Collaborative Wi-Fi fingerprint training for indoor positioning

As the scope of location-based applications and services further reach into our everyday lives, the demand for more robust and reliable positioning becomes ever more important. However indoor positioning has never been a fully resolved issue due to its complexity and necessity to adapt to different situations and environment. Inertial sensor and Wi-Fi signal integrated indoor positioning have become good solutions to overcome many of the problems. Yet there are still problems such as inertial heading drift, wireless signal fluctuation and the time required for training a Wi-Fi fingerprint database. The collaborative Wi-Fi fingerprint training (cWiDB) method proposed in this paper enables the system to perform inertial measurement based collaborative positioning or Wi-Fi fingerprinting alternatively according to the current situation. It also reduces the time required for training the fingerprint database. Different database training methods and different training data size are compared to demonstrate the time and data required for generating a reasonable database. Finally the fingerprint positioning result is compared which indicates that the cWiDB is able to achieve the same positioning accuracy as conventional training methods but with less training time and a data adjustment option enabled.