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

Human skeleton modeling method

A modeling method and bone model technology, applied in the field of human bone modeling, can solve problems such as complicated processing, high cost, and inability to analyze online, and achieve the effect of simple operation, accurate modeling, and online analysis

Inactive Publication Date: 2015-09-30
ANHUI RUIHONG MDT INFOTECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the human motion information analysis system based on the traditional photography principle has the problems of complicated follow-up processing and time-consuming, and cannot be analyzed online. Moreover, the current human skeleton modeling method is relatively complicated and expensive, and cannot achieve the purpose of rapid modeling.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] This specific embodiment adopts the following technical scheme: its modeling method is: 1, install sensors on each joint of the human body, and connect each sensor with the detection host; 2, perform motion capture through the sensor array installed on each joint, video 3. Reuse the smoothing and optimization algorithm of the curve to process the edge contour curve; 4. According to the hierarchical structure of the joints of the human body, each limb is abstracted into a simple rigid geometric entity, and Use VRML to build a sample of human skeleton model; 5. The skeleton model of each limb can be obtained by transformation on the basis of this sample model.

[0010] The principle of this specific embodiment is: the detection host adopts joint single-point recognition method, limb multi-point recognition technology and new method of mark point image processing. The spatial position of the joint can be obtained by specifying the marker point and installing the sensor.

...

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 relates to a human skeleton modeling method and relates to the technical field of human skeleton modeling. The modeling method comprises steps as follows: sensors are mounted at all joints of a human body and connected with a detection host; motion capture is performed by the sensor array mounted at all the joints and data points in a video are fitted to form a spline; an edge contour curve is processed with fairing and optimization algorithms of the spline; according to a joint connector hierarchical structure of the human body, all limbs are abstracted into simple rigid geometric entities and a sample of human skeleton models is constructed with the VRML (virtual reality modeling language); the skeleton models of all the limbs can be obtained through transformation on the basis of the sample model. Analysis recognition is performed on human skeleton characteristics with a video-based motion recognition technology, the operation is simple, rapid and accurate modeling can be realized, and online analysis is realized.

Description

Technical field: [0001] The invention relates to the technical field of human skeleton modeling, in particular to a human skeleton modeling method. Background technique: [0002] In the process of human-to-human interaction, vision is the most important information, which can help people quickly obtain some key features and facts. It has a wide range of application value in the fields of intelligent video surveillance, abnormal action recognition, human-computer interaction and virtual technology. At the current stage, the current research on human action recognition mainly focuses on the structural analysis of the moving human body and the tracking of human action targets. [0003] The analysis and recognition of human actions is one of the important topics in the current research fields of computer vision and pattern recognition. Human actions are composed of continuous static poses, because the action itself has quite complex high-dimensional information in space and...

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): G06T17/00G06T7/20
Inventor 谢海亭
Owner ANHUI RUIHONG MDT INFOTECH
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