5/26/16: Towards Continuous Eye Monitoring in the Mobile Environment with Ultra Low-power Computational Eyeglasses

May 26, 2016

About the Webinar:

The human eye offers a fascinating window into an individual’s health, cognitive attention, and decision making, but we lack the ability to continually measure these parameters in the natural environment. The challenges lie in: a) handling the complexity of continuous high-rate sensing from a camera and processing the image stream to estimate eye parameters, b) operating under stringent constraints imposed by an eyeglass form-factor device in terms of battery size and sensor placement, and c) dealing with the wide variability in illumination conditions in the natural environment.

This talk will discuss a new eyeglass form-factor platform, iShadow, that is designed to continually track the state of the eye. Unlike commercial eye trackers, iShadow is low power and operates at 5mW — 30mW of power while providing several eye parameters of interest including continuous tracking of gaze, (micro)saccadic eye movements, eye closures and blinks, and pupil dilation. The central idea underlying many of these techniques is the ability to reduce the number of pixels sampled and processed in-order to estimate the various parameters of the eye. We provide an overview of the iShadow architecture and algorithms, and some of the ongoing research directions.

Recommended Reading:

• iShadow: Design of a Wearable, Real-Time Mobile Gaze Tracker
• CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass

About Deepak Ganesan and Addison Mayberry:

Deepak Ganesan, Ph.D. is Associate Professor in the Department of Computer Science at the University of Massachusetts Amherst. Dr. Ganesan has worked for over a decade at the intersection of wireless sensing for health, wireless and mobile sensing, and low-power embedded systems, and designs novel systems based on strong theoretical foundations and grounded in real-world deployment and experimentation. He leads the Center for Mobile Health Sensing at UMass, and is on the advisory board of the Center for Personal Health Monitoring. More about Deepak Ganesan.

Addison Mayberry is a graduate researcher working with Dr. Deepak Ganesan in the College of Information and Computer Sciences at UMass Amherst. His research focus is in cyber-physical systems (CPS), specifically in embedded devices and sensors, as well as the fields of mobile health (mHealth) and wearable computing. His research goal is to push the technical achievements in small-form-factor devices of the past few years into novel CPS research that will positively affect people’s everyday lives. He emphasizes the synthesis of other fields, both in and out of computer science, into mHealth to see what interesting research opportunities could arise. More about Addison Mayberry.