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

Camera calibration method based on human body posture estimation in large scene

A technology of human body posture and camera calibration, applied in computing, image data processing, instruments, etc., to achieve the effect of easy implementation, good convergence effect, and reduced complexity

Active Publication Date: 2021-03-30
SOUTHEAST UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem of camera calibration in large scenes, the present invention proposes a camera calibration method based on human body pose estimation in large scenes

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
  • Camera calibration method based on human body posture estimation in large scene
  • Camera calibration method based on human body posture estimation in large scene
  • Camera calibration method based on human body posture estimation in large scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The detailed implementation of the present invention will be described in detail below according to the accompanying drawings.

[0040] like figure 1 As shown, the camera calibration method based on human body pose estimation under the large scene of the present invention specifically includes the following steps:

[0041] Step 1. First, you need to build a multi-view camera platform for the production of multi-view human body datasets and the initialization of camera parameters. The multi-view camera platform can be built in an open field outdoors. In this embodiment, a camera system with eight viewing angles is built in eight directions on the edge. For details, please refer to figure 2 form.

[0042] Step 2, in the built camera system, first place a calibration rod, and use Zhang Zhengyou's one-dimensional calibration method to initialize the parameters of the eight cameras. In this embodiment, one end of the calibration rod is first fixed, and an intermediate po...

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 camera calibration method based on human body posture estimation in a large scene. The method comprises the following steps: 1, obtaining initial camera parameters of each camera; 2, collecting a multi-person data set in a multi-view camera environment for optimizing initial camera parameters; 3, predicting human body joint point information in the data set; 4, projectingthe human body two-dimensional articulation points under multiple view angles by using the initialized camera parameters, projecting pixel coordinates under a two-dimensional image coordinate systemto a world coordinate system to obtain three-dimensional coordinates of the articulation points, and normalizing the three-dimensional projection of the same articulation point; and 5, reprojecting the three-dimensional space coordinates of the articulation points into an image coordinate system under each visual angle to obtain true values of the articulation points and mean square errors betweenthe reprojected articulation points, performing nonlinear secondary optimization by utilizing an LM algorithm, and updating camera parameters until the mean square errors reach a set threshold value.The method provided by the invention can realize more accurate camera calibration.

Description

technical field [0001] The invention relates to the fields of computer vision, camera calibration and three-dimensional vision, in particular to a camera calibration method based on human body posture estimation in a large scene. Background technique [0002] Multi-view camera calibration is the cornerstone of the field of computer 3D vision, and it is also a research hotspot in the field of 3D vision. One of the basic tasks in the field of computer vision is to calculate three-dimensional spatial position information from two-dimensional image information, and the relationship between three-dimensional position information and picture pixels is determined by camera parameters. The accuracy of camera parameters and algorithm stability directly affect the accuracy of subsequent work results, so improving the accuracy of camera calibration is the focus of computer vision. [0003] The traditional camera calibration algorithm is based on image feature extraction to calculate c...

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): G06T7/80
CPCG06T7/80G06T2207/30196
Inventor 谢艺明王雁刚赵允琦
Owner SOUTHEAST 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

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