English

Gaze Estimation on Spresense

Computer Vision and Pattern Recognition 2023-11-21 v2 Human-Computer Interaction Robotics

Abstract

Gaze estimation is a valuable technology with numerous applications in fields such as human-computer interaction, virtual reality, and medicine. This report presents the implementation of a gaze estimation system using the Sony Spresense microcontroller board and explores its performance in latency, MAC/cycle, and power consumption. The report also provides insights into the system's architecture, including the gaze estimation model used. Additionally, a demonstration of the system is presented, showcasing its functionality and performance. Our lightweight model TinyTrackerS is a mere 169Kb in size, using 85.8k parameters and runs on the Spresense platform at 3 FPS.

Cite

@article{arxiv.2308.12313,
  title  = {Gaze Estimation on Spresense},
  author = {Thomas Ruegg and Pietro Bonazzi and Andrea Ronco},
  journal= {arXiv preprint arXiv:2308.12313},
  year   = {2023}
}
R2 v1 2026-06-28T12:02:46.611Z