华南理工大学学报(自然科学版) ›› 2007, Vol. 35 ›› Issue (9): 70-73.

• 计算机科学与技术 • 上一篇    下一篇

足球视频中近镜头的分类方法

赵丕锡1 李起点1 王秀坤1 王巍1 李国辉2   

  1. 1.大连理工大学 电子与信息工程学院,辽宁 大连 116023; 2. 国防科技大学 信息系统与管理学院,湖南 长沙 410073
  • 收稿日期:2006-12-05 出版日期:2007-09-25 发布日期:2007-09-25
  • 通信作者: 赵丕锡(1963-) ,男,在职博士生,大连民族学院教授,主要从事视频数据挖掘方面的研究. E-mail:pixizhao@ yahoo. com. cn
  • 作者简介:赵丕锡(1963-) ,男,在职博士生,大连民族学院教授,主要从事视频数据挖掘方面的研究.
  • 基金资助:

    国家自然科学基金资助项目(60273066)

Classification for Close Short Shot in Soccer Video

Zhao Pi-xi1  Li Qi-dianWang Xiu-kunwang WeiLi Guo-hui2   

  1. 1. School of Electric and Infonnation Engineering, Dalian Univ. ofTech. , Dalian 116023 , Liaoning , China;2. School of Information System and Management , National Univ. of Defense Tech. , Changsha 410073 , Hunan , China
  • Received:2006-12-05 Online:2007-09-25 Published:2007-09-25
  • Contact: 赵丕锡(1963-) ,男,在职博士生,大连民族学院教授,主要从事视频数据挖掘方面的研究. E-mail:pixizhao@ yahoo. com. cn
  • About author:赵丕锡(1963-) ,男,在职博士生,大连民族学院教授,主要从事视频数据挖掘方面的研究.
  • Supported by:

    国家自然科学基金资助项目(60273066)

摘要: 视频镜头类型能够弥补低级特征和高级语义之间的鸿沟,有利于精彩事件的检测.文中在现有镜头分类算法的基础上,提出了一种将足球视频中的近镜头进一步分成特写镜头和场外观众镜头的分类方法.该方法选取近镜头关键帧图像在RGB 颜色空间中颜色分量最少的羊色图像,并对其进行尺寸归一化,然后采用各向同性Sobel 算子和闭运算处理,获得二值边缘图像,最后通过计算二值边缘图像中黑色分块的个数实现两类镜头的分类判别.实验结果表明,文中方法是有效且实用的.

关键词: 视频信号, 信号处理, 分类, 特写镜头, 场外观众镜头Sobel 算子, 闭运算

Abstract:

Video shot type can bridge the gap between the low-level features and the high-level semantics and helps to detect highlights. In this paper , a new method for the classification of the close short shot in soccer video is proposed , which classifies the shot into close-up shot or out-of-field audiences' shot. In the proposed method , a component image with the minimal summation in all pixel values is selected from the key frame of a close short shot in RGB color space , and the size of the image is then normalized. After that , the isotropic Sobel operator and the closed operation are adopted to obtain the corresponding binarization edge image , and the classification decision is made by calculating the amount of black blocks in the binarization edge image. Experimental results finally reveal the validity and practicality of the proposed method.

Key words: video signal, signal processing, classification, close-up shot, out-of-field audiences' shot, Sobel operator, closed operation