%0 Conference Proceedings
%T Comparing pose recognition algorithms and introducing a new approach
%D 2017
%8 Oct. 17-20, 2017
%A Carvalho, Gabriel Peixoto de,
%A Ferreira, Fernando Teubl,
%A Brandão, André Luiz,
%@affiliation Universidade Federal do ABC
%@affiliation Universidade Federal do ABC
%@affiliation Universidade Federal do ABC
%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
%S Proceedings
%I Sociedade Brasileira de Computação
%J Porto Alegre
%K hand pose recognition, multi-layer perceptron, support vector machines, SURF, SIFT, HOG, Camshift, gesture tracking.
%X Gesture-based interaction with 3D objects is commonly done using color and depth (RGB-D) information. This kind of scheme requires specialized software and hardware (camera and depth sensor) which increases both financial and computational cost. Most of the public does not have access to such kind of technology due to these increased costs. Our ongoing study will be an approach for interaction with 3D objects with color (RGB) information and hand poses recognition. The interaction target is those made by one person with a single webcam. In this study, we intend to evaluate the use of commonly available algorithms to implement a pose acquisition scheme and present a comparative study of classification algorithms to achieve a low-cost and real-time interaction. Preliminary results demonstrate satisfactory performance with the hand pose acquisition scheme and classification algorithms, pointing to a real-time interaction capability.
%@language en
%3 comparingposerecognitionalgorithms-gabrielpeixoto-al_camera_ready.pdf