A Fully Automatic Player Detection Method Based on One-Class SVM
- 1 January 2013
- journal article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E96.D (2) , 387-391
Abstract
Player detection is an important part in sports video analysis. Over the past few years, several learning based detection methods using various supervised two-class techniques have been presented. Although satisfactory results can be obtained, a lot of manual labor is needed to construct the training set. To overcome this drawback, this letter proposes a player detection method based on one-class SVM (OCSVM) using automatically generated training data. The proposed method is evaluated using several video clips captured fromWorld Cup 2010, and experimental results show that our approach achieves a high detection rate while keeping the training set construction's cost low. Copyright © 2013 The Institute of Electronics, Information and Communication Engineers.Keywords
This publication has 8 references indexed in Scilit:
- Playfield Detection Using Color Ratio and Local Entropy2011
- Automatic player labeling, tracking and field registration and trajectory mapping in broadcast soccer videoACM Transactions on Intelligent Systems and Technology, 2011
- Football Player Detection in Video Broadcast2010
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- An object detection method for describing soccer games from video2003
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Network constraints and multi-objective optimization for one-class classificationNeural Networks, 1996
- FCM: The fuzzy c-means clustering algorithmComputers & Geosciences, 1984