Indoor Floor Map Crowdsourcing Building Method Based on Inertial Measurement Unit Data

Abstract

Currently, the indoor navigation has attracted lots of attention and been considered as the most prominent technology in the future. However, the biggest obstacle that hinders the promotion of the indoor navigation is the cost of building floor map. In the unknown indoor environment, it will take a lot of resources to acquire or build indoor floor map. Therefore, in this paper, in order to reduce the floor map building cost, we mainly propose to utilize the pedestrian dead reckoning (PDR) method through massive users' inertial measurement unit (IMU) data to build indoor floor map. We proposed a novel algorithm through the density analysis of massive crowdsourcing trajectories, and keep the most proper trajectories with the suitable hotspots to generate floor map. The proposed algorithm relies on the improved PDR algorithm based on the proposed indoor walking model. We have implemented the proposed algorithm in our lab and evaluated its performances. The simulation results show that the proposed algorithm could automatically generate the floor map in the unknown environments with lower cost, which would contribute a lot for the indoor navigation technology.