特殊视频内容检测算法研究综述

doi:10.3969/j.issn.1671-1122.2016.09.037

摘要/Abstract

摘要：

网络流量的视频化趋势使得互联网视频内容呈现混杂化发展,各种非法特殊视频充斥其中,影响了社会公共安全,传统的通过视频源头进行控制的方式可行性较低,而建立内容检测过滤的方法将更为有效。为此,文章对色情、暴力、恐怖这三种特殊视频内容检测的研究现状和进展进行了综述。从三个角度,即视频内容描述模型、算法测试库、算法评判标准进行归纳和总结,详细介绍针对图像、视频等不同检测内容所采取的各种有效措施,对特征提取方法、分类检测策略及算法的检测效果进行了对比分析,之后对常用的算法测试库进行了整理,介绍不同测试库的数据量、数据特点及数据结构,同时介绍了视频内容检测方面几种常用的算法评判标准,最后对未来特殊视频检测技术的发展趋势进行了展望,以期为希望从事该领域研究的人员提供一些思路。

关键词: 内容检测, 特殊视频, 算法综述

Abstract:

Until now, research review of the special video content recognition algorithm has not yet appeared. But the network traffic has dominated by the video, and there are many types of contents, especial some illegal contents flooded the internet, which are affecting the social and public security. The traditional control methods which control the publishing of these videos are invalid, and the recognition model by content detection will be more effective. So, the survey of special content detection is given, and the summarization of the present work and developments about pornography, violence and terrorist videos content detection are presented. This paper has systematically surveyed the existing content detection algorithms from three aspects, and they are the content description model, the testing dataset, assessment criteria. Furthermore, combining with the current development of current technique, the research tendencies and the potential solutions are presented.

Key words: content identification, special video, algorithms survey

中图分类号:

TP309

任栋, 宋伟, 于京, 姜薇. 特殊视频内容检测算法研究综述[J]. 信息网络安全, 2016, 16(9): 184-191.

Dong REN, Wei SONG, Jing YU, Wei JIANG. A Survey on Special Video Content Detection Algorithms[J]. Netinfo Security, 2016, 16(9): 184-191.

图/表 12

表1

表2

表3

表4

表5

图1

图2

图3

图4

图5

图6

表6

参考文献 46

[1]	CNN. Smart Cameras Spot Shady Behavior[EB/OL]. , 2006-09-02.
[2]	DUAN L, CUI G, GAO W, et al.Adult Image Detection Method Base on Skin Color Model and Support Vector Machine[C]//Asian Federation of Computer Vision Societies. Asian conference on computer vision, January 22-25, 2002, Melbourne, Australia. Tokyo: ACCV, 2002: 797-800.
[3]	MICHAEL J J, JAMES M.Statistical Color Model with Application to Skin Detection[J]. International Journal of Computer Vision, 2002, 46(1):81-96.
[4]	PENG T, CUI P.Adult Image Detection Based on Skin Visual Words and Face Information[C]//Natural Computation (ICNC). 2015 11th International Conference on Natural Computation, August 15-17, 2015, Zhangjiajie, China. New York: IEEE, 2015: 944-948.
[5]	SHEN X, WEI W, QIAN Q.A Pornographic Image Filtering Model Based on Erotic Part[C]// IEEE Press CISP. The 3rd International Congress on Image and Signal Processing, October 16-18, 2010, Yantai, China. New York: IEEE, 2010:2473-2477.
[6]	HU W, ZUO H, WU O, et al.Recognition of Adult Images, Videos, and Web Page Bags[J]. ACM Transactions on Multimedia Computing Communications & Applications, 2011, 7(1):1-24.
[7]	黄杰, 倪鹏宇. 基于人体关键部位的不良图像过滤[J]. 应用科学学报, 2014, 32(4):416-422.
[8]	QING F Z, WEI Z,WEI Q W, et al.Shape-based Adult Image Detection[J]. International Journal of Image & Graphics, 2006, 6(1):115-124.
[9]	HU W, WU O, CHEN Z, et al.Recognition of Pornographic Web Pages by Classifying Texts and Images.[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007, 29(6):1019-34.
[10]	DESELAERS T, PIMENIDIS L, NEY H.Bag-of-visual-words Models for Adult Image Classification and Filtering[C]// IEEE Computer Society. 19th International Conference on Pattern Recognition (ICPR 2008), December 8-11, 2008, Tampa, Florida, USA. IEEE, 2008:1-4.
[11]	OPES A P B, DE AVILA S E F, PEIXOTO A N A, et al. A Bag-of-Features Approach Based on Hue-sift Descriptor for Nude Detection[C] //Signal Processing Conference, 2009 17th European, August 24-28, 2009, Glasgow, Scotland. IEEE, 2009: 1552-1556.
[12]	IA S M, RAHMANI H, MORTEZAEI R, et al. A Novel Scheme for Intelligent Recognition of Pornographic Images[J]. arXiv preprint arXiv:1402.5792, 2014.
[13]	I D, LI N, WANG J, et al. Pornographic Images Recognition Based on Spatial Pyramid Partition and Multi-instance Ensemble Learning[J]. Knowledge-Based Systems, 2015, 84(C):214-223.
[14]	MOUSTAFA M. Applying Deep Learning to Classify Pornographic Images and Videos[J]. arXiv preprint arXiv:1511.08899, 2015.
[15]	WIJAYA I, WIDIARTHA I B K, UCHIMURA K, et al. Phonographic Image Recognition Using Fusion of Scale Invariant Descriptor[C]//Frontiers of Computer Vision (FCV). 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2015, January 28-30, 2015, Mokpo, South Korea. IEEE, 2015: 1-5.
[16]	袁泽. 敏感视频识别的关键技术研究与应用[D].北京:北京化工大学,2 015.
[17]	YU W, QU Z, JIN Y.A Pornographic Video Detection Method Based on Semi-supervised Learning on Graphs[C]//Computational Intelligence and Design (ISCID). 2013 Sixth International Symposium on Computational Intelligence and Design, October 28-29, 2013, Hangzhou, China. IEEE, 2013: 347-350.
[18]	王辰龙. 基于结构和融合的特定敏感视频识别技术[D].北京:北京交通大学, 2015.
[19]	LIU Y Z, YANG Y, XIE H T, et al.Fusing Audio Vocabulary with Visual Features for Pornographic Video Detection[J]. Future Generation Computer Systems, 2014, 31(1):69-76.
[20]	AVILA S, THOME N, CORD M, et al.Pooling in Image Representation: The Visual Codeword Point of View[J]. Computer Vision and Image Understanding, 2013, 117(5): 453-465.
[21]	CAETANO C, AVILA S, GUIMARAES S, et al.Pornography Detection Using Bossanova Video Descriptor[C]//2014 22nd European Signal Processing Conference (EUSIPCO), September 1-5, 2014, Lisbon, Portugal. IEEE, 2014: 1681-1685.
[22]	WANG J, LI B, HU W, et al.Horror Movie Scene Recognition Based on Emotional Perception[C]// ICIP. 2010 17th IEEE International Conference on Image Processing, September 26-29, Hong Kong, China. IEEE, 2010: 1489-1492.
[23]	WANG J, LI B, HU W, et al.Horror Video Scene Recognition via Multiple-instance Learning[C]// ICASSP. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, May 22-27, 2011, Prague Congress Center, Prague, Czech Republic. IEEE, 2011: 1325-1328.
[24]	WU B, JIANG X, SUN T, et al.A Novel Horror Scene Detection Scheme on Revised Multiple Instance Learning Model[C]// Department of Computer Science and Engineering, National Taiwan Ocean University. International Conference on Multimedia Modeling, January 5-7, 2011, Taipei, China. Springer Berlin Heidelberg, 2011: 359-370.
[25]	SONG W, YANG P, YANG G, et al.Horror Video Recognition Based on Fuzzy Evolution[C]//CCT. International Conference on Cyberspace Technology, November 8-10, 2014, Beijing, China. IET, 2014: 1-5.
[26]	DING X, LI B, HU W, et al.Horror Video Scene Recognition Based on Multi-view Multi-instance Learning[C]//Computer Vision-ACCV 2012. 11th Asian Conference on Computer Vision, November 5-9, 2012, Daejeon, Korea. Springer Berlin Heidelberg, 2013: 599-610.
[27]	DING X, LI B, HU W, et al.Context-aware Horror Video Scene Recognition via Cost-sensitive Sparse Coding[C]//Pattern Recognition (ICPR). 2012 21st International Conference on Pattern Recognition, November 11-15, 2012, Tsukuba, Japan. IEEE, 2012: 1904-1907.
[28]	DING X, LI B, HU W, et al.Horror Video Scene Recognition Based on Multi-View Joint Sparse Coding[J]. Tien Tzu Hsueh Pao/acta Electronica Sinica, 2014, 42(2):301-305.
[29]	HU W, Ding X, Li B, et al.Multi-Perspective Cost-Sensitive Context-Aware Multi-Instance Sparse Coding and Its Application to Sensitive Video Recognition[J]. IEEE Transactions on Multimedia, 2015, 18(1):1-1.
[30]	DING C, FAN S, ZHU M, et al.Violence Detection in Video by Using 3D Convolutional Neural Networks[M]. Springer International Publishing, 2014:551-558.
[31]	NAM J H, ALGHONIEMY M, TEWFIK A H.Audio-visual Content-based Violent Scene Characterization[C]//ICIP. 1998 International Conference on Image Processing, October 4-7, 1998, Chicago, Illinois. IEEE, 1998:353-357.
[32]	LIN J, WANG W.Weakly-Supervised Violence Detection in Movies with Audio and Video Based Co-training[J]. Lecture Notes in Computer Science, 2009 (5879) : 930-935.
[33]	DATTA A, SHAH M, LOBO N D V. Person-on-person Violence Detection in Video Data[C]//ICPR. Proceedings of 16th International Conference on Pattern Recognition 2002, August. 11-15, 2002, Quebec City, Quebec, Canada. IEEE, 2002, 1: 433-438.
[34]	WANG K, ZHANG Z, WANG L.Violence Video Detection by Discriminative Slow Feature Analysis[J]. Communications in Computer & Information Science, 2012, 321:137-144.
[35]	CHEN D, WACTLAR H, CHEN D, et al.Recognition of Aggressive Human Behavior Using Binary Local Motion Descriptors[C]//Engineering in Medicine and Biology Society. 30th Annual International Conference of the IEEE, August 20-24, 2008, Vancouver, Canada. IEEE, 2008: 5238-5241.
[36]	GIANNAKOPOULOS T, MAKRIS A, KOSMOPOULOS D, et al.Audio-visual Fusion for Detecting Violent Scenes in Videos[M]//Artificial Intelligence: Theories, Models and Applications. Springer Berlin Heidelberg, 2010.
[37]	ACAR E, HOPFGARTNER F, ALBAYRAK S.Violence Detection in Hollywood Movies by the Fusion of Visual and Mid-level Audio Cues[C]//ACM. Proceedings of the 21st ACM international conference on Multimedia, October 21-25, 2013, Barcelona, Spain. ACM, 2013: 717-720.
[38]	HASSNER T, ITCHER Y, KLIPER-GROSS O.Violent Flows: Real-time Detection of Violent Crowd Behavior[C]// Computer Vision and Pattern Recognition Workshops (CVPRW). 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop, June 16-21, 2015, Providence, RI, USA. IEEE, 2015:1-6.
[39]	NIEVAS E B, SUAREZ O D, GARCIA G B, et al.Violence Detection in Video Using Computer Vision Techniques[C]//CAIP. Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part II, August 29-31, 2011, Seville, Spain. Springer-Verlag, 2011:332-339.
[40]	CHEN M, Hauptmann A[EB/OL]., 2015-1-26.
[41]	KATAOKA H, HASHIMOTO K, IWATA K, et al.Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition[M]// Computer Vision -- ACCV 2014. Springer International Publishing, 2014.
[42]	XU L, GONG C, YANG J, et al.Violent Video Detection Based on MoSIFT Feature and Sparse Coding[C]// Acoustics, Speech and Signal Processing (ICASSP). 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, May 4-9, 2014, Florence, Italy. IEEE, 2014:3538-3542.
[43]	PENG X, QIAO Y, PENG Q.Motion Boundary Based Sampling and 3D Co-occurrence Descriptors for Action Recognition[J]. Image & Vision Computing, 2014, 32(9):616-628.
[44]	MOUSAVI H, MOHAMMADI S, PERINA S, et al.Analyzing Tracklets for the Detection of Abnormal Crowd Behavior[C]// Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, January 6-8, 2015, Big Island, Hawaii. IEEE Computer Society, 2015:148-155.
[45]	YEFFET L, WOLF L.Local Trinary Patterns for Human Action Recognition[C]// Computer Vision. 2009 IEEE 12th International Conference on Computer Vision, September 29-October 2, 2009, Kyoto, Japan. IEEE, 2009:492-497.
[46]	LAPTEV I, MARSZALEK M, SCHMID C, et al.Learning Realistic Human Actions from Movies[C]//CVPR. Conference on Computer Vision and Pattern Recognition, June 24-26, 2008, Anchorage, Alaska, USA. IEEE Computer Society, 2008:1-8.