基于内容的视频检索综述  

Overview of Content-based Video Retrieval

作　　者：胡志军 徐勇 HU Zhi-jun;XU Yong(Guizhou Provincial Key Laboratory of Public Big Data,Guizhou University,Guiyang 550025,China;College of Computer Science&Technology,Guizhou University,Guiyang 550025,China;Harbin Institute of Technology(Shenzhen),Shenzhen,Guangdong 518055,China)

机构地区：[1]贵州大学贵州省公共大数据重点实验室,贵阳550025 [2]贵州大学计算机科学与技术学院,贵阳550025 [3]哈尔滨工业大学(深圳),广东深圳518055

出　　处：《计算机科学》2020年第1期117-123,共7页Computer Science

基　　金：贵州省公共大数据重点实验室开放课题基金(2018BDKFJJ001)~~

摘　　要：视频是携带信息量最大的媒体,随着抖音短视频等APP的兴起,网络以及数据库的视频数量急剧增加,人工标注的方法已经无法胜任视频检索的任务。视频检索通过提取视频帧的空间特征或者帧与帧之间的时间特征,使得用户能够更客观、更高效地进行视频查找与归类。文中概述了基于内容的视频检索算法,归纳总结了视频检索的一些经典算法,并总结了深度学习在基于内容的视频检索中的研究与应用,最后分析了深度学习在视频检索中的发展前景。Video is the medium with plenty of information,with the rise of short video APP such as vibrato,the number of videos in the network and database has increased dramatically and the method of manual labeling is no longer suitable for video retrieval.Video retrieval by extracting the spatial characteristics of video frames or temporal characteristics between frames and frames enables users to perform video search and categorization more objectively and efficiently.This paper summarized the content-based video retrieval algorithms,some classical algorithms of video retrieval,and the research and application of deep learning in content-based video retrieval.Finally,the development prospect of deep learning in video retrieval was anzlyzed.

关 键 词：视频检索 卷积神经网络 关键帧 特征提取 镜头分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]