Human centric sensing by android phone

• Main Author: Cheng, Edward Dehua.
• Other Authors: School of Computer Engineering
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/53218
• Institution: Nanyang Technological University

Existing indoor localization systems mostly require support from external infrastructures, especially WiFi hotspots or digitized floor maps, but we believe that an infrastructureless design is both desirable and possible. To this end, we propose our infrastructureless indoor localization system, a crowdsourced localization system exploring the indoor geomagnetism variance. Infrastructureless indoor localization system relies on crowd generated trajectories to both produce a virtual map and to fill the map with magnetic fingerprints. Without banking on extra sensors such as WiFi radio and accelerometer, infrastructureless indoor localization system leverages only magnetic fingerprints and gyroscope data to produce virtual maps and to perform location estimations. We deploy infrastructureless indoor localization system in various office buildings and shopping malls that cover tens of thousands of square meters. Our extensive experiments demonstrate that infrastructureless indoor localization system requires almost zero calibration, delivers satisfactory localization accuracy, and last but not least is easily accessible to the general public.