Abstract
A variety of indoor applications require both accurate location and orientation, such as indoor navigation and augmented reality. This paper presents 3DLoc, with which you can find your location and orientation by pointing your smartphone camera at 3D features e.g., doors and entrances. Different from the previous image-based localization of matching features via SIFT or SURF, 3DLoc takes advantage of rules for 3D features, including the ratio between height and width, the orientation and the distribution on the 2D floor map. The features around users are regarded as a unique 3D signature for the location. Based on prior researches on vanishing points and indoor geometric reasoning, we propose an algorithm to extract the signature from captured images and robustly decode the signature to accurate location and orientation. In terms of efficiency and user-friendliness, a series of optimizations are adopted through fusion of smartphone sensors and vision. We conduct experiments on different floors of a typical office building via the prototype built on Huawei P7 and iPhone 5S. Ninety percent of errors for location and orientation are within 25cm and two de4rees, respectively. With a 2D floor map provided, KB (-KiloByte-) level storage is required for the additional 3D information.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
