Development and evaluation of walking path estimation system using sensors of Android device and vector map matching

In this paper, we propose a new system for estimating walking paths, and people's indoor location (e.g., a floor or a room where user is staying) for life-logging. Our proposed system utilizes an acceleration sensor and an orientation sensor of an Android device, and the map matching with the preplotted vector map. Particularly emphasized new techniques in this paper are methods to estimate locations where walking directions are changed, to specify whether an elevator is used to move to another floor, and to estimate the walking path with the vector map matching. Through the experiment and evaluation, we have clarified that the proposed method has successfully estimated a walking path with accuracy of more than 80[%] in all routes, and 92[%] if an elevator is not included.