University of Twente Student Theses
Combining object detection and eye tracking to identify points of interest for VR art exhibition visitors
Kulyk, D. (2023) Combining object detection and eye tracking to identify points of interest for VR art exhibition visitors.
|
PDF
44MB |
| Abstract: | Understanding visitors' preferences for artistic content can help enhance their engagement and enjoyment of the paintings. To identify points of interest, we propose to combine an object detection algorithm in artworks with eye-tracking data from users participating in a virtual reality (VR) art exhibition. In the first phase, we fine-tune the object detection model on the two manually collected datasets to locate objects within the VR exhibition paintings. In the second phase, we correlate gaze data with object data for statistical analysis to make inferences about users' regions of interest. Our findings indicate that participants spent more time looking at the meaningful objects of the paintings. Several of these object categories, including Human head, Human hair, Human mouth, Human Eye, and Person achieve precision scores above 50% after fine-tuning the object detection model. This shows that using a computer vision task to identify the areas where participants fixate their gaze holds some promise for gaining insights into user preferences for artistic content. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Business & IT BSc (56066) |
| Link to this item: | https://purl.utwente.nl/essays/95999 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page