Computer Vision-assisted Decimeter-level Single-antenna RSSI Localization Harnessing Dynamic Blockage Events

This paper demonstrates the feasibility of received power strength indicator (RSSI)-based single-antenna localization (R-SAL) with decimeter-level localization accuracy. To achieve decimeter-level accuracy, either fine-grained radio frequency (RF) information (e.g., channel state information) or coarse-grained RF information (e.g., RSSI) from more than multiple antennas is required. Meanwhile, owing to deficiency of single-antenna RSSI which only indicates a distance between a receiver and a transmitter, realizing fine-grained localization accuracy with single coarse-grained RF information is challenging. Our key idea to address this challenge is to leverage computer vision (CV) and to estimate the most likely Fresnel zone between the receiver and transmitter, where the role of RSSI is to detect blockage timings. Specifically, historical positions of an obstacle that dynamically blocks the Fresnel zone are detected by the CV technique, and we estimate positions at which a blockage starts and ends via a time series of RSSI. These estimated obstacle positions, in principle, coincide with points on the Fresnel zone boundaries, enabling the estimation of the Fresnel zone and localization of the transmitter. The experimental evaluation revealed that the proposed R-SAL achieved decimeter-level localization in an indoor environment, which is comparable to that of a simple previous RSSI-based localization with three receivers.