• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
高级检索

视频拷贝检测方法综述

顾佳伟, 赵瑞玮, 姜育刚

顾佳伟, 赵瑞玮, 姜育刚. 视频拷贝检测方法综述[J]. 计算机研究与发展, 2017, 54(6): 1238-1250. DOI: 10.7544/issn1000-1239.2017.20170003
引用本文: 顾佳伟, 赵瑞玮, 姜育刚. 视频拷贝检测方法综述[J]. 计算机研究与发展, 2017, 54(6): 1238-1250. DOI: 10.7544/issn1000-1239.2017.20170003
Gu Jiawei, Zhao Ruiwei, Jiang Yugang. Video Copy Detection Method: A Review[J]. Journal of Computer Research and Development, 2017, 54(6): 1238-1250. DOI: 10.7544/issn1000-1239.2017.20170003
Citation: Gu Jiawei, Zhao Ruiwei, Jiang Yugang. Video Copy Detection Method: A Review[J]. Journal of Computer Research and Development, 2017, 54(6): 1238-1250. DOI: 10.7544/issn1000-1239.2017.20170003

视频拷贝检测方法综述

基金项目: 国家自然科学基金优秀青年科学基金项目(61622204)
详细信息
  • 中图分类号: TP311

Video Copy Detection Method: A Review

  • 摘要: 目前网络上存在着大量的拷贝视频,研究人员长期以来致力于视频拷贝检测技术的研究,特别是近年来随着深度学习方法的引入,又涌现出了一些新颖的检测算法.将对现有代表性的视频拷贝检测方法进行回顾与总结,涵盖视频拷贝检测系统的基本框架与各个主要步骤的不同实现方法,包含视频拷贝检测中的特征提取、建立索引、特征匹配与时间对齐等不同模块.总结的关键技术包括了最新的深度学习方法在其中的应用与取得的突破,主要体现在深度卷积神经网络和双胞胎卷积神经网络方法的应用.此外,还将详细介绍目前常用的5个用于视频拷贝检测评测的数据集及通用的评价标准,并讨论分析一些代表性方法的性能表现.最后,对视频拷贝检测技术未来发展趋势进行展望.
    Abstract: Currently, there exist large amount of copy videos on the Internet. To identify these videos, researchers have been working on the study of video copy detection methods for a long time. In recent years, a few new video copy detection algorithms have been proposed with the introduction of deep learning. In this article, we provide a review on the existing representative video copy detection methods. We introduce the general framework of video copy detection system as well as the various implementation choices of its components, including feature extraction, indexing, feature matching and time alignment. The discussed approaches include the latest deep learning based methods, mainly the application of deep convolutional neural networks and siamese convolutional neural networks in video copy detection system. Furthermore, we summarize the evaluation criteria used in video copy detection and discuss the performance of some representative methods on five popular datasets. In the end, we envision future directions on this topic.
计量
  • 文章访问数:  2127
  • HTML全文浏览量:  5
  • PDF下载量:  1152
  • 被引次数: 0
出版历程
  • 发布日期:  2017-05-31

目录

    /

    返回文章
    返回