摘要
提出并实现了一种基于HSI颜色空间的视频实时分级快速检索系统.首先采用亮度I累积直方图对视频序列进行粗检索和筛选,再利用色调H和饱和度S的分块二次空间划分直方图进行精检索,实现整个检索过程.实验表明,本系统速度快,误检、漏检率低,可应用在视频切换、视频资料检索、视频监控及视频点播等方面.
A novel real-time classification video retrieval system based on HSI model is presented. In this (system), Luminance cumulative histogram is used to do rough retrieval, and then chrominance twice area (dividing) histogram is used to do fine retrieval. This system has high speed and accuracy, can be good used in (lots) (of) (situations), such as VOD,video monitor recorder,video switch and video data retrieval, etc.
出处
《西安工程科技学院学报》
2004年第4期335-339,共5页
Journal of Xi an University of Engineering Science and Technology
关键词
视频检索
HSI空间
实时分级
video retrieval
HSI model
real-time classification