A method of personal positioning for indoor customer tracking utilizing wearable inertial sensors

In order to achieve in-store customer traffic tracking, a method should be capable of catching personnel routings and ambulation trajectories while shopping. In this study, we presented a practical method for indoor personnel positioning, especially focusing on ambulatory path recognition and trajectory estimation. The method was designed to be autonomous needless of neither external measures nor cumbersome installations to a store environment. To avoid an inherent problem of trajectory estimation through Dead-Reckoning algorithm, an advanced probabilistic Map Matching method was applied utilizing a Particle filtering technique. The experiment was performed to confirm the utility of the proposed method in a small retail store. The result showed that the proposed method provided feasible successes in tracking personnel positioning.