Saved in:
Bibliographic Details
Main Authors: Chen, Qinyu, Wang, Zuowen, Liu, Shih-Chii, Gao, Chang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.11771
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914645607972864
author Chen, Qinyu
Wang, Zuowen
Liu, Shih-Chii
Gao, Chang
author_facet Chen, Qinyu
Wang, Zuowen
Liu, Shih-Chii
Gao, Chang
contents 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$\times$ without losing accuracy when tested on a \texttt{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 \url{https://github.com/qinche106/cb-convlstm-eyetracking}.
format Preprint
id arxiv_https___arxiv_org_abs_2308_11771
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle 3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network
Chen, Qinyu
Wang, Zuowen
Liu, Shih-Chii
Gao, Chang
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68T10
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$\times$ without losing accuracy when tested on a \texttt{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 \url{https://github.com/qinche106/cb-convlstm-eyetracking}.
title 3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68T10
url https://arxiv.org/abs/2308.11771