Automatic initialization for 3D soccer player tracking

As a special application of computer vision, automatic sports video analysis has been studied by some researchers. This sports video analysis via computer vision is a moderately challenging problem: it is more difficult than analyzing a video of a few laboratory members acting as in a simple scenario and is easier than analyzing a video of crowded people at a subway station. So the success of an analysis heavily depends on how much one can exploit the prior information on the sport and setting. The most challenging and important part would be the tracking of players (and ball). With a multi-camera system, 3D tracking is feasible which is much more meaningful than 2D tracking for the analysis. As an initial step of 3D player tracking from multi-view soccer videos, this paper deals with automatic initialization of player positions. Initial 3D positions can be estimated by exploiting some conditions of a soccer match. To make it robust, prior knowledge on the features of players is learnt by support vector machines (SVM). Experimental results show that the proposed system is efficient for general soccer sequences.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Xinguo Yu,et al.  A 3D reconstruction and enrichment system for broadcast soccer video , 2004, MULTIMEDIA '04.

[3]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[4]  A. Singhal,et al.  Tracking soccer players using the graph representation , 2008 .

[5]  Aaron F. Bobick,et al.  Closed-world tracking , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Mubarak Shah,et al.  Tracking Multiple Occluding People by Localizing on Multiple Scene Planes , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  L. Davis,et al.  M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene , 2003, International Journal of Computer Vision.

[8]  Larry S. Davis,et al.  M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo , 2002, ECCV.

[9]  Stan Z. Li,et al.  Real-time multi-view face detection , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[10]  Mubarak Shah,et al.  Consistent Labeling of Tracked Objects in Multiple Cameras with Overlapping Fields of View , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  H.-W. Ok.  Multiple Soccer Players Tracking by Condensation with Occlusion Alarm Probability , 2002 .

[12]  Ming Xu,et al.  Tracking football players with multiple cameras , 2004 .

[13]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[14]  James W. Davis,et al.  Kernel-Based 3D Tracking , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  Thomas S. Huang,et al.  A Joint System for Person Tracking and Face Detection , 2005, ICCV-HCI.

[17]  Hideo Saito,et al.  Parallel tracking of all soccer players by integrating detected positions in multiple view images , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..