Multi-Source Data Fusion Method for Indoor Localization System

In this paper, a multi-source data fusion method for indoor localization system is designed to realize the high-accuracy locations. The indoor localization system consists of WiFi nodes, ultra-wideband (UWB) nodes and inertial measurement unit (IMU), where the IMU is integrated in a android smartphone. For our indoor localization system, there include two stages: offline stage and online stage. In the offline stage, we use crowdsourcing method to train a fingerprint database, which can be constructed at a low labor cost. In the online stage, particle filter to estimate the locations based on WiFi received signal strengths, UWB rangings, and IMU data. Experimental results show that our indoor localization system based on the multi-source data fusion method expands the coverage and improves the localization accuracy.

[1]  Robert A. Scholtz,et al.  Ranging in a dense multipath environment using an UWB radio link , 2002, IEEE J. Sel. Areas Commun..

[2]  John W. Fisher,et al.  Nonparametric belief propagation for self-localization of sensor networks , 2005, IEEE Journal on Selected Areas in Communications.

[3]  Lei Li,et al.  Vital Sign Integrated Tracking by Predictive KNN and Kalman Filter with UWB Radars , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[4]  Eric Foxlin,et al.  Pedestrian tracking with shoe-mounted inertial sensors , 2005, IEEE Computer Graphics and Applications.

[5]  Zhiyong Chen,et al.  Quaternion-based Complementary Filter for Aiding in the Self-Alignment of the MEMS IMU , 2019, 2019 IEEE International Symposium on Inertial Sensors and Systems (INERTIAL).

[6]  Zheng Wang,et al.  Integrated Wearable Indoor Positioning System Based On Visible Light Positioning And Inertial Navigation Using Unscented Kalman Filter , 2019, 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP).

[7]  Anshul Rai,et al.  Zee: zero-effort crowdsourcing for indoor localization , 2012, Mobicom '12.

[8]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[9]  Weiwei Xia,et al.  A 3-D Indoor Positioning System Using Asymmetry Double-Sided Two-Way Ranging And Chan Assisted Extended Kalman Filter , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[10]  Chi Wu,et al.  TDOA Based Indoor Positioning with NLOS Identification by Machine Learning , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[11]  Moe Z. Win,et al.  A smartphone localization algorithm using RSSI and inertial sensor measurement fusion , 2013, 2013 IEEE Global Communications Conference (GLOBECOM).

[12]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[13]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .