In this paper we discuss the design of an intelligent game systemcapable of selecting the players who exhibits the most outstandingbehavior from groups of people playing on a network. Playerscan be all in the same place (maximum 3) or in several locations ifconnected to the web. In that way, the total amount of players canbe very large. Tests were made with 3 players in a single locationand with 2 different locations of 2 players each. The system usesboth static and dynamic features extracted from the upper part ofthe players’ bodies such as symmetry, contraction index, motionindex or height. Those features are extracted using the RGB-DKinect sensor and their relative contrast and time evolution enablean adaptive selection of the most salient or different behavior withoutany complex rules. First users’ feedback and eye tracking testsare shown and applications to social interactions are presented.
|Title of host publication||ACCV 2012|
|Publication status||Published - 1 Jan 2012|
|Event||ACCV 2012 - 11th Asian Conference on Computer Vision - |
Duration: 1 Jan 2012 → …
|Conference||ACCV 2012 - 11th Asian Conference on Computer Vision|
|Period||1/01/12 → …|