Device-Free Target Following with Deep Spatial and Temporal Structures of CSI

Ching Lan Chen, Chun Hsien Ko, Sau Hsuan Wu*, Heng Shih Tseng, Ronald Y. Chang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

A novel device-free target tracking and following method is proposed based on both the received signal strength (RSS) and channel state information (CSI) of WiFi signals. Different from the typical device-free target tracking method, we consider a scenario where the device-free target under tracking is followed by a device that transmits the reference signals for location tracking of the target and the device itself. To meet the goal, a deep spatial-temporal neural network model is designed to learn and exploit the multi-resolution spatial and temporal features of RSSI and CSI for location tracking. By experimental results on our testbed, we show that the average positioning accuracy of the proposed method for the device-free target can reach 0.773 meters, which has a 64 % improvement over the accuracy of 2.164 meters of a typical device-free tracking method under the same experimental condition.

Original languageEnglish
JournalJournal of Signal Processing Systems
DOIs
StateAccepted/In press - 2023

Keywords

  • CSI-based positioning
  • Deep neural networks
  • Device-free location tracking
  • Indoor positioning
  • RSS-based positioning

Fingerprint

Dive into the research topics of 'Device-Free Target Following with Deep Spatial and Temporal Structures of CSI'. Together they form a unique fingerprint.

Cite this