Scout: a game speed analysis and tracking system

Authors:
Ping-Sing Tsai;Todd Meijome;Phillip G. Austin
Affiliations:
The University of Texas–Pan American, Department of Computer Science, 78541, Edinburg, TX, USA;Object Prediction Technologies LLC, 85260, Scottsdale, AZ, USA;15545 East Mustang Drive, 85268, Fountain Hills, AZ, USA
Venue:
Machine Vision and Applications
Year:
2007

Citing 6
Cited 1

Pfinder: Real-Time Tracking of the Human Body

IEEE Transactions on Pattern Analysis and Machine Intelligence
W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer and Robot Vision

Computer and Robot Vision
Motion segmentation and pose recognition with motion history gradients

Machine Vision and Applications - Special issue: IEEE WACV
Maintaining variance and k-medians over data stream windows

Proceedings of the twenty-second ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
A Fast Background Scene Modeling and Maintenance for Outdoor Surveillance

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4

A review of vision-based systems for soccer video analysis

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A sporting event game speed analysis and tracking system—Scout is presented in this paper. Common computer vision and pattern recognition methods, such as background subtraction, connected components labelling, morphology filtering, etc., are used for segmenting and tracking moving objects. A new vanishing-points-based method is proposed for the mapping between the screen (image) and physical (field) coordinate systems. The system is designed to evaluate football players’ performance and skills from the recorded training camps’ footages. The tracking results and performance analysis of real football training camps’ video clips are presented.