High-Frequency Near-Eye Ground Truth for Event-Based Eye Tracking

Abstract

Event-based eye tracking is a promising solution for efficient and low-power eye tracking in smart eyewear technologies. However, the novelty of event-based sensors has resulted in a limited number of available datasets, particularly those with eye-level annotations, crucial for algorithm validation and deep-learning training. This paper addresses this gap by presenting an improved version of a popular event-based eye-tracking dataset. We introduce a semi-automatic annotation pipeline specifically designed for event-based data annotation. Additionally, we provide the scientific community with the computed annotations for pupil detection at $200\,\textrm{Hz}$ 200 Hz .

Cite

Text

Simpsi et al. "High-Frequency Near-Eye Ground Truth for Event-Based Eye Tracking." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91989-3_19

Markdown

[Simpsi et al. "High-Frequency Near-Eye Ground Truth for Event-Based Eye Tracking." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/simpsi2024eccvw-highfrequency/) doi:10.1007/978-3-031-91989-3_19

BibTeX

@inproceedings{simpsi2024eccvw-highfrequency,
  title     = {{High-Frequency Near-Eye Ground Truth for Event-Based Eye Tracking}},
  author    = {Simpsi, Andrea and Aspesi, Andrea and Mentasti, Simone and Merigo, Luca and Ongarello, Tommaso and Matteucci, Matteo},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2024},
  pages     = {295-304},
  doi       = {10.1007/978-3-031-91989-3_19},
  url       = {https://mlanthology.org/eccvw/2024/simpsi2024eccvw-highfrequency/}
}