基于可变步长关键帧提取的网络视频拷贝检索

doi:10.11772/j.issn.1001-9081.2014.11.3295

计算机应用 ›› 2014, Vol. 34 ›› Issue (11): 3295-3299.DOI: 10.11772/j.issn.1001-9081.2014.11.3295

基于可变步长关键帧提取的网络视频拷贝检索

陈晓晖,陈秀宏,甘月松

江南大学数字媒体学院,江苏无锡 214122

收稿日期:2014-05-16 修回日期:2014-06-29 出版日期:2014-11-01 发布日期:2014-12-01
通讯作者: 陈晓晖
作者简介:陈晓晖(1989-),男,江苏宿迁人,硕士研究生,主要研究方向:视频拷贝检索;陈秀宏(1964-),男,江苏泰兴人,教授,博士,CCF会员,主要研究方向:数字图像处理、模式识别;甘月松(1992-),男,河南信阳人,硕士研究生,主要研究方向:图像检索。
基金资助:
国家自然科学基金资助项目

Web video copy detection based on variable-length step key frame selection

CHEN Xiaohui,CHEN Xiuhong,GAN Yuesong

School of Digital Media, Jiangnan University, Wuxi Jiangsu 214122, China

Received:2014-05-16 Revised:2014-06-29 Online:2014-11-01 Published:2014-12-01
Contact: CHEN Xiaohui

摘要/Abstract

摘要：

为快速有效地检测网络中的拷贝视频,针对现有关键帧提取算法时间复杂度高、关键帧不具有代表性的缺点,提出一种可变步长提取关键帧提取方法。根据视频变化连续性特点,用相似的两近邻帧代表它们之间的视频片段;该方法首先选取关键帧中的核心区域与受影响较小的边缘区域,对不同的区域取权值并通过转换距离度量分块灰度顺序特征(OM)来判断两帧间相似度;然后利用滑动窗口来查找最大相似匹配,从而检测出查询视频中的拷贝片段。在网络数据和MUSCLE-VCD-2007数据上的实验结果表明,该方法相对于现有的基于OM特征拷贝检测法而言,其鲁棒性更强,检测效率更高。

Abstract:

To weaken the influence of unrepresentative frames and time complexity on detecting the copy of the video on the network, a quick and efficient variable-length step algorithm was proposed to select the most representative key frames. According to the characteristics of the video continuous change, the highly similar adjacent frames could be used to replace the corresponding video between them. Firstly, the algorithm selected core region and less affected edge region of key frame and allocated different areas with different weights so as to use the Ordinal Measures (OM) transformation distance measurement to judge the similarity between two frames. Then the sliding window was used to find the most similar match to detect the copy clips of query videos. The experimental results on actual network and MUSCLE-VCD-2007 dataset show that the proposed algorithm has stronger robustness and higher detection efficiency compared with the existing algorithms of copy detection feature measure based on OM.

中图分类号:

TP391.4

陈晓晖陈秀宏甘月松. 基于可变步长关键帧提取的网络视频拷贝检索[J]. 计算机应用, 2014, 34(11): 3295-3299.

CHEN Xiaohui CHEN Xiuhong GAN Yuesong. Web video copy detection based on variable-length step key frame selection[J]. Journal of Computer Applications, 2014, 34(11): 3295-3299.

参考文献

[1]ZHOU X, CHEN L, ZHOU X. Structure tensor series-based large scale near-duplicate video retrieval[J]. IEEE Transactions on multimedia, 2012, 4(14): 1220-1233.
[2]KANG M, HUANG X, YANG L. Video clip retrieval based on incidence matrix and dynamic-step sliding-window[C]// ICCASM 2010: Proceedings of the 2010 International Conference on Computer Application and System Modeling. Piscataway: IEEE Press,2010: 256-259.
[3]WU X, GAO K, GUO J, et al. Video copy detection based on multiple visual feature matching[J]. Journal of Computer-Aided Design and Computer Graphics, 2010, 11(22):1856-1865.(吴潇, 高科, 郭俊波, 等. 基于多特征匹配的视频拷贝检测算法[J]. 计算机辅助设计与图形学学报, 2010, 11(22): 1856-1865.)
[4]LE D D, SATOH S. National institute of informatics Japan at TRECVID 2007: BBC rushes summarization[C]// Proceedings of the 2007 International Workshop on TRECVID Video Summarization. New York: ACM Press, 2007: 70-73.
[5]LIN Y, YANG Y, LING K, et al. Video copy detection based on multiple visual feature synthesizing[J]. Journal of Image and Graphics, 2013, 18(5):591-599.(林莹, 杨扬, 凌康, 等. 多特征综合的视频拷贝检测[J]. 中国图象图形学报, 2013, 18(5): 591-599.)
[6]BAY H, TUYTELAARS T, van GOOL L. SURF: speeded up robust features[C]// Proceedings of the 9th European Conference on Computer Vision, LNCS 3951. Berlin: Springer-Verlag,2006: 404-417.
[7]UCHIDA Y, AGRAWAL M, SAKAZAWA S. Accurate content-based video copy detection with efficient feature indexing[C]// Proceedings of the 1st ACM International Conference on Multimedia Retrieval. New York: ACM Press, 2011: 19-26.
[8]HAMPAPUR A, HYUN K, BOLLE R M. Comparison of sequence matching techniques for video copy detection[C]// Proceedings of SPIE 4676. Bellingham: SPIE Press,2001: 194-201.
[9]KIM C, VASUDEV B. Spatiotemporal sequence matching for efficient video copy detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005, 15(1): 127-132.
[10]ZHANG Y, ZHANG D, GUO J, et al. Rapid video copy detection on compressed domain[J]. Journal on Communications, 2009, 30(3):135-140.(张勇东, 张冬明, 郭俊波,等. 压缩域快速视频拷贝检测算法[J]. 通信学报, 2009, 30(3): 135-140.)
[11]PENG Y, NGO C, DONG Q, et al. Video clip retrieval by maximal matching and optimal matching in graph theory[C]// Proceedings of the 2003 International Conference on Multimedia and Expo. Piscataway:IEEE Press, 2003:317-320.
[12]BAO W, JI L, LI S, et al. Effective and efficient copy detection algorithm for Web video[J]. Application Research of Computers, 2013, 30(11):3414-3417.(鲍伟, 吉立新, 李邵梅, 等. 一种快速有效的网络视频拷贝检测方法[J]. 计算机应用研究, 2013, 30(11): 3414-3417.)
[13]NIE R, DING G, WANG J, et al. A new fingerprint sequences matching algorithm for content-based copy detection[C]// IAS 2009:Proceedings of the Fifth International Conference on Information Assurance and Security. Piscataway: IEEE Press, 2009: 427-430.
[14]NIE X, LIU J, SUN J, et al. A LLE-based video copy detection method[J]. Journal of Electronics and Information Technology, 2011, 33(5):1030-1034.(聂秀山, 刘琚, 孙建德, 等. 基于局部线性嵌入的视频拷贝检测方法[J]. 电子与信息学报, 2011, 33(5): 1030-1034.)
[15]ZHAO Y, ZHOU X, HE X, et al. An efficient method for video clip retrieval using equivalence relation theory[J]. Journal of Image and Graphics, 2007,12(1); 127-134.(赵亚琴,周献中,何新,等.利用等价关系理论进行视频拷贝检索的方法[J].中国图象图形学报,2007,12(1);127-134.)
[16]The origin of the video dataset is MUSCLE-VCD-2007 [DB/OL].[2014-05-14] https://www.rocq.infia.fr/imedia/civr-benth/index.html.

基于可变步长关键帧提取的网络视频拷贝检索

Web video copy detection based on variable-length step key frame selection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	罗圣钦陈金怡李洪均. 基于注意力机制的多尺度残差UNet实现乳腺癌灶分割[J]. 计算机应用, 0, (): 0-0.
[2]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[3]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[4]	鲁永帅唐英杰马鑫然. 基于深度特征融合的无纺布低对比度浆丝缺陷检测方法[J]. 计算机应用, 0, (): 0-0.
[5]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[6]	许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032.
[7]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[8]	魏淳武, 赵涓涓, 唐笑先, 强彦. 基于多时期蒸馏网络的随访数据知识提取方法[J]. 计算机应用, 2021, 41(10): 2871-2878.
[9]	韩建栋, 李晓宇. 基于多尺度特征融合的行人重识别方法[J]. 计算机应用, 2021, 41(10): 2991-2996.
[10]	张凯悦, 张鸿. 基于注意力机制网络的航运监控图像识别模型[J]. 计算机应用, 2021, 41(10): 3010-3016.
[11]	李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003.
[12]	高世伟, 张长柱, 王祝萍. 基于可分离金字塔的轻量级实时语义分割算法[J]. 计算机应用, 2021, 41(10): 2937-2944.
[13]	卓禹心, 韩素雅, 张榆锋, 李支尧, 董毅峰. 基于超声谐波包络Nakagami参数图像的微波消融区域自动分割方法[J]. 计算机应用, 2021, 41(10): 3089-3096.
[14]	李敬虎邢前国郑向阳李琳王丽丽. 基于深度学习的无人机影像夜光藻赤潮提取方法[J]. 计算机应用, 0, (): 0-0.
[15]	任炜白鹤翔. 基于全局与局部的多标签图像分类方法[J]. 计算机应用, 0, (): 0-0.