LMDD: Light-Weight Magnetic-Based Door Detection with Your Smartphone

Abstract

Doors are important landmarks for indoor positioning systems. Hence an accurate and light-weight door detection approach is highly desired. The state-of-the-art solutions are either vision based or infrastructure based, which incur nontrivial device or management cost. This paper presents a novel approach, Light-weight Magnetic-based Door Detection (LMDD), which only relies on the information from built-in sensors of a smartphone. LMDD detects a door by analyzing the change of magnetic signal and extracting special features caused by doors. It is light-weight in both computation and infrastructure cost. We have implemented a prototype of LMDD that has been installed on various Android phones. Experimental results show that LMDD achieves door detection accuracy of 74% in average, ranging from 66% to 85% in various typical environments such as offices, classrooms, residential houses, and a hospital.