基于视觉语义概念的暴恐视频检测

doi:10.3969/j.issn.1671-1122.2016.09.003

信息网络安全 ›› 2016, Vol. 16 ›› Issue (9): 12-17.doi: 10.3969/j.issn.1671-1122.2016.09.003

基于视觉语义概念的暴恐视频检测

宋伟¹(), 杨培^1,², 于京³, 姜薇⁴

1.中央民族大学信息工程学院,北京 100081
2.青海大学计算机技术与应用系, 青海西宁 810016
3.北京交通大学电子信息工程学院,北京 100044
4. 网络空间技术（北京）有限公司,北京 102200

收稿日期:2016-07-25 出版日期:2016-09-20 发布日期:2020-05-13
作者简介:
作者简介：宋伟（1983—）,男,湖北,讲师,博士,主要研究方向为图像处理、视频内容识别; 杨培（1986—）,男,河北,硕士,主要研究方向为视频内容检测;于京（1971—）,男,江苏,教授,博士,主要研究方向为图像处理;姜薇（1978—）,女,北京,高级工程师,硕士,主要研究方向为网络信息安全。
基金资助:
国家自然科学基金 [61503424];国家民委科研项目[14ZYZ017]

Terrorist Video Detection Using Visual Semantic Concepts

Wei SONG¹(), Pei YANG^1,², Jing YU³, Wei JIANG⁴

1.School of Information Engineering of Minzu University of China, Beijing 100081, China
2.Department of Computer Technology and Applications of Qinghai University, Xining Qinghai 810016, China
3. School of Electronic Information Engineering of Beijing Jiaotong University, Beijing 100044, China
4. Cyberspace Technology Limited Company, Beijing 102200, China

Received:2016-07-25 Online:2016-09-20 Published:2020-05-13

摘要/Abstract

摘要：

暴恐视频在互联网的传播严重威胁着社会稳定与安全,对暴恐视频进行检测充满技术挑战。文章创建了用于评价暴恐视频检测算法性能的暴恐视频数据集,对数据集进行了语义概念和视频两个层面的标注。研究了基于灰度直方图、颜色直方图、颜色矩、局部二值模式及梯度方向直方图等特征描述子和支持向量机及极限学习机的视觉语义概念检测,针对不同的视觉语义概念通过仿真实验确定了最佳特征与分类器组合方式及相应参数设置。提出了基于灰度质心的视频关键帧提取方法,利用帧间相似性和视频序列相似性判别完成镜头突变和渐变判别,完成视频关键帧的提取。基于视觉语义概念和视觉语义概念词袋构建暴恐视频词频特征,使用支持向量机和视觉语义词频特征完成了暴恐视频内容的检测,并通过实验验证了该方法的可行性。

关键词: 支持向量机, 极限学习机, 视觉语义概念, 暴恐视频检测

Abstract:

The spreading of terrorist video on internet threated the public safety a lot, and the detection of terrorist video content is full of technical challenges. In this paper, a terrorist video dataset was constructed for evaluation of algorithms, and the dataset is annotated by visual semantic concepts. Methods based on five kind of feature descriptor (gray histogram, color histogram, color moment, local binary pattern and histogram of orientation of gradient) and support vector machine and extreme learning machine were studied for visual semantic concept detection. A video key frame extraction algorithm based on gray massive center was implemented, and shots gradual change and sudden change were detected using similarity between neighboring frames and video sequence. A terrorist video detection framework was proposed combined visual semantic concepts and bag of visual semantic concepts, and the result of simulation experiment proved the effectiveness of it.

Key words: support vector machine, extreme learning machine, visual semantic concept detection, terrorist video detection

中图分类号:

TP309

宋伟, 杨培, 于京, 姜薇. 基于视觉语义概念的暴恐视频检测[J]. 信息网络安全, 2016, 16(9): 12-17.

Wei SONG, Pei YANG, Jing YU, Wei JIANG. Terrorist Video Detection Using Visual Semantic Concepts[J]. Netinfo Security, 2016, 16(9): 12-17.

图/表 7

图1

图2

表1

图3

图4

图5

图6

参考文献 23

[1]	中国互联网信息中心(CNNIC), 2016-09-12.
[2]	Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, , 2013-2018.
[3]	CONG Y, YUAN J, LIU J.Abnormal Event Detection in Crowded Scenes Using Sparse Representation[J]. Pattern Recognition, 2013(46): 1851-1864.
[4]	KARPATHY A, ARPATHY A, TODERICI G, et al.Large-scale Video Classification with Convolutional Neural Networks[C]// IEEE. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 23-28, Columbus, OH, USA. New York: IEEE, 2014:1725-1732.
[5]	BLANK M, GORELICK L, SHECHTMAN E, et al.Actions as Space-Time Shapes[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007, 29(12):2247-53.
[6]	YILMAZ A, SHAH M.Actions sketch: A Novel Action Representation[C]// IEEE. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 20-25. San Diego, CA, USA. New York: IEEE, 2005: 984-989.
[7]	HASSNER T, ITCHER Y, KLIPER-GROSS O.Violent flows: Real-time Detection of Violent Crowd Behavior[C] //IEEE. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 16-21,Providence, RI USA. New York: IEEE, 2012: 1-6.
[8]	de Souza F D M, Chávez G C, do Valle E A, et al. Violence Detection in Video Using Spatio-temporal Features[C]// IEEE. IEEE 23th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), August 30 - September 3, Gramado, Brazil. New York: IEEE, 2010: 224-230.
[9]	NIEVAS E B, SUAREZ O D, GARCIA G B, et al.Violence Detection in Video Using Computer Vision Techniques[C]// Computer Analysis of Images and Patterns, Springer Berlin Heidelberg. Berlin: Springer-Verlag, 2011: 332-339.
[10]	CHEN M Y, HAUPTMANN A, CHEN M Y, et al.MoSIFT: Recognizing Human Actions in Surveillance Videos[J]. Annals of Pharmacotherapy, 2009, 39(1):150-2.
[11]	XU L, GONG C, YANG J, et al.Violent Video Detection Based on MoSIFT Feature and Sparse Coding[C]//IEEE. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 4-9. Florence, Italy. New York: IEEE, 2014: 3538-3542.
[12]	GOTO S, AOKI T. TUDCL at MediaEval 2013 Violent Scenes Detection: Training with Multi-modal Features by MKL[EB/OL]. , 2016-9-2.
[13]	LAM V, LE D D, PHAN S, et al. NII-UIT at MediaEval 2013 Violent Scenes Detection Affect Task[EB/OL]. , 216-9-2.
[14]	DAI Q, TU J, SHI Z, et al. Fudan at MediaEval 2013: Violent Scenes Detection Using Motion Features and Part-Level Attributes[EB/OL]. , 2016-9-2.
[15]	LIU J, Yu Q, Javed O, et al.Video event recognition using concept attributes[C]//IEEE. IEEE Workshop on Applications of Computer Vision (WACV), Jan 17-18,Clearwater Beach, Florida. New York: IEEE, 2013: 339-346.
[16]	ASSARI S, ZAMIR A, SHAH M.Video Classification Using Semantic Concept Co-occurrences[C] // IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE, 2014: 2529-2536.
[17]	GOTO S, AOKI T.Violent Scenes Detection Using Mid-level Violence Clustering[J]. Computer Science, 2014: 283-296.
[18]	TAN C C, NGO C W. The Vireo Team at MediaEval 2013: Violent Scenes Detection by Mid-level Concepts Learnt from Youtube[EB/OL]. , 2016-9-2.
[19]	IONESCU B, SCHLUTER J, MIRONICA I, et al.A Naive Mid-level Concept-based Fusion Approach to Violence Detection in Hollywood Movies[C]// ACM. Proceedings of the 3rd ACM conference on International conference on multimedia retrieval, April 16-19, Dallas, Texas, USA. New York:ACM, 2013: 215-222.
[20]	YANG J, JIANG Y G, HAUPTMANN A G, et al.Evaluating Bag-of-visual-words Representations in Scene Classification[C]// ACM. Sigmm International Workshop on Multimedia Information Retrieval, September, 2007, Augsburg, Bavaria, Germany. New York:ACM, 2007:197-206.
[21]	DESELAERS T, PIMENIDIS L, NEY H.Bag-of-visual-words Models for Adult Image Classification and Filtering[C]// IEEE. International Conference on Pattern Recognition, December 8-11, Tampa Convection Center, Tampa, Florida, USA. New York:IEEE, 2008: 1-4.
[22]	DOS SANTOS J M, DE MOURA E S, DA SILVA A S, et al. A signature-based Bag of Visual Words Method for Image Indexing and Search[J]. Pattern Recognition Letters, 2015(65): 1-7.
[23]	ALDAVERT D, RUSINOL M, TOLEDO R, et al.A Study of Bag-of-Visual-Words Representations for Handwritten Keyword Spotting[J]. International Journal on Document Analysis and Recognition (IJDAR), 2015, 18(3): 223-234.

基于视觉语义概念的暴恐视频检测

Terrorist Video Detection Using Visual Semantic Concepts

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 23

相关文章 14

编辑推荐

Metrics

本文评价

[1]	胡建伟, 赵伟, 闫峥, 章芮. 基于机器学习的SQL注入漏洞挖掘技术的分析与实现[J]. 信息网络安全, 2019, 19(11): 36-42.
[2]	魏书宁, 陈幸如, 焦永, 王进. AR-OSELM算法在网络入侵检测中的应用研究[J]. 信息网络安全, 2018, 18(6): 1-6.
[3]	和湘, 刘晟, 姜吉国. 基于机器学习的入侵检测方法对比研究[J]. 信息网络安全, 2018, 18(5): 1-11.
[4]	宋金伟, 杨进, 李涛. 基于加权支持向量机的Domain Flux僵尸网络域名检测方法研究[J]. 信息网络安全, 2018, 18(12): 66-71.
[5]	魏书宁, 陈幸如, 唐勇, 刘慧. AR-HELM算法在网络流量分类中的应用研究[J]. 信息网络安全, 2018, 18(1): 9-14.
[6]	苏静, 路文玲, 赵毅强, 史艳翠. 基于支持向量机的硬件木马检测建模与优化[J]. 信息网络安全, 2017, 17(8): 33-38.
[7]	张谦, 高章敏, 刘嘉勇. 基于Word2vec的微博短文本分类研究[J]. 信息网络安全, 2017, 17(1): 57-62.
[8]	张晓惠, 林柏钢. 基于平衡二叉决策树SVM算法的物联网安全研究[J]. 信息网络安全, 2015, 15(8): 20-25.
[9]	戚名钰, 刘铭, 傅彦铭. 基于PCA的SVM网络入侵检测研究[J]. 信息网络安全, 2015, 15(2): 15-18.
[10]	. 基于区域性构建支持向量机模型的空域水印算法[J]. , 2014, 14(2): 32-.
[11]	晁沛;周亚建. 基于区域性构建支持向量机模型的空域水印算法[J]. , 2014, 14(2): 0-0.
[12]	宋健豪;赵刚;宋君易. 基于离线检测的SVMNIDS模式研究[J]. , 2012, 12(9): 0-0.
[13]	黄华军;钱亮;王耀钧. 基于异常特征的钓鱼网站URL检测技术[J]. , 2012, 12(1): 0-0.
[14]	郑辉. 基于KPCA组合核函数SVM的网络危险因素识别[J]. , 2010, (2): 0-0.