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

Multi-camera external parameter automatic calibration method based on human skeleton extraction

An automatic calibration, human skeleton technology, applied in the field of computer vision, can solve the problems of complex calibration process of accurate calibration objects and known calibration information with high precision

Active Publication Date: 2021-07-06
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional calibration method is to use the known scene structure information for calibration, which usually involves the production of precise calibration objects, complex calibration process and high-precision known calibration information, requiring complex operations by professionals
Moreover, every time the position of the camera group is changed, a recalibration operation is required

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
  • Multi-camera external parameter automatic calibration method based on human skeleton extraction
  • Multi-camera external parameter automatic calibration method based on human skeleton extraction
  • Multi-camera external parameter automatic calibration method based on human skeleton extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only for illustration and explanation of the present invention, and are not intended to limit this invention.

[0038] A method for automatic calibration of multi-camera extrinsic parameters based on human skeleton extraction, comprising the following steps:

[0039] Step 1. After installing the multi-camera system, let a single pedestrian walk in the camera monitoring area, and multi-cameras record video at the same time to obtain synchronized video;

[0040] Step 2, intercept images of pedestrians at different positions with the same number of frames from each video;

[0041] Step 3, process each frame of image, use the convolutional neural network to extract 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 multi-camera external parameter automatic calibration method based on human skeleton extraction, and belongs to the technical field of computer vision. The method comprises the following steps: processing each frame of image, and extracting the position of a human skeleton joint point in the image by using a deep learning method; selecting any one camera coordinate system as a world coordinate system, and calculating external parameters of other cameras through the essential matrix; calculating a translation vector scale by using the human body size information. According to the method, human body skeleton joint points are used as feature points, point cloud formed by motion trails of the human body skeleton joint points is used as a virtual calibration object, then essential matrixes between cameras are calculated, relative poses between the cameras are obtained through essential matrix decomposition, and real-time online accurate external parameter calibration of a multi-camera system is completed.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a method for online external parameter calibration of a multi-camera system by extracting pedestrian skeletons. Background technique [0002] In computer vision technology and artificial intelligence related fields, for the application of multi-camera systems in scene reconstruction, smart city security monitoring, airport monitoring, motion capture, sports video analysis and industrial measurement, it is necessary to accurately and quickly perform multi-camera systems. Calibration of external parameters. Camera extrinsic parameters are a set of parameters that characterize the camera's position in the world coordinate system, rotation direction and other attributes, so it needs to be calibrated after the camera is installed. Multi-camera extrinsic calibration is the process of obtaining camera extrinsic parameters [0003] The traditional calibration method is to use the known s...

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): G06T7/80G06T7/73G06K9/46G06N3/04G06N3/08G06F17/16
CPCG06T7/80G06T7/73G06N3/08G06F17/16G06T2207/10016G06T2207/10028G06T2207/30196G06V10/44G06N3/045
Inventor 关俊志耿虎军高峰柴兴华陈彦桥张泽勇李晨阳王雅涵彭会湘陈韬亦
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
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