Compass fusion

Abstract

Indoor localization has attracted more and more attention with the growth of emerging location-based services (LBS), e.g. microblogging, location-based content sharing, and interactive indoor multimedia display. In the literature, wireless-based indoor positioning for hand-held mobile devices is in meter-level precision, including WLAN (Wi-Fi), Bluetooth, and GSM-based approaches. A smartphone-based LBS fusing various sensors, such as accelerometer, digital compass, Wi-Fi, and GPS, can achieve the localization at a better room-level accuracy. In addition, the scanned Wi-Fi access point can determine the room-level identification for a mobile user. However, when multiple human subjects locating in the same coverage area for the same Wi-Fi access points, e.g. in the same room, the individuals often cannot be identified from each other. Therefore, in order to achieve a high precision in a centimeter level for the indoor localization, we extended our head detection scheme of detecting people from depth camera, with an average estimation accuracy of 98.72%, and an average distortion of 2.06 cm. That is, because the compass of a mobile device can provide the orientation of how a human subject holds the mobile device, we proposed to fuse the orientation information analyzed according to the trajectory of a human subject obtained from depth cameras, for enhancing both the indoor localization and people identification accuracies to a centimeter level.