The idea of augmented reality -- the ability to look at a physical object through a camera and view annotations about the object is certainly not new. Yet, this apparently feasible vision has not yet materialized into a precise, fast, and comprehensively usable system. This project asks: What does it take to enable augmented reality (AR) on smartphones today? To build a ready-to-use mobile AR system, we adopt a top-down approach cutting across smartphone sensing, computer vision, cloud offloading, and linear optimization. Our
proposed system OverLay allows random physical object
tagging from camera's viewfinder. Later, these tags can be
seen by others from different angles, locations, and times.
Our approach does not require changes to infrastructure,
localization schemes, specialized cameras, or modification
to phone's operating system. Designed and developed for
current generation smartphones, our experiments in an indoor setup shows promising results. If made commercially available,
OverLay can immediately apply to city tourism, PoI discovery, infrastructure maintenance, and object privacy.
This work won best demo at HotMobile 2015 and appeared in ACM MobiSys 2015 main conference.