%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/08.21.19.58
%2 sid.inpe.br/sibgrapi/2017/08.21.19.58.27
%@doi 10.1109/SIBGRAPI.2017.40
%T Color-Based and Recursive Fiducial Marker for Augmented Reality
%D 2017
%A Tybusch, Douglas,
%A Moraes, Gilseone Rosa de,
%A Santos, Osmar M. dos,
%A Legg, Andrei Piccinini,
%A Ceolin, Simone Regina,
%@affiliation Universidade Federal de Santa Maria
%@affiliation Universidade Federal de Santa Maria
%@affiliation Universidade Federal de Santa Maria
%@affiliation Universidade Federal de Santa Maria
%@affiliation Universidade Federal de Santa Maria
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ, Brazil
%8 17-20 Oct. 2017
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K fiducial marker, augmented reality, image processing, color marker.
%X The popularity of applications using Augmented Reality, especially due to the dissemination of smartphones with high processing power, introduces the need for Fiducial Markers that can be detected quickly, with good accuracy and can deal with partial occlusion. Fiducial Markers can have different shapes, sizes, structure and colors, and are inserted into a scene to facilitate the detection and consequent projection of virtual objects. In particular, this paper proposes a new Color-based and Recursive Fiducial Marker (CRFM), which is constructed by square-based geometric forms and uses different colors to produce a recursive structure that was designed to still work under partial occlusion. We describe the CRFM design and how its detection mechanism works. Our evaluation results show that CRFM achieves a good level of accuracy. Moreover, we show that the detection of the CRFM can be as fast as a board of ArUco, where only black and white colors are used.
%@language en
%3 PID4960211.pdf