Visual indoor localisation using a building information model
PhD Completion Seminar by Debaditya Acharya
With the emergence of the global navigation satellite system (GNSS), the performance of outdoor localisation has become excellent over the years. However, a single technology or solution that can satisfy the needs of localisation in indoor spaces is absent to date. The ubiquity of smart-phones and wearable computers with integrated cameras has resulted in a renewed interest in infrastructure-independent visual localisation approaches for the indoor environments. However, the existing visual approaches provide challenges that restrict the wide applicability of such approaches. This research proposes approaches to address the challenges by using a building information model (BIM). The motivation of using BIM for this research comes from the fact that BIMs of modern buildings are readily available, as they are jointly maintained by the constructors and facility managers. The results of the qualitative and quantitative experimentation of the proposed approaches with photo-realistic synthetic and real datasets indicate the proposed research address the major limitations of the existing approaches. In addition, the proposed research points out directions towards a single technology for infrastructure-independent indoor localisation.
Debaditya Acharya, PhD candidate