SmartMTra: Robust Indoor Trajectory Tracing Using Smartphones

Abstract

Using smartphones for indoor motion trajectory tracing has attracted a lot of attention in recent years, which offers great potential to support a broad spectrum of applications in indoor environment, including elder care, business analysis, and navigation. Yet most existing approaches only work for certain pedestrian’s motion modes or smartphone’s carrying patterns, which lack the robustness and adaptability to general scenarios. In this paper, we propose SmartMTra, a comprehensive, robust, and accurate solution for indoor motion trajectory tracing based on smartphone’s built-in inertial sensors. Through analyzing the data from inertial sensors, we extract a set of features that are found to be highly related to human’s physical activities, which can help to identify motion mode and phone’s carrying pattern through a decomposition model. After that, SmartMTra utilizes the pedestrian dead reckoning technique, which involves estimating step counts, step-length, and heading direction, to achieve accurate trajectory tracing. We have conducted extensive experiments to evaluate the performance of SmartMTra in a campus building, and the results demonstrate the robustness of SmartMTra in various scenarios, as well as the superiority of SmartMTra over the state-of-the-art solutions.