SHAPE-BASED INDIVIDUAL/GROUP DETECTION FOR SPORT VIDEOS CATEGORIZATION
Open Access
- 1 September 2008
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 22 (06) , 1187-1213
Abstract
We present a shape-based method for automatic people detection and counting without any assumption concerning camera motion. In order to evaluate the robustness of the proposed method, we apply it for classifying athletics videos into two classes: videos of individual and videos of team sports. The videos used are real and characterized by dynamic and unconstrained environment. Moreover, in the case of team sport, we propose a shape deformations based method for running/hurdling discrimination (activity recognition). Robust, adaptive and independent from color, illumination changes and the camera motion, the proposed features are combined in the Transferable Belief Model (TBM) framework providing a two-level (frames and shot) video categorization. Experimental results of 97% of accuracy for individual/team sport categorization using a dataset of 252 real videos of athletic meetings, acquired by moving cameras under varying view angles, indicate the stability and the good performance of the proposed scheme.Keywords
This publication has 22 references indexed in Scilit:
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- Real time multiple objects tracking and identification based on discrete wavelet transformPattern Recognition, 2006
- Tracking soccer players aiming their kinematical motion analysisComputer Vision and Image Understanding, 2006
- Shape-From-Silhouette Across Time Part II: Applications to Human Modeling and Markerless Motion TrackingInternational Journal of Computer Vision, 2005
- A Survey on Visual Surveillance of Object Motion and BehaviorsIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2004
- TRACKING MULTIPLE MOVING OBJECTS USING A LEVEL-SET METHODInternational Journal of Pattern Recognition and Artificial Intelligence, 2004
- A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenesImage and Vision Computing, 2003
- A Survey of Computer Vision-Based Human Motion CaptureComputer Vision and Image Understanding, 2001
- W/sup 4/: real-time surveillance of people and their activitiesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Representation and combination of uncertainty with belief functions and possibility measuresComputational Intelligence, 1988