Towards Arbitrary Placement of Multi-sensors Assisted Mobile Navigation System

X. Zhao, S. Saeedi, N. El-Sheimy, Z. Syed, C. Goodall

Abstract:	Multi-sensors assisted navigation system is one of the most promising solutions for GPS-denied areas. However, as the portable positioning device can be arbitrarily placed on the user's body, it violates the assumed condition of sensor enabled positioning: the alignment. This poses great challenge since sensors´ placement greatly impacts on the positioning solution. The paper attempts to solve this problem by classifying the placement mode from the accelerometer and gyro signals. Then the system adapts proper pedestrian dead reckoning algorithms according to the identified device placement. Six commonly used placement modes including belt, pocket, backpack, in-hand dangling, messaging and near the ear talking are considered as the study cases in this paper. Simple time and frequency domain features are extracted from the inertial sensors then some machine learning algorithms, such as k-nearest neighbour, artificial neural networks, and support vector machines are applied for classification. Subsequently, step detections can be conducted by selecting the most appropriate sensor. Stride length and heading can be further estimated. From some preliminary field test results, the placement-aware solution shows significant improvement over conventional pedestrian solutions. The system fits for a variety of applications in the mass market, such as E-911, personnel/patient monitoring, indoor positioning, and many other location-based services.
Published in:	Proceedings of the 23rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2010) September 21 - 24, 2010 Oregon Convention Center, Portland, Oregon Portland, OR
Pages:	556 - 564
Cite this article:	Zhao, X., Saeedi, S., El-Sheimy, N., Syed, Z., Goodall, C., "Towards Arbitrary Placement of Multi-sensors Assisted Mobile Navigation System," Proceedings of the 23rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2010), Portland, OR, September 2010, pp. 556-564.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In