Milan Redzic

Dual-sensor Approach for Indoor User Localisation and Tracking Milan Redzic

Indoor localisation based on ubiquitous WLAN has exhibited the capability of being a cheap and relatively precise technology and has been verified by many successful examples. Its performance is subject to change due to multipath propagation and changes in the environment which cannot be easily eliminated. This book addresses the automatic localisation of indoor user and proposes solutions for both positioning and seamlessly tracking a user using WLAN technology in addition to image sensing. By fusing these modalities we obtain better performance than using them individually. A fusion function designed to merge both analysis results into one semantic interpretation of user location is presented. Also a tracking approach based on an adaptive function that converts times between locations into probabilities and employs a Viterbi-based solution is proposed. The effectiveness of the fusion and the tracking approaches is evaluated on a very challenging dataset throughout a university building. Results that are presented demonstrate high accuracy that can be achieved. The potential usefulness of this work is envisaged in a range of ambient assisted living applications.