IndoorGML Modeling for WiFi-Based Indoor Positioning and Navigation

Abstract

With the advancement in indoor localization and navigation, indoor spaces are represented using distinct forms of spatial information. Communication and interoperability among different systems comprising different technologies demand a common standardized representation. From this demand, OGC published IndoorGML as a standard spatial data model. However, sensor-based indoor localization research hardly utilizes such spatial data model for better interoperability. The main aim of this work is to bridge this gap and propose a framework to (i) extract IndoorGML representation of the benchmark dataset of indoor localization; (ii) coarse grained localization based on sensory data with IndoorGML representation. We performed a case study on a WiFi fingerprint-based benchmark dataset for indoor localization based on our university campus. The result of the case study validates the robustness of the proposed framework.