FM-track: pushing the limits of contactless multi-target tracking using acoustic signals

Abstract

Contactless acoustic motion tracking enables new opportunities to interact with smart devices, such as smartphones and voice-controlled smart assistants. The speakers and microphones integrated in these devices provide unique opportunities to simultaneously track multiple targets in a fine-grained manner. To this end, we propose a system, namely FM-Track, that enables contactless multi-target tracking using acoustic signals. We first introduce a signal model to characterize the location and motion status of targets by fusing the information from multiple dimensions (i.e., range, velocity, and angle of targets). Then we develop a series of techniques to separate signals reflected from multiple targets and accurately track each individual target. We implement and evaluate FM-Track on both research-purpose hardware platform (i.e., Bela) and commercial devices (i.e., smartphones and smart speakers). Extensive experiments show that FM-Track can successfully differentiate two targets with a spacing as small as 1 cm, and achieve a median tracking accuracy of 0.86 cm and 0.11 cm for absolute range and displacement estimates respectively. For multi-target tracking, FM-Track can accurately track four targets and the tracking range can be up to 3 m.