A trajectory-based ball detection and tracking system with applications to shooting angle and velocity estimation in basketball videos

This paper presents a system to automatically analyse a basketball long-shot using trajectory-based ball tracking method from a basketball video sequence. The accuracy of a long-shot in a basketball game is mostly dependent on the ball throwing angle and the velocity at which the ball is to be thrown. The proposed system detects and tracks the ball in a basketball long-shot sequence by exploiting the trajectory information of the ball. The ball motion characteristics are used to determine the ball trajectory. The candidate trajectories are generated from a set of ball candidates in each frame. The trajectory-based ball tracking minimised the rate of error of ball tracking in the video which occurs due to occlusion and merging of the ball image with other objects in the frame, distortion of the ball image due to ball and camera motion and the presence of many moving objects in the foreground and background in the video. The ball locations verified by the tracking results are then used to estimate the ball throwing angle and the throwing velocity. The experiments show encouraging results for videos with dynamic background and different illumination conditions.

[1]  S. Meher,et al.  A trajectory-based ball detection and tracking system with applications to shot-type identification in volleyball videos , 2012, 2012 International Conference on Signal Processing and Communications (SPCOM).

[2]  Shahbe Mat Desa,et al.  Image subtraction for real time moving object extraction , 2004, Proceedings. International Conference on Computer Graphics, Imaging and Visualization, 2004. CGIV 2004..

[3]  Ning-Song Peng,et al.  Adaptive Kernel Based Tracking Using Mean-Shift , 2006, ICIAR.

[4]  Edward J. Delp.  Nonlinear Image Processing , 1990 .

[5]  Chien-Li Chou,et al.  Screen-strategy analysis in broadcast basketball video using player tracking , 2011, 2011 Visual Communications and Image Processing (VCIP).

[6]  Chao Huang,et al.  A new Method for Shot Identification in Basketball Video , 2011, J. Softw..

[7]  Ramsey Michael Faragher,et al.  Understanding the Basis of the Kalman Filter Via a Simple and Intuitive Derivation [Lecture Notes] , 2012, IEEE Signal Processing Magazine.

[8]  Sukadev Meher,et al.  A real-time trajectory-based ball detection-and-tracking framework for basketball video , 2013 .

[9]  Matej Kristan,et al.  A trajectory-based analysis of coordinated team activity in a basketball game , 2009, Comput. Vis. Image Underst..

[10]  Hua-Tsung Chen,et al.  Physics-based ball tracking and 3D trajectory reconstruction with applications to shooting location estimation in basketball video , 2009, J. Vis. Commun. Image Represent..