Evaluation of Stereovision Tracking of Targets with Gaussian Pixel Intensity Distribution for Measuring 3D Displacements of Structures

Abstract

This study evaluates a method for tracking targets using stereovision-based structural monitoring for accurately measuring three-dimensional (3D) displacements of structures. The greyscale targets are printed with a Gaussian pixel intensity distribution, which allows to efficiently identify their centres using an optimisation algorithm. Compared to traditional sensors, such as linear transducers, this non-contact technique provides enhanced versatility, especially in situations where the application of contact-based sensors may be challenging and full-field vision-based measurements, such as Digital Image Correlation (DIC), may be impractical. A series of experimental tests on a calibration bench were conducted to evaluate the displacement measurements using the target tracking algorithm in comparison to traditional contact-based monitoring systems and DIC. The evaluation was carried out according to five criteria: resolution, accuracy, repeatability, reversibility, and standard error. Various parameters, including target size, colour schemes, and camera orientations, were analysed. The results obtained in this study demonstrate that tracking of the Gaussian greyscale targets provides precise measurements with low computational cost, achieving accuracies comparable to both contact-based sensors and DIC. It was shown that a minimum target size of 6 pixels is required and that target sizes between 9 and 36 pixels are preferable, as the impact of colour scheme or camera orientation is least significant. Overall, the tracking algorithm shows promise as a viable alternative for structural and mechanical testing, offering advantages in speed, flexibility, and the ability to measure 3D motion, addressing some limitations of existing techniques.