Multi-objective optimization multi-lens human motion tracking method

A multi-objective optimization and human body motion technology, applied in image data processing, instruments, calculations, etc., can solve the problem that the similarity of the appearance model is not enough to accurately track the posture of the human body, and achieve simple algorithms, low time complexity, and improved accuracy degree of effect

Inactive Publication Date: 2012-08-01
XIDIAN UNIV
View PDF3 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this patent application is that it can only track the human body in a fixed scene

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
  • Multi-objective optimization multi-lens human motion tracking method
  • Multi-objective optimization multi-lens human motion tracking method
  • Multi-objective optimization multi-lens human motion tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] refer to figure 1 , the specific implementation process of the present invention is as follows:

[0036] Step 1, building a human skeleton model.

[0037] According to anatomical knowledge, although the human skeleton is constantly changing due to the influence of age and health, the composition of the skeleton remains unchanged. The human body roughly includes: tibia, femur, hip, trunk, radius, humerus, clavicle, neck and head . In this case, this example represents the human body as a skeleton model composed of 15 joint points and 14 rod-shaped bones. In the virtual space, the 14 rod-shaped skeletal models are represented by straight line segments between 14 joint points with three-dimensional coordinates.

[0038] The three-dimensional coordinates of the i-th joint point are expressed as v i =[xi ,y i ,z i ] T , i=1, 2, ..., 14, the whole human skelet...

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 a multi-objective optimization multi-lens human motion tracking method and mainly solves the problems that an existing technology is limited by a training database and has high complexity of the tracking process and a recovered human posture is inaccurate. The multi-objective optimization multi-lens human motion tracking method has the following implementing processes of: (1) establishing a three-dimensional human skeleton model by using a bone abstract method; (2) preprocessing a video image to obtain human body joints on the image; (3) initializing human skeleton parameters; (4) constructing similarity functions under two synchronous lenses; (5) optimizing the similarity functions by a non-dominated neighbor immune algorithm; and (6) selecting the most accurate human skeleton from a group of human skeletons obtained by optimization as a tracking result. The method is suitable for universal videos; two similarity functions are adopted; video image information can be better utilized; the accuracy of tracking the human motion is improved; and the method can be used for the athletic training and the animation production.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a method for realizing human body motion tracking in the field of computer vision, which adopts a multi-objective optimization method to realize human body motion tracking and three-dimensional attitude estimation, and can be used in fields such as sports training and animation production . Background technique [0002] The main task of human motion tracking is to detect the outline of the human body from the video image, and then locate the joint points of the human body. Since the current video image is the projection of the human body contour in the 3D scene on the 2D image, a lot of depth information is lost, and during the movement of the human body, the self-occlusion phenomenon of the limbs of the human body often occurs, and the video image has ambiguity, which makes It is difficult to recover human motion pose from unlabeled monocular videos. Therefore, ...

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): G06T7/20
Inventor 韩红冯光洁苟靖翔王瑞谢福强顾建银张红蕾李晓君韩启强
Owner XIDIAN 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