Correction method for tracking registration precision in an augmented reality system

Abstract

The invention requests to protect a tracking registration precision correction method in an augmented reality system. The method comprises the following specific operation processes: performing clustering analysis on spatial data; Locally employing t-S fuzzy system preprocessing; Deep learning is utilized globally for training; Preliminarily correcting a training target of the convolutional neuralnetwork by using a deep learning algorithm; Solving by adopting a least square support vector machine; And outputting a correction result when the precision reaches the application requirement, or else returning the data to continue deep learning training.

Description

technical field [0001] The invention belongs to the technical field of augmented reality, and in particular relates to a method for correcting tracking registration accuracy in an augmented reality system. Background technique [0002] Augmented reality (Augmented Reality, AR) technology is a technology that ingeniously integrates virtual information with the real world. It uses multimedia, 3D modeling, real-time tracking and registration, intelligent interaction, sensing and other technical means to integrate computer The generated text, images, 3D models, music, video and other virtual information are simulated and applied to the real world, and the two kinds of information complement each other, thereby realizing the "enhancement" of the real world. In recent years, with the continuous improvement of the performance of GPU and CPU of computers and various mobile devices, as well as the improvement of technologies such as computer graphics and machine vision technology, au...

AI Technical Summary

Problems solved by technology

Although the fitting function method has been recognized by the industry, its analytical formula is difficult or impossible to solve accurately in many cases; the space network linear interpolation method limits the absolute error within 5mm, but it cannot reach the precision of this application. Requirements; The three-axis approximation-inverse distance interpolation method is aimed at the dual-emitter magnetic tracking system, which expands the magnetic tracking working range, but it still approximates the linear relationship between the data

Images