CSI-based Indoor Tracking with Positioning-Assisted

High accurate indoor positioning and tracking is crucial to pervasive applications such as elderly care, intrusion monitor and behavior analysis. Recently, Channel State Information(CSI) as a fine grained physical layer information has been proposed to achieve high positioning accuracy by using laborious learning-based methods. In this work, we propose a CSI-based indoor tracking system which combines velocity estimation and dead reckoning to track human trajectory. Additionally, an efficient quantization method for depicting the correlation between human velocity and CSI dynamics is raised. On this basis, the results of indoor positioning could be used for trajectory initialization and calibration. Extensive experiments demonstrate that our system provides high accurate trajectory information.