• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Mathematical Problems in Engineering >Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections
【24h】

Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections

机译：基于自适应局部保留投影的视频镜头边界识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A novel video shot boundary recognition method is proposed, which includes two stages of video feature extraction and shot boundary recognition. Firstly, we use adaptive locality preserving projections (ALPP) to extract video feature. Unlike locality preserving projections, we define the discriminating similarity with mode prior probabilities and adaptive neighborhood selection strategy which make ALPP more suitable to preserve the local structure and label information of the original data. Secondly, we use an optimized multiple kernel support vector machine to classify video frames into boundary and nonboundary frames, in which the weights of different types of kernels are optimized with an ant colony optimization method. Experimental results show the effectiveness of our method.
机译：提出了一种新颖的视频镜头边界识别方法，该方法包括视频特征提取和镜头边界识别两个阶段。首先，我们使用自适应局部保留投影（ALPP）提取视频特征。与保留位置的预测不同，我们使用模式先验概率和自适应邻域选择策略定义区分相似性，这使ALPP更适合保留原始数据的局部结构和标签信息。其次，我们使用优化的多核支持向量机将视频帧分为边界帧和非边界帧，其中使用蚁群优化方法对不同类型内核的权重进行优化。实验结果表明了该方法的有效性。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2013年第14期|353261.1-353261.9|共9页
  • 作者

    Yongliang Xiao; Limin Xia; Shaoping Zhu; Dazu Huang; Jianquan Xie;

  • 作者单位

    School of Information Science and Engineering, Central South University, Changsha 410083, China,Department of Information Management, Hunan University of Finance and Economics, Changsha 410205, China;

    School of Information Science and Engineering, Central South University, Changsha 410083, China;

    Department of Information Management, Hunan University of Finance and Economics, Changsha 410205, China;

    Department of Information Management, Hunan University of Finance and Economics, Changsha 410205, China;

    Department of Information Management, Hunan University of Finance and Economics, Changsha 410205, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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