Abstract
Human identification is a prerequisite for many personalized services in smart spaces. This paper presents RFree-ID, the first unobtrusive RFID-based human identification system irrespective of walking cofactors (e.g. appearance changes or inconsistent walking paths). The key insight is that the RFID reader and tags can serve as a radio gate, and the walking-induced RF signal fluctuations from tags are capable of perceiving different walking patterns when people cross this gate. More importantly, spatially separated tags can provide abundant temporal and spatial information for amplifying discrepancies among people and minifying the influence of walking cofactors. Therefore, after collecting phase fluctuations received from RFID tags, RFree-ID identifies people by using a sequence of signal processing techniques and a well-designed matching algorithm. The system is implemented on COTS RFID devices, and extensive experimental evaluation under various conditions validates the high reliability and robustness of our system.