• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Computational Collective Intelligence >Automatic Detection of Play and Break Segments in Basketball Videos Based on the Analysis of the Slope of the Basketball Court Boundary
【24h】

Automatic Detection of Play and Break Segments in Basketball Videos Based on the Analysis of the Slope of the Basketball Court Boundary

机译：基于篮球场边界斜率的分析自动检测篮球比赛中的休息时间段

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Content-based video analysis is still a very intensively developed area of research in computer science. One of the most frequent purpose of content-based analysis is a video summarization. A basketball game coverage usually lasts for around two hours whereas the game itself is less than one hour. The basketball video can be modeled as a sequence of plays being defined as the segments when an important action occurs interleaved with breaks which can be ignored in video summarizing or highlight detection automatic processes. The paper proposes a method a basketball game segmentation into plays and breaks. The proposed method is based on the analysis of the slope of the basketball top court boundary. The tests performed in the AVI Indexer showed that the analysis of the slope of the playing field leads to the correct detection of more than 85% of play and break segments.
机译：基于内容的视频分析仍然是计算机科学领域非常密集的研究领域。基于内容的分析最常见的目的之一就是视频摘要。篮球比赛通常持续约两个小时，而比赛本身不到一个小时。可以将篮球视频建模为一系列比赛，这些比赛被定义为当重要动作发生并带有中断时所定义的片段，这些中断在视频摘要或高亮检测自动过程中可以忽略。提出了一种将篮球比赛划分为比赛和休息的方法。所提出的方法是基于对篮球最高场边界的斜率的分析。在AVI Indexer中进行的测试表明，对比赛场地坡度的分析可以正确检测到超过85％的比赛和休息区。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号