In Proc. of 2018 Conference on Computer Vision, Graphics and Image Processing, Tainan, Taiwan, Aug. 2018
A REAL-TIME MOBILE AUGMENTED-REALITY SYSTEM FOR STREET-AREA EXPLORATION BY COMPUTER VISION TECHNIQUES USING SMART
GLASSES
1Ting-Wen Ko (柯婷文), 2Yu-Shiuan Tsai (蔡宇軒), and 1Wen-Hsiang Tsai (蔡文祥)
1Department of Computer Science,
National Chiao Tung University, Hsinchu, Taiwan
2Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, Taiwan E-mails: [email protected], [email protected]
Abstract
A new real-time augmented reality (AR) tour guidance system using smart glasses for outdoor street-area exploration is proposed, which is based on image matching using speeded up robust features (SURFs). Novel methods or techniques have been proposed for the system to perform the following functions: (1) learning a street-area environment before a tour guidance is started; (2) computing the accurate positions and orientations of a touring user; (3) updating the latest user position and orientation in realtime; (4)
planning a shortest path to guide the user by updating dynamically an AR guidance arrow shown on the display of a pair of smart glasses worn by the user; (5) displaying
information about along-path buildings on the screen of the smart glasses in an AR manner. Good experimental results show the feasibility of the proposed methods and system for practical realtime applications.
Keywords: tour guidance system, augmented reality (AR), speeded up robust features (SURFs), smart glasses, image matching.
