A New Computational Approach to Identify Human Social intention in Action

Mohamed Daoudi (1) , Yann Coello (2) , Paul Audain Desrosiers (2) , Laurent Laurent Ott Ott (2)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
2 SCALab - Laboratoire Sciences Cognitives et Sciences Affectives - UMR 9193

In this paper, we propose to analyze the trajec-tories of the human arm to predict social intention (personal or social intention). The trajectories of different 3D markers acquired by Mocap system, are defined in shape spaces of open curves. The results obtained in the experiments on a new dataset show an average recognition of about 68% for the proposed method, which is comparable with the average score produced by human evaluation. The experimental results show also that the classification rate could be used to improve social communication between human and virtual agents. To the best of our knowledge, this is the first paper which uses computer vision techniques to analyze the effect of social intention on motor action for improving the social communication between human and avatar.

Domaines: Neurosciences; Informatique; Vision par ordinateur et reconnaissance de formes [cs.CV]

Mohamed Daoudi, Yann Coello, Paul Audain Desrosiers, Laurent Laurent Ott Ott. A New Computational Approach to Identify Human Social intention in Action. IEEE International Conference on AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2018), May 2018, Xi'an, China. ⟨10.1109/FG.2018.00082⟩. ⟨hal-01692111v2⟩