Haojian Jin, Zhijian Yang, Swarun Kumar, and Jason I. Hong

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)

December 2017

We introduce RF-Wear, an accurate and wearable solution to track movements of a user’s body using passive RFIDs embedded in their clothing. RF-Wear processes wireless signals reflected off these tags to a compact single-antenna RFID reader in the user’s pocket. In doing so, RF-Wear enables a first-of-its-kind body-frame tracking mechanism that is lightweight and convenient for day-to-day use, without relying on external infrastructure. At the heart of RF-Wear is a novel primitive that computes angles between different parts of the user’s body using the RFID tags attached to them. RF-Wear achieves this by treating groups of RFID tags as an array of antennas whose orientation can be computed accurately relative to the handheld reader. By computing the orientation of individual body parts, we demonstrate how RF-Wear reconstructs the real-time posture of the user’s entire body frame. Our solution overcomes multiple challenges owing to the interactions of wireless signals with the body, the 3-D nature of human joints and the flexibility of fabric on which RFIDs are placed. We implement and evaluate a prototype of RF-Wear on commercial RFID readers and tags and demonstrate its performance in body-frame tracking. Our results reveal a mean error of 8-12° in tracking angles at joints that rotate along one degree-of-freedom, and 21°- azimuth, 8°- elevation for joints supporting two degrees-of-freedom.

RFID, smart fabric, wearable computing