A Global 3D Human Pose Trustworthy Estimation Method for Two Views

A human body posture and view technology, applied in computing, image analysis, image enhancement, etc., can solve problems such as large differences in individual body proportions and sizes, unreliable 3D posture estimation results, and high dimensionality of 3D posture state parameters. Realize the effect of attitude tracking

Active Publication Date: 2021-04-27
ZHEJIANG UNIV +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the 3D pose data set is difficult to obtain and the scale is small; at the same time, the state parameters of the 3D pose have a high dimensionality, and the individual body proportions and sizes vary greatly
This leads to the inability to guarantee the reliability of the 3D pose estimation results

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
  • A Global 3D Human Pose Trustworthy Estimation Method for Two Views
  • A Global 3D Human Pose Trustworthy Estimation Method for Two Views
  • A Global 3D Human Pose Trustworthy Estimation Method for Two Views

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] A method for reliable estimation of three-dimensional human poses for two views, comprising the following steps:

[0064] (1) Obtain N frames of images (N ≥ 100) from the left and right cameras respectively; use N groups of one-to-one corresponding left and right views to perform preliminary estimation of the two-dimensional human body posture respectively, and obtain the initial two-dimensional image of N groups of joint points. dimension position;

[0065] Each group of joint points contains 14 joint points of the human body. According to the existing records, the names of each joint point are as follows: , such as image 3 shown. The corresponding numbers of joint points are , and the corresponding parent joint numbers of each joint point are . Among them, # means no parent node, joint point 9 (Hip.L) and joint point 13 (Hip.R) do not form a fixed bone length with the parent joint point (Neck), and other joint points form a joint with the parent joint point. Bone...

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 proposes a two-view global three-dimensional human body posture trustworthy estimation method, which can be used for unmarked human motion capture. The core innovations of the present invention are as follows: First, the present invention proposes to detect unreliable joint points based on two-view epipolar geometric constraints and human bone length constraints. Secondly, the present invention proposes to correct the unreliable joints based on the joint point confidence map estimated by the network for polar line constraints and bone length constraints. Finally, the present invention proposes a simple and efficient automatic calibration technology of external camera parameters and a bone length calculation method. The present invention can realize stable and credible two-dimensional and global three-dimensional human body posture estimation for any person with different body shapes without using a human body model or assuming any prior knowledge of the human body. The pose generated by the invention satisfies the two-view epipolar geometric constraints and the human bone length constraint, and realizes robust and credible human pose estimation in extremely challenging scenes such as severe occlusion, symmetric ambiguity, and motion blur.

Description

technical field [0001] Given two views of a human subject, the present invention aims at estimating plausible 3D human poses satisfying epipolar geometry constraints and bone length constraints. First, the present invention proposes a method for detecting unreliable joint point estimation using two-view epipolar geometry constraints and human bone length constraints. Secondly, the present invention proposes an unreliable joint correction method for polar line constraints and bone length constraints. Finally, the present invention proposes automatic camera extrinsic calibration and bone length calculation methods. For challenges such as severe occlusion, symmetric ambiguity, and motion blur in human body pose estimation, the present invention achieves robust and credible pose estimation. The present invention can realize stable and credible two-dimensional and global three-dimensional human body posture estimation for any person with different skeleton sizes and proportions w...

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 Patents(China)
IPC IPC(8): G06T7/246G06T7/292G06T17/00G06T5/00
CPCG06T5/006G06T17/00G06T2207/10012G06T2207/20081G06T2207/20084G06T2207/30196G06T7/251G06T7/292
Inventor 刘新国李妙鹏周子孟
Owner ZHEJIANG 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