We present the SPEED method to predict endpoints, based on analysis of the kinetic characteristics of the pointing gesture. Our model splits the gesture into an acceleration phase and a deceleration phase to precisely detect target. The rst phase allows us to identify a velocity peak that marks the beginning of the second phase. This phase is approached with a quadratic model to predict gesture endpoint. A pilot study shows that SPEED predicts a target more precisely than other existing methods, for 1D tasks without distractors.
J. Wonner , J. Grosjean , A. Capobianco , D. Bechmann
IHM 2011 , page 113--116 - 2011
National conference with proceedings
SPEED : Prédiction de cibles, IHM 2011, Nice - Sophia Antipolis, France, pages 113--116, ACM, octobre 2011
Research team : IGG
@Inproceedings{5-WGCB11, author = {Wonner, J. and Grosjean, J. and Capobianco, A. and Bechmann, D.}, title = {SPEED : Pr\'ediction de cibles}, booktitle = {IHM 2011}, pages = {113--116}, month = {Oct}, year = {2011}, publisher = {ACM}, organization = {ACM}, x-international-audience = {No}, x-language = {FR}, url = {http://publis.icube.unistra.fr/5-WGCB11} }