3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network
METADATA ONLY
Loading...
Author / Producer
Date
2023
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
This paper presents a sparse Change-Based Convolutional Long Short-Term Memory (CB-ConvLSTM) model for event-based eye tracking, key for next-generation wearable healthcare technology such as AR/VR headsets. We leverage the benefits of retina-inspired event cameras, namely their low-latency response and sparse output event stream, over traditional frame-based cameras. Our CB-ConvLSTM architecture efficiently extracts spatio-temporal features for pupil tracking from the event stream, outperforming conventional CNN structures. Utilizing a delta-encoded recurrent path enhancing activation sparsity, CB-ConvLSTM reduces arithmetic operations by approximately 4.7× without losing accuracy when tested on a v2e-generated event dataset of labeled pupils. This increase in efficiency makes it ideal for real-time eye tracking in resource-constrained devices. The project code and dataset are openly available at https://github.com/qinche106/cb-convlstm-eyetracking.
Permanent link
Publication status
published
Editor
Book title
2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Journal / series
Volume
Pages / Article No.
10389062
Publisher
IEEE
Event
Biomedical Circuits and Systems Conference (BioCAS 2023)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Pubil tracking; Event cameras; Sparsity; ConvLSTM; Healthcare; AR/VR
Organisational unit
02533 - Institut für Neuroinformatik / Institute of Neuroinformatics
Notes
Funding
Related publications and datasets
Is supplemented by: https://github.com/qinche106/cb-convlstm-eyetracking