A Methodological Framework to Assess the Accuracy of Virtual Reality Hand-Tracking Systems: A case study with the Oculus Quest 2
Abdlkarim, D.; Di Luca, M.; Aves, P.; Yeo, S.-H.; Miall, C.; Holland, P.; Galea, J. M.
Show abstract
Optical marker-less hand-tracking systems incorporated into virtual reality (VR) headsets are transforming the ability to assess motor skills, including hand movements, in VR. This promises to have far-reaching implications for the increased applicability of VR across scientific, industrial and clinical settings. However, so far, there is little data regarding the accuracy, delay and overall performance of these types of hand-tracking systems. Here we present a novel methodological framework which can be easily applied to measure these systems absolute positional error, temporal delay and finger joint-angle accuracy. We used this framework to evaluate the Meta Quest 2 hand-tracking system. Our results showed an average fingertip positional error of 1.1cm, an average finger joint angle error of 9.6o and an average temporal delay of 38.0ms. Finally, a novel approach was developed to correct for these positional errors based on a lens distortion model. This methodological framework provides a powerful tool to ensure the reliability and validity of data originating from VR-based, marker-less hand-tracking systems.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.