Journal article

Accurate Step Length Estimation for Pedestrian Dead Reckoning Localization Using Stacked Autoencoders

Fuqiang Gu, Kourosh Khoshelham, Chunyang Yu, Jianga Shang

IEEE Transactions on Instrumentation and Measurement | Institute of Electrical and Electronics Engineers | Published : 2019

Abstract

Pedestrian dead reckoning (PDR) is a popular indoor localization method due to its independence of additional infrastructures and the wide availability of smart devices. Step length estimation is a key component of PDR, which has an important influence on the performance of PDR. Existing step length estimation models suffer from various limitations such as requiring knowledge of user's height, lack of consideration of varying phone carrying ways, and dependence on spatial constraints. To solve these problems, we propose a deep learning-based step length estimation model, which can adapt to different phone carrying ways and does not require individual stature information and spatial constrain..

View full abstract

Grants

Awarded by National Key Research and Development Program of China


Awarded by China Scholarship Council-University of Melbourne Research Scholarship


Funding Acknowledgements

This work was supported in part by the National Key Research and Development Program of China under Grant 2016YFB0502200 and in part by the China Scholarship Council-University of Melbourne Research Scholarship under Grant CSC 201408420117. The Associate Editor coordinating the review process was Subhas Mukhopadhyay. (Corresponding author: Fuqiang Gu.)