Evaluation of Bayesian Approaches for Multi-sensor Multi-network Seamless Positioning

Heidi Kuusniemi, Liang Chen, Ling Pei, Jingbin Liu, Yuwei Chen, Laura Ruotsalainen, Ruizhi Chen

Abstract:	This paper discusses different Bayesian framework alternatives and system models for fusing multiple sensors and multiple network navigation solutions for pedestrian positioning. Sensor and network measurements are integrated together, namely GPS provided location, accelerometer derived pedestrian speed, digital compass providing direction, and Bluetooth network derived location based on fingerprinting. The information sources are fused in a Bayesian network with three different system and measurement models. The models are compared and evaluated based on the accuracy they provide with near error-free data and with low-cost sensor provided data from a pedestrian experiment inside an office building. This paper provides an initial fusion model comparison exercise which is a step on the path for obtaining a robust, seamless, and mobile sensor fusion solution for pedestrian navigation.
Published in:	Proceedings of the 24th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2011) September 20 - 23, 2011 Oregon Convention Center, Portland, Oregon Portland, OR
Pages:	2137 - 2144
Cite this article:	Kuusniemi, Heidi, Chen, Liang, Pei, Ling, Liu, Jingbin, Chen, Yuwei, Ruotsalainen, Laura, Chen, Ruizhi, "Evaluation of Bayesian Approaches for Multi-sensor Multi-network Seamless Positioning," Proceedings of the 24th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2011), Portland, OR, September 2011, pp. 2137-2144.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In