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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS) |
Place of Publication | Danvers |
Publisher | IEEE |
Number of pages | 5 |
ISBN (Electronic) | 979-8-3503-0026-0 |
ISBN (Print) | 979-8-3503-0027-7 |
DOIs | |
Publication status | Published - 2023 |
Event | 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS) - Toronto, Canada Duration: 19 Oct 2023 → 21 Oct 2023 |
Conference
Conference | 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS) |
---|---|
Country/Territory | Canada |
City | Toronto |
Period | 19/10/23 → 21/10/23 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- Pupil tracking
- event cameras
- sparsity
- ConvLSTM
- healthcare
- AR/VR