CVHCROAug 23, 2023

Gaze Estimation on Spresense

arXiv:2308.12313v21 citationsh-index: 6
Originality Synthesis-oriented
AI Analysis

This work addresses efficient gaze estimation for embedded applications like human-computer interaction, but it is incremental as it applies an existing method to a new hardware platform.

The paper tackled gaze estimation by implementing a lightweight system on the Sony Spresense microcontroller, achieving a model size of 169Kb with 85.8k parameters and running at 3 FPS.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes