Welcome to Yu Huang's homepage!

Home
Resume
Research
Retargeting
VideoAnnotation
TeamClassification
StereoRectification
DisparityEstimation
ViewInterpolation
DetectTrack
ObjectDetection
ClutterModeling
MosaicGeneration
AdaptiveKernelParticle
Factorization
BodyTracking
BodyMotionLearning
StereoTracking
Publications
Rori
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
 

Demo Video1:      Object Highlighting (4MB).
 
Demo Video2: Team Classification (2.4MB).