【24h】

A SYNTACTIC VIDEO SEGMENTATION ALGORITHM BASED ON FUZZY CLUSTERING NEURAL NETWORK

机译:基于模糊聚类神经网络的句法视频分割算法。

获取原文
获取原文并翻译 | 示例

摘要

Video segmentation is an important and challenging task in a video library system, since it is the prerequisite of video indexing and retrieval. In this paper, we address a syntactic video segmentation algorithm based on fuzzy clustering neural network (FCNN). By the FCNN, we realize the unsupervised video shot boundary detection so that reduce human intervention. For the novel algorithm, in the one hand, it need not pre-specify a proper for each video sequence, in the other hand, the fuzzy processing method also improves the segmentation precision of video data stream. The efficacy of the proposed algorithm is extensively tested on more than 3.5 hours of news programs.
机译:视频分割是视频库系统中一项重要且具有挑战性的任务,因为它是视频索引和检索的前提。本文提出了一种基于模糊聚类神经网络(FCNN)的句法视频分割算法。通过FCNN,我们实现了无监督视频镜头边界检测,从而减少了人工干预。对于新颖的算法,一方面不需要为每个视频序列预先指定合适的方法,另一方面,模糊处理方法也提高了视频数据流的分割精度。在超过3.5小时的新闻节目中,对该算法的有效性进行了广泛的测试。

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