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

Joint positioning method of single-view unmarked human motion tracking

A technology of human body movement and positioning methods, which is applied in image data processing, instruments, calculations, etc., and can solve the problems of difficulty in guaranteeing the coverage and representativeness of training sample sets, and inaccurate results

Inactive Publication Date: 2011-08-17
SHANGHAI YINGSUI NETWORK TECH
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it can only recognize known actions, and the results may not be accurate; for complex movements, the coverage and representativeness of its training sample set are difficult to guarantee

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
  • Joint positioning method of single-view unmarked human motion tracking
  • Joint positioning method of single-view unmarked human motion tracking
  • Joint positioning method of single-view unmarked human motion tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0111] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention will be further elaborated below.

[0112] The present invention is mainly aimed at single-view unmarked human body motion tracking, especially the joint positioning method therein. For the convenience of description and understanding, the method of the present invention will be described below by taking the left arm as an example.

[0113] figure 1 The position of each joint point of the body is shown. If the "person" is defined as a tree, the arm is a branch of the "person" tree, including three joint points of the hand, elbow, and shoulder, where the shoulder is the root node and the hand is the end node.

[0114] Based on the characteristics of the human body structure, the present invention defines the unit length of the human body as sizeUnit, and the length of height and arm span is 8 unit lengths, i.e. 8 si...

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 belongs to the technical field of human motion tracking, and discloses a joint positioning method of single-view unmarked human motion tracking. The method comprises the following steps of: detecting the position of a hand, and acquiring handCandidate which is {Hi (xi, yi)}, wherein i is 0, 1, ..., numHandCandidate-1, Hi (xi, yi) is the candidate of the ith hand, and numHandCandidate is the number of the hand candidates; screening the position of the hand, and acquiring the candidates with high probability as optimal candidates; detecting the position of an elbow, and acquiring candidates of the elbow; compositely screening the positions of the hand and the elbow; combining every two optimal candidates of the hand and the elbow to form front arm candidates, and performing optimization on the front arm candidates to acquire an optimal front arm candidate; compositely screening the positions of the hand, the elbow and a shoulder, and performing composite optimization according to the optimal front arm candidate and the position of the shoulder to acquire an arm sample; and performing optimization weighing on the arm candidates to acquire final positions of the hand, the elbow and the shoulder. The method can be widely applied to human tracking and positioning.

Description

technical field [0001] The invention relates to the technical field of human motion tracking, in particular to a tracking and positioning method for human joints. Background technique [0002] Human motion analysis and understanding based on video is a research hotspot in the field of computer vision, and motion tracking is an important part of it. There are two main approaches to motion tracking: labeled video motion tracking and unmarked video motion tracking. Among them, the video-based unmarked human motion tracking is to recover the human body posture information from one or more synchronized image sequences, mainly including the movement of the head, torso and limbs, which has the characteristics of non-invasive, low cost, and intelligent , has broad application prospects. [0003] However, due to the difficulties of non-rigid motion of the human body, occlusion and self-occlusion, high-dimensional state space search, and feature extraction under complex conditions, ...

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 唐霖董初宁姜涛涂治国
Owner SHANGHAI YINGSUI NETWORK 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