"You're It!": Role Identification Using Pairwise Interactions in Tag Games

We aim at designing interactive playgrounds that automatically analyze the behavior of children while playing games, in order to adapt the gameplay and make the games more engaging. In this paper, we focus on recognizing roles in tag games, where children are taggers or runners. We start by tracking the location and motion of individual players, and subsequently recognize pairwise interactions: approach, chase and avoid. At each moment in time, we inspect the full set of pairwise interactions to determine the role of each player. Our approach is fully probabilistic, deals with any number of players and can easily be extended to include other interactions and roles. We evaluate our algorithm using simulations, which show promising results. We intend to extend our framework to recognize variants of the tag game, and to address actual play interactions.

[1]  Tao Xiang,et al.  Video Analytics for Business Intelligence , 2012, Studies in Computational Intelligence.

[2]  E. Hall,et al.  The Hidden Dimension , 1970 .

[3]  Silvio Savarese,et al.  Learning context for collective activity recognition , 2011, CVPR 2011.

[4]  Vittorio Murino,et al.  Social interactions by visual focus of attention in a three‐dimensional environment , 2013, Expert Syst. J. Knowl. Eng..

[5]  Panos Markopoulos,et al.  Increasing children's social competence through games, an exploratory study , 2009, IDC.

[6]  Bodo Rosenhahn,et al.  Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[7]  Qi Tian,et al.  Group Activity Recognition by Gaussian Processes Estimation , 2010, 2010 20th International Conference on Pattern Recognition.

[8]  Anton Nijholt,et al.  Design of an Interactive Playground Based on Traditional Children's Play , 2012, INTETAIN.

[9]  James M. Rehg,et al.  Quasi-periodic event analysis for social game retrieval , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Luc Van Gool,et al.  Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings , 2010, ECCV.

[11]  Ming-Ching Chang,et al.  Probabilistic group-level motion analysis and scenario recognition , 2011, 2011 International Conference on Computer Vision.

[12]  Robert T. Collins,et al.  Vision-Based Analysis of Small Groups in Pedestrian Crowds , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Bingbing Ni,et al.  Recognizing human group activities with localized causalities , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Yunde Jia,et al.  Learning Human Interaction by Interactive Phrases , 2012, ECCV.

[15]  Vittorio Murino,et al.  Analyzing Groups: A Social Signaling Perspective , 2012, Video Analytics for Business Intelligence.

[16]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[17]  Alessio Del Bue,et al.  Human behavior analysis in video surveillance: A Social Signal Processing perspective , 2013, Neurocomputing.

[18]  Vittorio Murino,et al.  Decentralized particle filter for joint individual-group tracking , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Ronald Poppe,et al.  A survey on vision-based human action recognition , 2010, Image Vis. Comput..

[20]  M. Argyle,et al.  EYE-CONTACT, DISTANCE AND AFFILIATION. , 1965, Sociometry.

[21]  Dariu Gavrila,et al.  Monocular Pedestrian Detection: Survey and Experiments , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Georg Groh,et al.  Detecting Social Situations from Interaction Geometry , 2010, 2010 IEEE Second International Conference on Social Computing.

[23]  Luis E. Ortiz,et al.  Who are you with and where are you going? , 2011, CVPR 2011.