Broad Motion Mode Recognition for Portable Navigation

Mostafa Elhoushi, Jacques Georgy, Michael Korenberg, Aboelmagd Noureldin

Abstract:	The main challenge facing portable navigation is the ability to obtain accurate positioning results in urban canyons or indoors where Global Navigation Satellite System (GNSS) signals are weak or unavailable. Self-contained motion sensors, such as accelerometers and gyroscopes, are hence used; however, their accuracies are not sufficient. One of the methods used to improve positioning performance is to recognize the motion mode of the user carrying the portable device. The illustrated work presents a motion mode recognition module implemented within a portable navigation device recognizing a broad range of motion modes. The motion mode recognition is robust to the device usage, device orientation, user's motion characteristics, and GNSS signal availability. The motion modes recognized by the module include stationary, walking, running, cycling, land-based vessel (including car, train, or bus, whether sitting or standing), walking up/down stairs, going up/down in an elevator, standing in an escalator, walking on an escalator, standing on a moving walkway, and walking on a moving walkway. The recognition module has been implemented and tested in real-time on smartphones, tablets, smart glasses, and smartwatches of various brands and types.
Published in:	Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014) September 8 - 12, 2014 Tampa Convention Center Tampa, Florida
Pages:	1768 - 1773
Cite this article:	Elhoushi, Mostafa, Georgy, Jacques, Korenberg, Michael, Noureldin, Aboelmagd, "Broad Motion Mode Recognition for Portable Navigation," Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014), Tampa, Florida, September 2014, pp. 1768-1773.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In