Files and links (1)
CC BY V4.0, Open Access
Thesis
Development of Eye Tracking System Via EOG and Eyes Image
Washington State University
Master of Science (MS), Washington State University
2023
DOI:
https://doi.org/10.7273/000005196
Abstract
Recent wearable technologies advances have enabled ways for people to interact with external devices, known as human−machine interfaces (HMIs). Electrophysiology signals, such as electrooculography (EOG), electromyography (EMG), electroencephalogram (EEG), and electrocardiogram (ECG) from body movements, contain critical information regarding physical/psychological health, perception, intention, and preference. Among them, EOG, measured by wearable devices, is often used for eye movement-enabled HMI. However, most prior studies have utilized conventional gel electrodes for EOG recording. The gel is problematic due to skin irritation, while separate bulky electronics cause motion artifacts. Also, EOG signals are susceptible to the sensor's skin-contact quality, limiting the precise detection of eye angles and gaze. To solve these problems, this thesis presents two types of eye movements monitoring systems – 1) a soft wireless EOG Headband for persistent HMI and 2) a camera-based gaze and eye direction tracking system. The first part of this thesis presents a soft material-based, all-in-one headband EOG device, which can detect eye movements and use an HMI for RC car. The portable and wearable EOG system enables real-time, continuous, and long-term recording of EOG signals to classify eye movements. Various dry electrodes, such as carbon nanotube paper composite and fractal gold electrodes, have been characterized and used for detecting EOG. A set of signal processing data demonstrates successful real-time classification of eye motions via the convolutional neural network (CNN). The second part presents a two-camera eye-tracking system and a data classification method for HMI to compensate for the EOG device. This system integrates machine-learning technology for a continuous real-time classification of gaze and eye directions, which is used to precisely control a robotic arm.
Metrics
4 File views/ downloads
33 Record Views
Details
- Title
- Development of Eye Tracking System Via EOG and Eyes Image
- Creators
- Seunghyeb Ban
- Contributors
- Jong Hoon Kim (Advisor)Xiaolin Chen (Committee Member)Dave Ph.D Kim (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- Engineering and Computer Science (VANC), School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 108
- Identifiers
- 99901019838401842
- Language
- English
- Resource Type
- Thesis