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

Human body tracking method based on gauss mixing model

A Gaussian mixture model and human body technology, applied in the field of image processing, can solve problems such as the inability to effectively overcome the occlusion problem, and achieve the effects of ensuring accuracy, simple and intuitive calculation, and high tracking accuracy.

Inactive Publication Date: 2008-08-27
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its shortcoming is that each tracking part is tracked as a tracking object as a whole, which cannot effectively overcome the occlusion problem

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
  • Human body tracking method based on gauss mixing model
  • Human body tracking method based on gauss mixing model
  • Human body tracking method based on gauss mixing model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following the described embodiment.

[0017] As shown in FIG. 3 , this embodiment is used to track pedestrians in a video sequence.

[0018] This embodiment includes the following steps:

[0019] Step 1, use the linear model of the human body to build a model of the human body, as shown in Figure 1, Figure (a) is a human body structure diagram, (b) is a schematic diagram of a human body linear model, with circles representing the head, neck, center of mass and feet of the human body, The parts of the human body represented by the circles are the tracking parts, which are connected by line segments, and t...

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 human body tracking method based on a Gaussian mixture model in the image processing technical field. The invention firstly uses a linear model of a human body to establish a model to the human body, the head, the neck, the mass center and two feet of the human body are taken as tracking positions, then each tracking position of the human body is made a Kalman filtering tracking in a subsequent frame, wherein, two legs are tracked based on a Gaussian mixture model, the left foot adopts the Kalman filtering to track, and the motion state of the right foot is judged through the state of the left foot to simplify the tracking to the right foot. The invention forecasts the parameter of the component in the next frame through the Kalman filtering and uses the observed value to modify the predicted value, thereby assuring the accuracy of the component tracking. To use the Gaussian mixture model to build models for the tracked objects improves the tracking efficiency and can recognize the state of the motion of two legs.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a human body tracking method based on a Gaussian mixture model. Background technique [0002] Human motion analysis is an important technology combining contemporary biomechanics and computer vision. It has a wide range of applications in the fields of intelligent monitoring, human-computer interaction, biometric technology and virtual reality. In particular, the motion analysis of human legs provides important reference data for medical and sports research. [0003] After searching the prior art documents, it was found that Part Based HumanTracking In A Multiple Cues Fusion Framework (Part Based Human Tracking In A Multiple Cues Fusion Framework under the multi-cues fusion framework) published by Qi Zhao et al. In tracking), it is proposed to establish HMM (hidden Markov) model for each tracking part of the human body, and use the criterion of maximum post...

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): G06K9/62G06T7/20
Inventor 张玉冰曾贵华
Owner SHANGHAI JIAO TONG 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