Indoor Navigation with iPhone/iPad: Floor Plan Based Monocular Vision Navigation

Bei Huang and Yang Gao

Abstract:	Pedestrian device like smart phone and tablet nowadays become more and more intelligent and the interest to apply those smart devices for indoor navigation is growing. Most of such smart devices are integrated with a GPS chip, an inertial sensor(s), a magnetic compass along with other gadgets such as camera and Wi-Fi. The large varieties of sensors enable hybrid location solution to not only improve availability of indoor positioning but also the accuracy and smoothness. But in deep indoor scenario, the positioning accuracy is seldom satisfactory and suffers from accumulative error due to dead-reckoning sensors. In this paper, a floor plan based vision navigation method is designed for pedestrian handset indoor application. The floor plan for buildings is an easily accessible online resource. Besides of the fact that floor plan is a useful indoor map containing detailed paths and rooms, vision measurement will be matched with floor plan to derive accurate and drift-free position. The Random Sample Consensus (RANSAC) algorithm is adopted for robust matching between the floor plan and the camera image. An iPhone demo App is developed and tested on real device with indoor tests conducted in the University of Calgary. The derived iPhone positions are compared with the landmark reference and the results indicate meter-level horizontal accuracy. With such accuracy, the demo App is also featured with augmented navigation reality which has shown great feasibility and innovation for pedestrian indoor navigation.
Published in:	Proceedings of the 25th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2012) September 17 - 21, 2012 Nashville Convention Center, Nashville, Tennessee Nashville, TN
Pages:	2440 - 2449
Cite this article:	Huang, Bei, Gao, Yang, "Indoor Navigation with iPhone/iPad: Floor Plan Based Monocular Vision Navigation," Proceedings of the 25th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2012), Nashville, TN, September 2012, pp. 2440-2449.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In