Collaborative Wi-Fi fingerprint training for indoor positioning

Jing, Hao and Pinchin, James and Hill, Chris and Moore, Terry (2014) Collaborative Wi-Fi fingerprint training for indoor positioning. In: 27th International Technical Meeting of The Satellite Division of the Institute of Navigation, 8-12 Sept 2014, Tampa, Florida.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

As the scope of location-based applications and services further reach into our everyday lives, the demand for more robust and reliable positioning becomes ever more important. However indoor positioning has never been a fully resolved issue due to its complexity and necessity to adapt to different situations and environment. Inertial sensor and Wi-Fi signal integrated indoor positioning have become good solutions to overcome many of the problems. Yet there are still problems such as inertial heading drift, wireless signal fluctuation and the time required for training a Wi-Fi fingerprint database. The collaborative Wi-Fi fingerprint training (cWiDB) method proposed in this paper enables the system to perform inertial measurement based collaborative positioning or Wi-Fi fingerprinting alternatively according to the current situation. It also reduces the time required for training the fingerprint database. Different database training methods and different training data size are compared to demonstrate the time and data required for generating a reasonable database. Finally the fingerprint positioning result is compared which indicates that the cWiDB is able to achieve the same positioning accuracy as conventional training methods but with less training time and a data adjustment option enabled.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published in: Proceedings of the 27th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2014), Tampa, Florida, September 2014, pp. 1669-1678.
Keywords: Collaborative positioning; Indoor positioning; Wi-Fi fingerprint; SLAM
Schools/Departments: University of Nottingham UK Campus > Faculty of Engineering
Depositing User: Eprints, Support
Date Deposited: 24 May 2016 18:49
Last Modified: 23 Sep 2016 04:41
URI: http://eprints.nottingham.ac.uk/id/eprint/33478

Actions (Archive Staff Only)

Edit View Edit View