Three-Dimensional Coordinate Calibration Models for Augmented Reality Applications in Indoor Industrial Environments

Abstract

The calibration of three-dimensional (3D) coordinates in augmented reality systems is a complex activity. It involves the recognition of environmental characteristics and technology that models the 3D space of the device, determining its position and orientation. Single markers suffer from numerical instability, particularly when they are small within the camera image. In the industrial environment, it is common for augmented reality applications to cover large spaces, making it difficult to maintain attributes such as precision and accuracy. To address this issue, our study proposes a two-step calibration model that leverages multiple markers for accurate localization in a larger indoor environment. We developed the calibration model using Unity3D, Mixed Reality ToolKit, and Vuforia and evaluated it in terms of precision and accuracy in a proof of concept using the MS Hololens device. Our findings reveal that employing two markers significantly reduces angular discrepancies between points in the real and augmented environments. Moreover, our results underscore that registration accuracy improves as the number of calibration points increases. The results show improvements in determining the axes that define the 3D space, with a direct influence on the position of the points observed in the experiment.