Positioning in Large Indoor Spaces using Smartphone Camera based on Static Objects

摘要

Large indoor spaces with wide field of vision and stable light (such as museums, malls and airports) provide a suitable scene for visual positioning. Static objects interior of these sites can be served as positioning references. Besides, increasingly powerful smartphones provide more strong computing support for visual methods. Therefore, this paper designed a visual positioning method integration with computer vision and deep learning algorithms. By using smartphone cameras, it detects static objects in large indoor spaces and calculate smartphones' position. Experiment in an art museum with complicated visual environment suggests that this method is able to achieve positioning accuracy within 1 meter.