Classifying Elevators and Escalators in 3D Pedestrian Indoor Navigation

Abstract

For quick and targeted rescuing of individuals in emergency situations indoors, an accurate knowledge of the current floor-level by the rescue personnel is essential. In this paper, we investigate the capabilities to recognize ransportation platforms like elevators and escalators using foot mounted inertial measurement units including magnetometer and barometer for applications in 3D pedestrian navigation. We evaluate Features and classification concepts for discriminating between activities in static environments, elevator environments (up/down), and escalator environments (up, down) in everyday situations. The features are compared via an information gain metric and selected classifier concepts are analyzed with focus on fast response times necessary for dead-reckoning navigation. We identified features exploiting statistical characteristics of the magnetic intensity and the acceleration to be most promising when fast response times are required. The resulting feature space is highly non-linear and is best approximated locally.