A view-independent calibration method for somatosensory camera network

A technology of somatosensory cameras and calibration methods, which is applied in image analysis, image data processing, instruments, etc., can solve problems such as large amount of calculation, and achieve the effect of strong real-time performance and simple operation

Active Publication Date: 2016-07-13
TONGJI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main disadvantage of the above method is that it is computationally intensive and requires additional auxiliary references

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 view-independent calibration method for somatosensory camera network
  • A view-independent calibration method for somatosensory camera network
  • A view-independent calibration method for somatosensory camera network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] Such as figure 1 As shown, a view-independent somatosensory camera network calibration method aims at fast and robust calibration of the somatosensory camera network, and proposes to use the robust skeleton joint points of the human body as reference points to construct a view-independent human skeleton coordinate system, and adopts a coordinate-based It is realized by the method of system conversion. The method includes the following steps:

[0030] In step S101, among the multiple installed cameras, the coordinate system where one camera is located is selected as the reference coordinate system, and the rest are non-reference coordinate systems. In this embodiment, two cameras are assumed to be A and B, and selected The coordinate system where camera A is located is the reference coordinate system;

[0031] In step S102, two cameras acquire and display the skeleton position information of the same person at the same time;

[0032] In step S103, a human skeleton coo...

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 present invention relates to an angle-independent somatosensory camera network calibration method, which comprises steps: 1) selecting the coordinate system where one camera is located as a reference coordinate system among multiple installed cameras, and the rest are non-reference coordinate systems; 2) Multiple cameras obtain and display the skeleton position information of the same person at the same time; 3) establish a human skeleton coordinate system, and multiple cameras calculate the rotation matrix and translation vector of each camera relative to the human skeleton coordinate system according to the detected skeleton position information; 4 ) According to the rotation matrix and translation vector obtained in step 3), calculate the rotation matrix and translation vector of each non-reference coordinate system relative to the reference coordinate system; 5) According to the rotation matrix and translation vector obtained in step 4), the non-reference coordinate system is located The skeleton position information detected by the camera is mapped to the reference coordinate system. Compared with the prior art, the present invention has the advantages of simple operation, strong real-time performance, no special preparation of other auxiliary markers and the like.

Description

technical field [0001] The invention relates to a camera calibration method, in particular to a viewing angle-independent somatosensory camera network calibration method. Background technique [0002] Camera calibration can be divided into two categories: one is the calibration of a single camera; the other is the global calibration of multiple cameras. The calibration of a single camera refers to solving the internal and external parameters of each camera and the relationship parameters between cameras. The commonly used methods are the chessboard calibration method proposed by Zhengyou Zhang and the RAC two-part calibration method proposed by Tsai. Among them, the checkerboard calibration method proposed by Zhang uses the vertices of black and white chessboards artificially marked as marking points, which has high calibration accuracy and has become a mainstream method. The global calibration of multiple cameras refers to unifying the data of all cameras into the overall...

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): G06T7/00
Inventor 陈启军韩云
Owner TONGJI 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