基于目标变化的监控视频关键帧提取方法

doi:10.3969/j.issn.1006-2475.2016.08.013

计算机与现代化

基于目标变化的监控视频关键帧提取方法

(南京航空航天大学计算机科学与技术学院，江苏南京 211106)

收稿日期:2016-02-16 出版日期:2016-08-18 发布日期:2016-08-11
作者简介:周萍(1990-)，女，江苏南通人，南京航空航天大学计算机科学与技术学院硕士研究生，研究方向：图像处理和视频分析，数据挖掘，垂直搜索引擎。

Surveillance Video Keyframe Extraction Based on Objects Change

(School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China)

Received:2016-02-16 Online:2016-08-18 Published:2016-08-11

摘要/Abstract

摘要： 监控视频关键帧提取技术作为监控视频分析的重要研究内容，能够有效地解决视频数据的高效存储和快速访问等问题。本文提出一种基于目标变化的监控视频关键帧提取方法，分析监控视频帧间的目标变化，并采用局部极大值优化方法将原监控视频划分成视频片段。最后，从每个视频片段中选取特征中心对应视频帧作为关键帧，并依据目标的属性删除冗余的关键帧得到最终的视频关键帧集合。实验结果表明，该方法所提取的视频关键帧冗余性较低，所包含的内容很具有代表性。同时，该方法的复杂度较低，适用于监控视频的关键帧提取工作。

关键词: 关键帧, 特征距离曲线, 局部最大值优化, 冗余关键帧

Abstract: As an important research content of surveillance video analysis, video keyframe extraction can effectively solve a series of problems such as the efficient storage and rapid access of video data. This paper proposes a surveillance video keyframe extraction method based on objects change. We firstly analyze objects change between different video frames, and then use the local maximum optimization to decompose an original surveillance video into some video clips. Finally, each keyframe is chosen from each video clip corresponding to feature center. On the basis of the object attribute, some redundant keyframes will be deleted to ensure a more compact keyframe set. The experimental results show that our method extracted video keyframes with low redundancy; meantime the contained content is very representative. In addition, our method has low complexity, which is suitable for online surveillance video analysis.

Key words: keyframe, curve of feature distance, local maximum optimization, redundant keyframe

中图分类号:

TP391.4

周萍. 基于目标变化的监控视频关键帧提取方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2016.08.013.

ZHOU Ping. Surveillance Video Keyframe Extraction Based on Objects Change[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2016.08.013.

参考文献

[1] 欧阳建权,李锦涛,张勇东. 视频摘要技术综述[J]. 计算机工程, 2005,31(10):7-9.

[2] 彭海强,廖华丽. 基于水下视频图像去雾帘的关键帧提取系统[J]. 计算机与现代化, 2015(11):84-88.

[3] Liu Gentao, Wen Xiangming, Zheng Wei, et al. Shot boundary detection and keyframe extraction based on scale invariant feature transform[C]// Proceedings of the 8th IEEE/ACIS International Conference on Computer and Information Science. 2009:1126-1130.

[4] Hanjalic A, Zhang Hongjiang. An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999,9(8):1280-1289.

[5] Kim G, Sigal L, Xing E P. Joint summarization of large-scale collections of Web images and videos for storyline reconstruction[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2014:4225-4232.

[6] 张芯,谢毓湘,栾悉道. 一种基于局部二值模式的关键帧提取方法[J]. 计算机与现代化, 2013(11):8-12.

[7] Hadi Y, Essannouni F, Thami R O H. Video summarization by k-medoid clustering[C]// Proceedings of the 2006 ACM Symposium on Applied Computing. 2006:1400-1401.

[8] Borgo R, Chen Min, Daubney B, et al. A survey on video-based graphics and video visualization[C]// EuroGraphics. 2011:1-23.

[9] 唐铭谦. 基于对象的监控视频摘要算法研究[D]. 西安:西安电子科技大学, 2014.

[10] 刘云鹏,张三元,王仁芳,等. 视觉注意模型的道路监控视频关键帧提取[J]. 中国图象图形学报, 2013,18(8):933-943.

[11] Wang Feng, Ngo C W. Summarizing rushes videos by motion, object, and event understanding[J]. IEEE Transactions on Multimedia, 2012,14(1):76-87.

[12] Wang Meng, Hong Richang, Li Guangda, et al. Event driven Web video summarization by tag localization and key-shot identification[J]. IEEE Transactions on Multimedia, 2012,14(4):975-985.

[13] Meghdadi A H, Irani P. Interactive exploration of surveillance video through action shot summarization and trajectory visualization[J]. IEEE Transactions on Visualization and Computer Graphics, 2013,19(12):2119-2128.

[14] Barnich O, Van Droogenbroeck M. ViBe: A universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011,20(6):1709-1724.

[15] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]// Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition. 2000,2:142-149.

[16] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). 2005,1:886-893.

[17] 张婵,高新波,姬红兵. 视频关键帧提取的可能性C-模式聚类算法[J]. 计算机辅助设计与图形学学报, 2005,17(9):2040-2045.

[18] Truong B T, Venkatesh S. Video abstraction: A systematic review and classification[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2007,3(1): Article No. 3.

[19] Goyette N, Jodoin P-M, Porikli F, et al. Changedetection.net: A new change detection benchmark dataset[C]// Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2012.

[20] Kim C, Hwang J N. Object-based video abstraction for video surveillance systems[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2002,12(12):1128-1138.

[21] de Avila S E F, Lopes A P B, da Luz Jr. A, et al. VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method[J]. Pattern Recognition Letters, 2011,32(1):56-58.

基于目标变化的监控视频关键帧提取方法

Surveillance Video Keyframe Extraction Based on Objects Change

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	陈翔, 邹庆年, 谢绍宇, 陈翠琼. 一种面向运动目标的关键帧自动选择算法[J]. 计算机与现代化, 2020, 0(10): 81-89.
[2]	阿不都克里木·玉素甫1,2，王亮亮1. 基于自主可控平台的FFMPEG在线视频转换系统[J]. 计算机与现代化, 2020, 0(01): 81-.
[3]	彭海强，廖华丽. 基于水下视频图像去雾帘的关键帧提取系统[J]. 计算机与现代化, 2015, 0(11): 84-88.
[4]	曾华;杨汉辉. 一种两阶段的关键帧提取方法[J]. 计算机与现代化, 2011, 1(6): 33-3.
[5]	袁铨;张建中;张剑平. 基于Hermite样条曲线的关键帧插值角色动画[J]. 计算机与现代化, 2010, 1(8): 130-134.