Crowdsourcing Trajectory Based Indoor Positioning Multisource Database Construction on Smartphones

The bottleneck of fingerprinting-based indoor localization method is the extensive human effort that is required to construct and update the database for indoor positioning. In this paper, we propose a crowdsourcing trajectory based indoor positioning multisource database construction method that can be used to collect fingerprints and construct the radio map by exploiting the trajectories of smartphone users. By integrating multisource information from the smartphone sensors (e.g., camera, accelerometer, and gyroscope), this system can accurately reconstruct the geometry of trajectories. After then, the location of trajectories can be spatially estimated in the reference coordinate system. The experimental results show that the average calibration error of the fingerprints is 0.67 m. A weighted k-nearest neighbor method (without any optimization) and image matching method are used to evaluate the performance of constructed multisource database. The average localization error of RSS based indoor positioning and image based positioning are 3.2 m and 1.2 m respectively.