A complex system for football player detection in broadcasted video

In this paper a novel segmentation system for football player detection in broadcasted video is presented. The system is based on the combination of Histogram of Oriented Gradients (HOG) descriptors and linear Support Vector Machine (SVM) classification. Although recently HOG-based methods were successfully used for pedestrian detection, experimental results presented in this paper show that combination of HOG and SVM seems to be a promising technique for locating and segmenting players in broadcasted video. Proposed detection system is a complex solution incorporating a dominant color based segmentation technique of a football playfield, a 3D playfield modeling algorithm based on Hough transform and a dedicated algorithm for player tracking. Evaluation of the system is carried out using SD (720×576) and HD (1280×720) resolution test material. Additionally, performance of the proposed system is tested with different lighting conditions (including non-uniform pith lightning and multiple player shadows) and various camera positions.

[1]  Hong Shao,et al.  Image Retrieval Based on MPEG-7 Dominant Color Descriptor , 2008, 2008 The 9th International Conference for Young Computer Scientists.

[2]  D. Goldgof,et al.  Detection of Thin Lines using Low-Quality Video from Low-Altitude Aircraft in Urban Settings , 2009, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Xueming Qian,et al.  Ball and Field Line Detection for Placed Kick Refinement , 2009, 2009 WRI Global Congress on Intelligent Systems.

[4]  Guoquan Jiang,et al.  A straight line detection based on randomized method , 2008, 2008 9th International Conference on Signal Processing.

[5]  David Zhang,et al.  Dark line detection with line width extraction , 2008, 2008 15th IEEE International Conference on Image Processing.

[6]  Jae Wook Jeon,et al.  An improvement of the Standard Hough Transform to detect line segments , 2008, 2008 IEEE International Conference on Industrial Technology.

[7]  Yu Huang,et al.  Players and Ball Detection in Soccer Videos Based on Color Segmentation and Shape Analysis , 2007, MCAM.

[8]  Fan Zhang,et al.  Probabilistic Hough transform for line detection utilizing surround suppression , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[9]  J.R. Nunez,et al.  Soccer video segmentation: Referee and player detection , 2008, 2008 15th International Conference on Systems, Signals and Image Processing.

[10]  Wen Gao,et al.  Automatic Multi-Player Detection and Tracking in Broadcast Sports Video using Support Vector Machine and Particle Filter , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[11]  MacaireLudovic,et al.  Color image segmentation by pixel classification in an adapted hybrid color space , 2003 .

[12]  Joemon M. Jose,et al.  Football Video Segmentation Based on Video Production Strategy , 2005, ECIR.

[13]  Nicolas Vandenbroucke,et al.  Color image segmentation by pixel classification in an adapted hybrid color space. Application to soccer image analysis , 2003, Comput. Vis. Image Underst..

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Chu-Song Chen,et al.  Fast Human Detection Using a Novel Boosted Cascading Structure With Meta Stages , 2008, IEEE Transactions on Image Processing.

[16]  Mohan S. Kankanhalli,et al.  Semantic labeling of soccer video , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[17]  Xinguo Yu,et al.  A gridding Hough transform for detecting the straight lines in sports video , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[18]  S. Paisitkriangkrai,et al.  Performance evaluation of local features in human classification and detection , 2008 .