Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy

Abstract In goal-type ball games, such as handball, basketball, hockey or soccer, teammates and opponents share the same field. They switch dynamically their behaviors and relationships based on other players’ behaviors or intentions. Interactions between players are highly complicated and hard to comprehend, but recent technological developments have enabled us to acquire positions or velocities of their behaviors. We focus on handball as an example of goal-type ball games and analyze causality between teammates’ behaviors from tracking data with Hidden Semi-Markov Model (HSMM) and delayed Transfer Entropy (dTE). Although ‘off-the-ball’ behaviors are a crucial component of cooperation, most research tends to focus on ‘on-the-ball’ behaviors, and relations of behaviors are only known as tacit knowledge of coaches or players. In contrast, our approach quantitatively reveals player's relationships of ‘off-the-ball’ behaviors. The extracted causal models are compared to the corresponding video scenes, and we claim that our approach extracts causal relationships between teammates’ behaviors or intentions and clarifies roles of the players in both attacking and defending phase.

[1]  Qiang Ji,et al.  Complex Activity Recognition Using Granger Constrained DBN (GCDBN) in Sports and Surveillance Video , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Frank D. Wood,et al.  Inference in Hidden Markov Models with Explicit State Duration Distributions , 2012, IEEE Signal Processing Letters.

[3]  Minoru Asada,et al.  Learning of Joint Attention from Detecting Causality Based on Transfer Entropy , 2008, J. Robotics Mechatronics.

[4]  Patrick Bouthemy,et al.  Trajectory-based handball video understanding , 2009, CIVR '09.

[5]  Chris Button,et al.  A Review of Vision-Based Motion Analysis in Sport , 2008, Sports medicine.

[6]  Schreiber,et al.  Measuring information transfer , 2000, Physical review letters.

[7]  Jürgen Perl,et al.  Tactical pattern recognition in soccer games by means of special self-organizing maps. , 2012, Human movement science.

[8]  Tadahiro Taniguchi,et al.  Contextual scene segmentation of driving behavior based on double articulation analyzer , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  John M. Beggs,et al.  Extending Transfer Entropy Improves Identification of Effective Connectivity in a Spiking Cortical Network Model , 2011, PloS one.

[10]  Y. Loewenstein,et al.  Reinforcement learning in professional basketball players , 2011, Nature communications.

[11]  Anthony Bedford,et al.  Evaluating Australian football league player contributions using interactive network simulation. , 2013, Journal of sports science & medicine.

[12]  Bob Fisher,et al.  Recognition of coordinated multi agent activities, the individual vs the group , 2006 .

[13]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[14]  A. Murat Tekalp,et al.  Automatic Soccer Video Analysis and Summarization , 2003, IS&T/SPIE Electronic Imaging.

[15]  Matthew J. Johnson,et al.  Bayesian nonparametric hidden semi-Markov models , 2012, J. Mach. Learn. Res..

[16]  Ki-Joune Li,et al.  Spatial and spatiotemporal analysis of soccer , 2011, GIS.

[17]  Shih-Fu Chang,et al.  Structure analysis of soccer video with hidden Markov models , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Keiko Yokoyama,et al.  Common and Unique Network Dynamics in Football Games , 2011, PloS one.