Share Email Print

Proceedings Paper

Player detection using one-class SVM
Author(s): Xuefeng Bai; Tiejun Zhang; Chuanjun Wang; Qiong Li; Xiamu Niu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a novel player detection method via One-Class SVM(OCSVM) is proposed, inspired by both the player detection problem and the property of the OCSVM. In this detection method, candidate regions are got by local entropy and local range analysis firstly. Then a set of training samples is obtained by several predefined rules on shape and area. These samples are used to train two OCSVM models. One model uses color feature, and the other uses gradient feature. Finally, we locate the regions of player by fusing the detection result of the two models. Extensive experiments demonstrate effectiveness and efficiency of the proposed method.

Paper Details

Date Published: 8 June 2012
PDF: 5 pages
Proc. SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), 83342X (8 June 2012); doi: 10.1117/12.956462
Show Author Affiliations
Xuefeng Bai, Harbin Institute of Technology (China)
Tiejun Zhang, Harbin Institute of Technology (China)
Chuanjun Wang, Harbin Institute of Technology (China)
Qiong Li, Harbin Institute of Technology (China)
Xiamu Niu, Harbin Institute of Technology (China)

Published in SPIE Proceedings Vol. 8334:
Fourth International Conference on Digital Image Processing (ICDIP 2012)
Mohamed Othman; Sukumar Senthilkumar; Xie Yi, Editor(s)

© SPIE. Terms of Use
Back to Top