Playfield registration in broadcast soccer video

In this paper, we present a method to conduct playfield registration for ball and player trajectory mapping in soccer videos. The task is to find the geometric correspondence between a screen image plane and the standard playfield model, and then map the ball and players from the image plane to the field model. We firstly learn the video dominant colour, and use it to extract the field region. Then apply Hough transform to detect lines and extract their intersection points. If the number of intersection points is big enough (>=4), we use direct way to estimate the homography mapping matrix. Otherwise, we apply indirect way that reconstructs the mapping matrix by taking motion between adjacent frames as transition factor. We tested the method on thousands of frames in FIFA World Cup 2006 videos, and demonstrated the method is practicable and robust in cases player occlusion and moderate camera motion.

[1]  Hanspeter Bieri,et al.  A Video‐Based 3D‐Reconstruction of Soccer Games , 2000, Comput. Graph. Forum.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Jia Liu,et al.  Automatic Player Detection, Labeling and Tracking in Broadcast Soccer Video , 2007, BMVC.

[5]  Xinguo Yu,et al.  3D reconstruction and enrichment of broadcast soccer video , 2004, MULTIMEDIA '04.

[6]  Stefan Carlsson,et al.  Multi-Target Tracking - Linking Identities using Bayesian Network Inference , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Jake K. Aggarwal,et al.  Tracking soccer players using broadcast TV images , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[8]  Wolfgang Effelsberg,et al.  Robust camera calibration for sport videos using court models , 2003, IS&T/SPIE Electronic Imaging.

[9]  Stefan Carlsson,et al.  Tracking and Labelling of Interacting Multiple Targets , 2006, ECCV.

[10]  Tao Wang,et al.  Soccer Highlight Detection using Two-Dependence Bayesian Network , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[11]  James J. Little,et al.  A Boosted Particle Filter: Multitarget Detection and Tracking , 2004, ECCV.

[12]  Loong Fah Cheong,et al.  Automatic camera calibration of broadcast tennis video with applications to 3D virtual content insertion and ball detection and tracking , 2009, Comput. Vis. Image Underst..

[13]  Wen Gao,et al.  A new method to calculate the camera focusing area and player position on playfield in soccer video , 2005, Visual Communications and Image Processing.

[14]  Graham A. Thomas,et al.  Real-time camera tracking using sports pitch markings , 2007, Journal of Real-Time Image Processing.

[15]  Wenlong Li,et al.  Optimization and Parallelization on a Multimeida Application , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[16]  Lifeng Sun,et al.  A Three-Level Scheme for Real-Time Ball Tracking , 2007, MCAM.

[17]  Dong Xu,et al.  Visual Event Recognition in News Video using Kernel Methods with Multi-Level Temporal Alignment , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Harry Shum,et al.  Automatic extraction of semantic colors in sports video , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[19]  Peter H. N. de With,et al.  Fast camera calibration for the analysis of sport sequences , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[20]  P.V.C. Hough,et al.  Machine Analysis of Bubble Chamber Pictures , 1959 .

[21]  Sang Wook Lee,et al.  Probabilistic Tracking of Soccer Players and Ball , 2004 .

[22]  Miki Haseyama,et al.  A soccer field tracking method with wire frame model from TV images , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[23]  Svetha Venkatesh,et al.  Object labelling from human action recognition , 2003, Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003)..

[24]  Samy Bengio,et al.  Semi-supervised adapted HMMs for unusual event detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[25]  Wen Gao,et al.  Mining Information of Attack-Defense Status from Soccer Video Based on Scene Analysis , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[26]  Yongduek Seo,et al.  Physics-based 3D position analysis of a soccer ball from monocular image sequences , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).