首页> 外文期刊>Broadcast technology >A Video Search Technique Based on Image Analysis
【24h】

A Video Search Technique Based on Image Analysis

机译:基于图像分析的视频搜索技术

获取原文
获取原文并翻译 | 示例
       

摘要

Thanks to advances in video compression technologies, improved hardware performance, and the expanding Internet network, it is now easier than ever for people to access massive amounts of stored video content. In step with this trend, there is a growing demand for large-scale video assets such as broadcast archives to be made available to the public, increasing the need for a video retrieval technology that can efficiently find scenes that a user is looking for. The current search methods mostly rely on keyword searches of the text information attached to each scene of video content. However, there is also a need for a search technique that allows people to look for scenes that are difficult to describe in words, such as "I just want a scene that looks something like this." Addressing this need requires a retrieval technology that can search based on various characteristics beyond textual data. We are researching video
机译:得益于视频压缩技术的进步,改进的硬件性能以及不断扩展的Internet网络,人们现在比以往任何时候都更容易访问大量存储的视频内容。与这种趋势同步,对诸如广播档案之类的大规模视频资产提供给公众的需求不断增长,从而增加了对视频检索技术的需求,该技术可以有效地找到用户正在寻找的场景。当前的搜索方法主要依靠对视频内容的每个场景所附加的文本信息的关键字搜索。但是,还需要一种搜索​​技术,该技术可以使人们查找难以用文字描述的场景,例如“我只想要一个看起来像这样的场景”。为了满足这一需求,需要一种能够基于文本数据以外的各种特征进行搜索的检索技术。我们正在研究视频

著录项

  • 来源
    《Broadcast technology》 |2011年第45期|p.5|共1页
  • 作者

    Takahiro Mochizuki;

  • 作者单位

    Human & Information Science Research Division;

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

  • 入库时间 2022-08-18 01:51:41

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