Computational Eyeglasses for Advanced Context Sensing

Abstract:

Continuous real-time tracking of the eye and field-of-view of an individual is profoundly important to understanding how humans perceive and interact with cyber-physical systems. Such continuous monitoring can enable detection of hazardous behaviors such as drowsiness while driving, mental health issues such as schizophrenia, addictive behavior and substance abuse, neurological disease progression, head injuries, and others. This proposal seeks to perform fundamental cross-disciplinary research into a vertically-integrated architecture for designing novel ultra-low-power and affordable real-time visual context sensing systems, thereby advancing the state of the art in on-body context sensing. Our work will advance both the technology and engineering of cyber-physical systems by designing an innovative paradigm involving next-generation computational eyeglasses with capability for real-time visual context sensing and inference in conjunction with on-body and infrastructure sensors, and real-time interventions in transportation and health. The proposed effort integrates novel research into low-power embedded systems, image representation, image processing and machine learning, and on-body sensing and inference, to advance the state-of-art in body sensing for CPS applications.