Estimation of Ball Route under Overlapping with Players and Lines in Soccer Video Image Sequence

This paper deals with the analysis of broadcast soccer video. To recognize interesting events such as a goal, estimation of ball movements is necessary. It is, however, sometimes difficult to detect a ball by a simple color and shape-based method when it overlaps with players and lines. We therefore develop a method of estimating a ball route during such overlaps by considering spatio-temporal relationships between players, lines, and the ball. The method can deal with difficult cases such as the one where a ball disappears at a player and re-appears from another player. Experimental results show the effectiveness of the method

[1]  Yoshiaki Shirai,et al.  Tracking players and a ball in video image sequence and estimating camera parameters for 3D interpretation of soccer games , 2002, Object recognition supported by user interaction for service robots.

[2]  Osamu Yamaguchi,et al.  Facial Feature Point Extraction Method Based on Combination of Shape Extraction and Pattern Matching , 1998 .

[3]  Qi Tian,et al.  A ball tracking framework for broadcast soccer video , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[4]  Yongduek Seo,et al.  Probabilistic Tracking of the Soccer Ball , 2004, ECCV Workshop SMVP.

[5]  Nicola Ancona,et al.  Ball detection in static images with Support Vector Machines for classification , 2003, Image Vis. Comput..

[6]  Cataldo Guaragnella,et al.  A new algorithm for ball recognition using circle Hough transform and neural classifier , 2004, Pattern Recognit..

[7]  Yoshiaki Shirai,et al.  Tracking players and estimation of the 3D position of a ball in soccer games , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Ming Xu,et al.  A general framework for 3D soccer ball estimation and tracking , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..