A Fully Automatic Player Detection Method Based on One-Class SVM
Summary :
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 from World Cup 2010, and experimental results show that our approach achieves a high detection rate while keeping the training set construction's cost low.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.2 pp.387-391
- Publication Date
- 2013/02/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.387
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Xuefeng BAI, Tiejun ZHANG, Chuanjun WANG, Ahmed A. ABD EL-LATIF, Xiamu NIU, "A Fully Automatic Player Detection Method Based on One-Class SVM" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 2, pp. 387-391, February 2013, doi: 10.1587/transinf.E96.D.387.
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 from World Cup 2010, and experimental results show that our approach achieves a high detection rate while keeping the training set construction's cost low.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.387/_p
Copy
@ARTICLE{e96-d_2_387,
author={Xuefeng BAI, Tiejun ZHANG, Chuanjun WANG, Ahmed A. ABD EL-LATIF, Xiamu NIU, },
journal={IEICE TRANSACTIONS on Information},
title={A Fully Automatic Player Detection Method Based on One-Class SVM},
year={2013},
volume={E96-D},
number={2},
pages={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 from World Cup 2010, and experimental results show that our approach achieves a high detection rate while keeping the training set construction's cost low.},
keywords={},
doi={10.1587/transinf.E96.D.387},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - A Fully Automatic Player Detection Method Based on One-Class SVM
T2 - IEICE TRANSACTIONS on Information
SP - 387
EP - 391
AU - Xuefeng BAI
AU - Tiejun ZHANG
AU - Chuanjun WANG
AU - Ahmed A. ABD EL-LATIF
AU - Xiamu NIU
PY - 2013
DO - 10.1587/transinf.E96.D.387
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2013
AB - 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 from World Cup 2010, and experimental results show that our approach achieves a high detection rate while keeping the training set construction's cost low.
ER -
English
