Players Highlighting and Team Classification in Soccer Video
A framework of player segmentation, tracking, highlighting and team classification in soccer game video is proposed. Main contributions consist of:
1) playfield modeling combining the Gaussian model with the dominant color extraction to segment the players/referees;
2) mean shift-based tracking with soft constraints from the foreground map to alleviate the shortcomings in handling the fast moving players;
3) discriminant similarity metric de-weighted by the surrounding background distribution applied for scale adaptation;
4) conservative update of the target model by aligning with its initial;
5) bi-histogram matching employed for team classification.
An inivited talk is presented at WOCC'09.
Some demos are shown below.
Figure 1 Object Highlighting
Figure 2 Team Classification