Enabling Gesture-based Interactions with Objects Longfei Shangguan

Increasing numbers of everyday objects in libraries, stores and warehouses are instrumented with passive RFID tags, resulting in a ripe opportunity for gesture-based interactions with people. By a simple act of picking up and gesturing with an RFID-tagged object, users can send their opinions and sentiments about that object to the cloud. Prior work in RFID-based gesture tracking relies on multiple bulky and expensive antennas and readers to function, which incurs unacceptable infrastructure costs for large-scale ubiquitous deployment (over an entire warehouse or mall, for example) thus hindering practical adoption. In this paper, we propose Pantomime, the first RFID-based gesture recognition system that uses just a single antenna per geographical area of coverage. Our key insight is to replace the conventional multiple antenna single tag tracking framework with an equivalent multiple tag single antenna system. Through a novel tag coordination protocol and a lightweight tracking algorithm, Pantomime enables accurate gesture tracking that works for objects tagged with just two RFID tags. We implement a real-time prototype of Pantomime with commercial off-the-shelf (COTS) RFID readers and antennas. Extensive evaluations and real-world case studies in a classroom and a retail store demonstrate that Pantomime achieves comparable gesture tracking accuracy (87%) to state-of-the-art multi-antenna schemes (88%) at a minimal deployment cost.