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

Method for tracking human body posture based on visual information

A technology of human posture and visual information, applied in the field of computer vision, can solve problems such as difficult to meet real-time requirements and large amount of calculation, and achieve the effect of improving efficiency, good real-time and accuracy, and ensuring accuracy

Inactive Publication Date: 2014-06-04
WUHAN UNIV OF SCI & TECH
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

General particle filter algorithms, especially those used for human body posture tracking, such as immune particle filter, their motion models are all first-order linear; because the original space dimension of human body posture is too high, the motion model established in this high-dimensional space The method has a large amount of calculation, and it is difficult to meet the real-time requirements in tracking

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
  • Method for tracking human body posture based on visual information
  • Method for tracking human body posture based on visual information
  • Method for tracking human body posture based on visual information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] A human pose tracking method based on visual information. The concrete steps of this human posture tracking method are:

[0046] The first step is to determine the prior model of human motion

[0047] According to the type of human motion in the video to be tested, find out whether a relevant prior model of human motion exists. The type of human motion selected in this example is walking; assuming that no prior motion model has been established for this type of motion, proceed to the second step.

[0048] The second step is to train the prior model of human motion

[0049] The training data Ψ is composed of K frames of real human posture data, and the training data Ψ is

[0050] Ψ={X i |i∈[1,K],X i ∈X D} (1)

[0051] In formula (1): X i Indicates the posture of the human body in the i-th frame, X i It is composed of coordinates of all relevant nodes of the human body;

[0052] D is the original spatial dimension of the human body posture;

[0053] x D Re...

Embodiment 2

[0083] A human pose tracking method based on visual information. The concrete steps of this human posture tracking method are:

[0084] The first step is to determine the prior model of human motion

[0085] According to the type of human motion in the video to be tested, find out whether a prior model of human motion has been established; the type of human motion selected in this example is throwing. Assuming that the prior motion model of the motion type has been established, the third step is performed next.

[0086] The third step, test human body posture tracking

[0087] Step 3.1: Initialize the particle set according to the real posture of the human body in the first frame of the data to be tested, and generate the particle set S t

[0088] S t = { S t , n } ...

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 method for tracking the human body posture based on visual information. According to the technical scheme, the method comprises the steps that in the training stage, according to real three-dimensional human body posture time series data in training data and with the adoption of the Gauss latent variable model algorithm, the human body posture is studied, so that a human body posture motion prior model is obtained; in the tracking test stage, video data to be tested and a first frame of the three-dimensional human body posture in the video data are input, a latent variable motion model is established with the use of the human body posture motion prior model studied in the training stage, and the particle updating step in an immune particle filtering algorithm is achieved through the latent variable motion model. The method for tracking the human body posture based on the visual information has the advantages of being high in practicality, accuracy and efficiency.

Description

technical field [0001] The invention belongs to the technical field of computer vision. Specifically, it relates to a human body pose tracking method based on visual information. Background technique [0002] The problem of human pose tracking can be described as: according to the video sequence collected in the monitoring environment and the real pose of the first frame, estimate the whole body pose of the controlled person in each frame of the image, and the estimated pose vector is required to include the three-dimensional positions of all relevant nodes of the human body coordinate. Human motion posture tracking has a wide range of applications in intelligent monitoring, video marking, image compression, film animation, games, human-computer interaction, sports analysis, virtual reality and other fields. [0003] At present, most human motion posture tracking is based on the particle filter framework. For high-dimensional state estimation problems such as human motion ...

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): G06T7/20G06K9/66
Inventor 蒋旻董珂雷泽姚世杰
Owner WUHAN UNIV OF SCI & TECH
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