With the development of indoor localization technology, the location-based services such as product advertising recommendation in the shopping mall attract widespread attention, as precise user location significantly improves the efficiency of advertising push and brings broader profits. However, most of the Wi-Fi-based indoor localization approaches requiring professionals to deploy expensive beacon devices and intensively collect fingerprints in each location grid, which severely limits its extensive promotion. We introduce a zero-cost indoor localization algorithm utilizing crowdsourcing fingerprints to obtain the shop recognition where the user is located. Naturally utilizing the Wi-Fi, GPS, and time-stamp fingerprints collected from the smartphone when user paid as the crowdsourcing fingerprint, we avoid the requirement for indoor map and get rid of both devices cost and manual signal collecting process. Moreover, a shop-level hierarchical indoor localization framework is proposed, and high robustness features based on Wi-Fi sequences variation pattern in the same shop analysis are designed to avoid the received signal strength fluctuations. Besides, we also pay more attention to mine the popularity properties of shops and explore GPS features to improve localization accuracy in the Wi-Fi absence situation effectively. Massive experiments indicate that SP-Loc achieves more than 93% localization accuracy.
SP-Loc: A crowdsourcing fingerprint based shop-level indoor localization algorithm integrating shop popularity without the indoor map
