Indoor localisation based on fusing WLAN and image data

Abstract

In this paper we address the automatic identification of indoor locations using a combination of WLAN and image sensing. We demonstrate the effectiveness of combining the strengths of these two complementary modalities for very chal- lenging data. We describe a fusion approach that allows localising to a specific office within a building to a high degree of precision or to a location within that office with reasonable precision. As it can be orientated towards the needs and capabilities of a user based on context the method becomes useful for ambient assisted living applications.