We propose the design of a battery-free wearable eye tracker that achieves sub-millimeter tracking accuracy at high track ing rates. It tracks pupil’s 2D position based on pupil’s light absorption effect. With a few near-infrared (NIR) lights and photodiodes around the eye, NIR lights sequentially illu minate the eye from various directions while photodiodes sense spatial patterns of reflected light, which are used to infer pupil positions on the fly through a lightweight infer ence algorithm. The system also exploits characteristics of different eye movement stages and adjusts its sensing and computation accordingly for further energy savings. We have built a prototype with off-the-shelf hardware components and integrated it into a regular pair of glasses. Experiments with ten participants show that the system achieves 0.9-mm mean tracking accuracy (2.4 mm at the 95th percentile) at 120-Hz output frame rate, consuming 395µW mean power supplied by two small, thin solar cells on glasses side arms.
CITATION STYLE
Li, T., & Zhou, X. (2018). Battery-free eye tracker on glasses. In Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM (pp. 27–29). Association for Computing Machinery. https://doi.org/10.1145/3264877.3264885
Mendeley helps you to discover research relevant for your work.