Key points are not available for this paper at this time.
Nowadays, smartphones have become indispensable to everyone, with more and more built-in location-based applications to enrich our daily life. In the last decade, fingerprinting based on RSS has become a research focus in indoor localization, due to its minimum hardware requirement and satisfiable positioning accuracy. However, its time-consuming and labor-intensive site survey is a big hurdle for practical deployments. Fingerprint crowdsourcing has recently been promoted to relieve the burden of site survey by allowing common users to contribute to fingerprint collection in a participatory sensing manner. For its promising commitment, new challenges arise to practice fingerprint crowdsourcing. This article first identifies two main challenging issues, fingerprint annotation and device diversity, and then reviews the state of the art of fingerprint crowdsourcing-based indoor localization systems, comparing their approaches to cope with the two challenges. We then propose a new indoor subarea localization scheme via fingerprint crowdsourcing, clustering, and matching, which first constructs subarea fingerprints from crowdsourced RSS measurements and relates them to indoor layouts. We also propose a new online localization algorithm to deal with the device diversity issue. Our experiment results show that in a typical indoor scenario, the proposed scheme can achieve a 95 percent hit rate to correctly locate a smartphone in its subarea.
Wang et al. (Wed,) studied this question.