Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.04779 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909891640164352 |
|---|---|
| author | Aspesi, Andrea Simpsi, Andrea Tognoli, Aaron Mentasti, Simone Merigo, Luca Matteucci, Matteo |
| author_facet | Aspesi, Andrea Simpsi, Andrea Tognoli, Aaron Mentasti, Simone Merigo, Luca Matteucci, Matteo |
| contents | Event-based cameras are becoming a popular solution for efficient, low-power eye tracking. Due to the sparse and asynchronous nature of event data, they require less processing power and offer latencies in the microsecond range. However, many existing solutions are limited to validation on powerful GPUs, with no deployment on real embedded devices. In this paper, we present EETnet, a convolutional neural network designed for eye tracking using purely event-based data, capable of running on microcontrollers with limited resources. Additionally, we outline a methodology to train, evaluate, and quantize the network using a public dataset. Finally, we propose two versions of the architecture: a classification model that detects the pupil on a grid superimposed on the original image, and a regression model that operates at the pixel level. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EETnet: a CNN for Gaze Detection and Tracking for Smart-Eyewear Aspesi, Andrea Simpsi, Andrea Tognoli, Aaron Mentasti, Simone Merigo, Luca Matteucci, Matteo Computer Vision and Pattern Recognition Event-based cameras are becoming a popular solution for efficient, low-power eye tracking. Due to the sparse and asynchronous nature of event data, they require less processing power and offer latencies in the microsecond range. However, many existing solutions are limited to validation on powerful GPUs, with no deployment on real embedded devices. In this paper, we present EETnet, a convolutional neural network designed for eye tracking using purely event-based data, capable of running on microcontrollers with limited resources. Additionally, we outline a methodology to train, evaluate, and quantize the network using a public dataset. Finally, we propose two versions of the architecture: a classification model that detects the pupil on a grid superimposed on the original image, and a regression model that operates at the pixel level. |
| title | EETnet: a CNN for Gaze Detection and Tracking for Smart-Eyewear |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.04779 |