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

Three-dimensional tracking registration method for augmented reality

A 3D tracking and augmented reality technology, applied in image enhancement, image data processing, instruments, etc., can solve the problems of low registration accuracy and long registration time

Pending Publication Date: 2021-01-29
JIANGNAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of long registration time and low registration accuracy in existing 3D registration methods, the present invention provides a 3D tracking registration method oriented to augmented reality, the method comprising:

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
  • Three-dimensional tracking registration method for augmented reality
  • Three-dimensional tracking registration method for augmented reality
  • Three-dimensional tracking registration method for augmented reality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This embodiment provides an augmented reality-oriented three-dimensional tracking registration method, the method comprising:

[0058] Step 1: Use KCF for target tracking to obtain the target position in the current image frame;

[0059] Step 2: Perform feature extraction on the current image frame and filter the extracted features;

[0060] Step 3: Solve the camera pose change matrix according to the feature point matching results filtered by two adjacent frames of images; obtain the virtual object coordinates, camera coordinates and real-world coordinate transformation relationship according to the camera pose change matrix, and register the virtual object to the real world in the image.

[0061] In this embodiment, the improved ORB algorithm is used to detect the tracked target location area to be registered, and the Gaussian kernel function convolution is used to solve the extreme points for screening in the multi-scale space, and finally the target area is detecte...

Embodiment 2

[0063] This embodiment provides a three-dimensional tracking registration method for augmented reality, see figure 1 , when performing ORB feature matching, the method proposes a feature point screening mechanism according to the multi-scale space theory, uses Gaussian kernel function convolution to solve extreme points in multi-scale space, and selects local extreme points as candidate ORB feature points in scale space , these extreme points are evenly distributed and have scale invariance, and finally complete the tracking and registration according to these filtered feature points, which has certain advantages in time and accuracy.

[0064] Specifically, the method includes:

[0065] Step 1 KCF target tracking

[0066] KCF is a target tracking method. First, train a target detector based on the least squares classifier; then, use the target detector to obtain the approximate area of ​​the target in the next frame; finally, use the current frame detection result as a new sa...

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 three-dimensional tracking registration method for augmented reality, and belongs to the technical field of computer vision tracking registration. According to the method, animproved ORB algorithm is adopted to detect a tracked to-be-registered target position area, Gaussian kernel function convolution is adopted to solve extreme points in a multi-scale space for screening, and finally, the target area is detected to obtain feature points with uniform distribution and scale invariance; compared with a traditional ORB algorithm, the method has the advantages that theextracted feature points are screened through a screening mechanism, registration precision is higher, and meanwhile the calculated amount is reduced. According to the method, the KCF target trackingalgorithm and the three-dimensional registration method are combined together, seamless superposition of the virtual object and the real world is achieved, and good real-time performance, accuracy androbustness are achieved.

Description

technical field [0001] The invention relates to an augmented reality-oriented three-dimensional tracking and registration method, which belongs to the technical field of computer vision tracking and registration. Background technique [0002] Augmented Reality (Augmented Reality, AR) is a technology that connects the virtual world with the real world. It uses computers to analyze and process the real scene observed by the user, and embeds virtual objects into the real scene to achieve the same effect as the real scene. Virtual information seamless fusion effect. AR technology can provide information that is difficult to directly realize in real scenes, so that users can see the scene after the fusion of virtual information and real scenes through handheld augmented reality devices, assisting users in cognition of the real world and giving users a sense of real experience . In recent years, augmented reality has been used in many popular research fields, such as service rob...

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): G06T7/73G06T5/00
CPCG06T7/73G06T2207/20081G06T5/70
Inventor 吴广运周治平
Owner JIANGNAN 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