Unlock instant, AI-driven research and patent intelligence for your innovation.

Correction Method of Feature Points of AR Reference Object Based on Rigid Body Kinematics

A rigid body motion and feature point technology, applied in the AR field, can solve problems such as inability to change and limit the scope of application, and achieve the effect of avoiding jitter and improving stability.

Active Publication Date: 2019-12-13
苏州爱乐智能科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Once the space virtual coordinates are calibrated, they cannot be changed
Moreover, spatial calibration requires additional sensors distributed in the room, which greatly limits its application range

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
  • Correction Method of Feature Points of AR Reference Object Based on Rigid Body Kinematics
  • Correction Method of Feature Points of AR Reference Object Based on Rigid Body Kinematics
  • Correction Method of Feature Points of AR Reference Object Based on Rigid Body Kinematics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0032] This patent proposes an AR reference object feature point correction algorithm based on rigid body kinematics.

[0033] The AR reference object feature point correction algorithm based on rigid body kinematics is used to correct the feature points of the recognition deviation, avoiding the reference coordinates from shaking due to recognition errors, thereby improving the stability of the fusion of virtual objects and the real world in AR applications.

[0034] Principle: Since the reference object in the real world is a rigid body, no distortion and deformation will occur. Therefore, in the process of integrating virtual objects and the real world in AR applications, all f...

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 an AR reference object feature point correction method based on rigid body kinematics. The invention discloses an AR reference object feature point correction method based on rigid body kinematics, and the method is characterized in that the feature point vector sets of a front frame and a rear frame in an image sequence are according to the classical rigid body motion principle, the motion of a reference object conforms to a rigid body motion model. The method has the advantages that the AR reference object feature point correction algorithm based on rigid body kinematics is adopted to correct the feature points of the recognition deviation, the reference coordinates are prevented from shaking due to the recognition error, and therefore the fusion stability of thevirtual object and the real world in AR application is improved.

Description

technical field [0001] The invention relates to the field of AR, in particular to a method for correcting feature points of an AR reference object based on rigid body kinematics. Background technique [0002] Augmented Reality (AR for short) is a technology that superimposes virtual three-dimensional objects onto real scenes by calculating the position and angle of camera images in real time. In order to accurately and stably integrate the virtual object into the real scene, it is necessary to identify the reference object and its position in the real scene in real time, so as to calculate the relative position where the virtual object should appear. The relatively stable technologies currently commercially available mainly include: machine vision-based recognition solutions, such as Apple AR Kit, Google AR Core, and Vufroia; and 3D-space calibration-based solutions, such as Microsoft Hololens and Oculus. There are also some independent programs in China, but their applicab...

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): G06T19/00
CPCG06T19/006G06T2219/2016
Inventor 张量
Owner 苏州爱乐智能科技有限公司