Comparing eye tracking technologies
Heikkilä, Kaarlo; Pudas, Niilo; Ukkola, Samuli (2023-11-10)
Heikkilä, Kaarlo
Pudas, Niilo
Ukkola, Samuli
K. Heikkilä; N. Pudas; S. Ukkola
10.11.2023
© 2023 Kaarlo Heikkilä, Niilo Pudas, Samuli Ukkola. Ellei toisin mainita, uudelleenkäyttö on sallittu Creative Commons Attribution 4.0 International (CC-BY 4.0) -lisenssillä (https://creativecommons.org/licenses/by/4.0/). Uudelleenkäyttö on sallittua edellyttäen, että lähde mainitaan asianmukaisesti ja mahdolliset muutokset merkitään. Sellaisten osien käyttö tai jäljentäminen, jotka eivät ole tekijän tai tekijöiden omaisuutta, saattaa edellyttää lupaa suoraan asianomaisilta oikeudenhaltijoilta.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202311103199
https://urn.fi/URN:NBN:fi:oulu-202311103199
Tiivistelmä
Eye tracking is a technology that monitors eye movements, and by the data, detects gaze directions and target points. The number of potential use cases and capabilities of such technology are huge, and at the time being, there are at least five commercial VR headsets with built-in eye tracking systems. The aim of this study is to compare the performance of eye tracking technologies with two devices. We compare the eye tracking glasses from SeeTrue Technologies against Varjo Aero’s eye tracking system and evaluate, would it be worthwhile to place SeeTrue’s eye tracking technology into university’s headsets, which have no eye tracking capabilities at all, or is it better to use Varjo’s device, whenever eye tracking is needed. Motivated by previous research, we built a physical setup for SeeTrue device and virtual setup for Varjo device, in which the participant is directed to look at a white target dot shown on the black screen. We decided to use a moving target dot and a target dot, which changes its position on the screen, but stays at one place for two seconds. From the scripts that control the target dot position, actual positions of the targets were collected and compared with the gaze target positions that were received by the eye tracking devices. In our study, we used accuracy and precision as measures of performance. According to the results of this study, Varjo performed better, and the results stand for using Varjo’s device when eye tracking is needed, instead of placing SeeTrue’s system into headsets, which have no eye tracking capabilities. However, both devices were easy to use and highly capable of eye tracking. We recorded the results of mean error in visual angle within five degrees on both devices, and even with the moving target. This study, along with the other studies in the field, gives an idea and methodologies to one kind of performance testing of eye tracking devices.
Kokoelmat
- Avoin saatavuus [32150]