Player position estimation by monocular camera for soccer video analysis
Player position estimation by monocular camera for soccer video analysis
复制标题
通过单目摄像头估计球员位置以进行足球视频分析
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Y. Aoki
中科院分区：
文献类型：
--
作者：
Hirokatsu Kataoka;K. Hashimoto;Y. Aoki
在足球内容方面，现在有很多服务。比如球员战术分析和高光场景制作。为了将这些内容付诸实践，有必要从足球录像中获取重要信息。本文提出了一种在单目摄像机拍摄的足球视频中对多名球员和球进行跟踪的方法。在从单一视角捕捉视频的情况下，可能会有很多玩家遮挡的情况。为了克服这一问题，我们提出了一种结合粒子滤波和分类器的多参与者鲁棒跟踪方法。为了对球进行跟踪，我们尝试应用标记和最近邻算法进行跟踪。此外，我们应用透视变换来提取球员在球场上的位置。实验结果表明了该方法的有效性。
In football contents, there are many services now. For example, player's tactics analysis and production of highlight scenes. In order to put into practice these contents, it is necessary to acquire important information from the football videos. In this paper, we propose a method to track multiple players and ball in a football video which is captured by monocular camera. In the case of capturing the video from a single view, there might be a lot of occluded situations of players. To overcome this problem, we propose a robust tracking method for multiple players by combining Particle Filter and Classifier. In order to track the ball, we try to track applying labeling and nearest neighbor algorithm. And more, we apply perspective transformation to extract player's position on the pitch. We show the experimental result and effectiveness of our proposed method.