%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.04.17.21
%2 sid.inpe.br/sibgrapi/2017/09.04.17.21.49
%T An experimental setup and protocol for offline performance assessment of eye/gaze tracking strategies
%D 2017
%A Cruz, Mateus da Mota Cardoso da,
%A Zampolo, Ronaldo de Freitas,
%A Silva, Matthieu Perreira da,
%A Callet, Patrick Le,
%@affiliation Federal University of Pará
%@affiliation Federal University of Pará
%@affiliation University of Nantes
%@affiliation University of Nantes
%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 Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Experimental setup, experimental protocol, visual attention models, low-cost eye/gaze tracking.
%X Several applications (crowdsourcing, human-computer interface, and web design, just to name a few) can largely benefit from reliable low-cost eye/gaze tracking solutions with either reduced or no-calibration procedure. Although very accurate eye/gaze trackers are currently affordable to common users, special hardware is still needed and calibration procedure remains apparent. This paper presents an experimental setup and protocol aimed at providing ground truth and supporting data to allow offline performance evaluation of different eye/gaze tracking schemes. This work is part of an ongoing research on the use of visual attention models in conjunction with eye/gaze tracking strategies for performance improvement as well as reduction of calibration phase in low-cost solutions. The proposed experimental setup hardware is composed of off-the-shelf equipment (eye/gaze tracker, conventional webcam, and a desktop computer). In turn, the control software is developed in PsychoPy/Python and made publicly available. Data acquisition components and conceived experimental protocol are discussed in details.
%@language en
%3 sigbrapi2017.pdf