Motion Recognition Assisted Indoor Wireless Navigation on a Mobile Phone

L. Pei, R. Chen, J. Liu, W. Chen, H. Kuusniemi, T. Tenhunen, T. Kröger, Y. Chen, H. Leppäkoski, J. Takala

Abstract:	The paper presents an indoor navigation solution combining physical motion recognition with WLAN positioning on a smart phone. Orientationindependent features are extracted from vertical and horizontal components of acceleration. The simple features such as the mean of horizontal acceleration, the variance of acceleration magnitude, and the variance of horizontal acceleration are selected as the nodes in a decision tree. Six common motion modes during indoor navigation, e.g., static, standing with hand swinging, normal walking with holding the phone in hand, normal walking with hand swinging, fast walking, and U-turning are detected. A fingerprinting based WLAN positioning approach offers the headings and initial positions for pedestrian dead reckoning with about 10 seconds interval. The velocities for six motion modes are trained by five testers and applied in the dead reckoning during the WLAN positioning gap. Test results indicate that the motion mode is recognized correctly in 95% of test cases. The field test shows 4.6m horizontal mean error for motion recognition assisted indoor wireless positioning.
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:	3366 - 3375
Cite this article:	Pei, L., Chen, R., Liu, J., Chen, W., Kuusniemi, H., Tenhunen, T., Kröger, T., Chen, Y., Leppäkoski, H., Takala, J., "Motion Recognition Assisted Indoor Wireless Navigation on a Mobile Phone," Proceedings of the 23rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2010), Portland, OR, September 2010, pp. 3366-3375.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In