TraIL: pinpoint trajectory for indoor localization

摘要: Indoor localization on smartphones is an enabler for a number of ubiquitous and mobile computing applications attracting worldwide attentions. Many location-based services rely WiFi fingerprinting approaches to achieve reasonable accuracy. However, there still room improvement due the prevalent-existing errors (e.g., 8-12 m). In this study, we devise implement high-accuracy indoor solution leveraging WiFi-based method pedestrian mobility provided by smartphones. Our basic idea that WiFi-only can generate rough but absolute positions, while user motion able bring accurate relative locations. Taking both sides into account simultaneously, design techniques refine raw positions in process laying precise local trajectory appropriately down coordinate using novel least median squares (LMS) fit algorithm. We develop prototype system, named TraIL, conduct comprehensive experiments building along different shaped routes. The evaluation results show TraIL 80% average error with respect localization.