G06T7/215
Inventor 张强宋丹丹周东生魏小鹏
Owner DALIAN 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