基于轨迹分段LDA主题模型的视频异常行为检测方法

doi:10.11772/j.issn.1001-9081.2015.02.0515

计算机应用 ›› 2015, Vol. 35 ›› Issue (2): 515-518.DOI: 10.11772/j.issn.1001-9081.2015.02.0515

基于轨迹分段LDA主题模型的视频异常行为检测方法

郑併斌^1,2, 范新南^1,2, 李敏², 张继^1,2

1. 江苏省输配电装备技术重点实验室(河海大学), 江苏常州 213022;
2. 河海大学物联网工程学院, 江苏常州 213022

收稿日期:2014-09-18 修回日期:2014-11-07 出版日期:2015-02-10 发布日期:2015-02-12
通讯作者: 郑併斌
作者简介:郑併斌(1989-),男,福建罗源人,硕士研究生,主要研究方向:智能图像处理; 范新南(1965-),男,江苏宜兴人,教授,博士,CCF高级会员,主要研究方向:信息获取与信息处理、智能图像处理; 李敏(1982-),女,山西大同人,讲师,博士,主要研究方向:遥感图像异常检测、仿生系统建模; 张继(1990-),男,江苏盐城人,硕士研究生,主要研究方向:图像融合。
基金资助:
国家自然科学基金资助项目(61273170, 41301448)。

Trajectory segment-based abnormal behavior detection method using LDA model

ZHENG Bingbin^1,2, FAN Xinnan^1,2, LI Min², ZHANG Ji^1,2

1. Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology (Hohai University), Changzhou Jiangsu 213022, China;
2. College of Internet of Things Engineering, Hohai University, Changzhou Jiangsu 213022, China

Received:2014-09-18 Revised:2014-11-07 Online:2015-02-10 Published:2015-02-12

摘要/Abstract

摘要：

基于目标轨迹的异常行为检测算法忽略了轨迹内部信息,容易导致异常检测虚警率偏高。为解决该问题,提出一种基于轨迹分段主题模型的视频异常行为检测方法。首先将目标原始轨迹根据轨迹转角分段,然后采用分段量化的方式提取轨迹片段中包含的行为特征信息,接着通过潜在狄利克雷分配(LDA)主题模型建模发掘目标轨迹之间的时空关系,最后通过学习所构建的模型并结合贝叶斯理论进行行为模式分析和异常行为检测。分别对两个视频场景进行了目标行为模式分析和异常行为检测的仿真实验,检测出了场景内多种异常行为模式。实验结果表明,通过结合轨迹分段与LDA主题模型,该算法能够充分挖掘目标轨迹内部的行为特征信息,识别多种异常行为模式,并且能提高对异常行为检测的准确率。

关键词: 视频分析, 行为模式分析, 异常检测, 潜在狄利克雷分配, 主题模型, 轨迹分段

Abstract:

Most of the current trajectory-based abnormal behavior detection algorithms do not consider the internal information of the trajectory, which might lead to a high false alarm rate. An abnormal behavior detection method based on trajectory segment using the topic model was presented. Firstly, the original trajectories were partitioned into trajectory segments according to turning angles. Secondly, the behavior characteristic information was extracted by quantifying the observations from these segments into different visual words. Then the time-space relationship among the trajectories was explored by Latent Dirichlet Allocation (LDA) model. Finally, the behavior pattern analysis and the abnormal behavior detection could be implemented by learning the corresponding generative topic model combined with the Bayesian theory. Simulation experiments of behavior pattern analysis and abnormal behavior detection were conducted on two video scenes, and different kinds of abnormal behavior patterns were detected. The experimental results show that, combining with trajectory segmentation, the proposed method can dig the internal behavior characteristic information to identify a variety of abnormal behavior patterns and improve the accuracy of abnormal behavior detection.

Key words: video analysis, behavior pattern analysis, abnormal detection, Latent Dirichlet Allocation (LDA), topic model, trajectory segmentation

中图分类号:

TP391.41

郑併斌, 范新南, 李敏, 张继. 基于轨迹分段LDA主题模型的视频异常行为检测方法[J]. 计算机应用, 2015, 35(2): 515-518.

ZHENG Bingbin, FAN Xinnan, LI Min, ZHANG Ji. Trajectory segment-based abnormal behavior detection method using LDA model[J]. Journal of Computer Applications, 2015, 35(2): 515-518.

参考文献

[1] POPOOLA O P, WANG K. Video-based abnormal human behavior recognition — a review [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2012, 42(6): 865-878.
[2] BENABBAS Y, IHADDADENE N, DJERABA C. Motion pattern extraction and event detection for automatic visual surveillance [J]. Journal on Image and Video Processing — Special Issue on Advanced Video-based Surveillance, 2011, 2011: Article No. 7.
[3] KWON E, NOH S, JEON M, et al. Scene modeling-based anomaly detection for intelligent transport system [C]//ISMS 2013: Proceedings of the 2013 4th International Conference on Intelligent Systems Modelling & Simulation. Piscataway: IEEE, 2013: 252-257.
[4] ZHU Y, NAYAK N M, ROY-CHOWDHURY A K. Context-aware activity recognition and anomaly detection in video [J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7(1): 91-101.
[5] ZHANG Z, MIAO D, GAO C. Short text classification using latent Dirichlet allocation [J]. Journal of Computer Applications, 2013, 33(6): 1587-1590.(张志飞, 苗夺谦, 高灿. 基于LDA主题模型的短文本分类方法[J]. 计算机应用, 2013, 33(6): 1587-1590.)
[6] BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation [J]. Journal of Machine Learning Research. 2003, 3: 993-1022.
[7] WANG X, MA X, GRIMSON W E L. Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 539-555.
[8] VARADARAJAN J, ODOBEZ J. Topic models for scene analysis and abnormality detection [C]//ICCV Workshops 2009: Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Workshops. Piscataway: IEEE, 2009: 1338-1345.
[9] KWAK S, BYUN H. Detection of dominant flow and abnormal events in surveillance video [J]. Optical Engineering, 2011, 50(2): 027202.
[10] LI J, HOSPEDALES T M, GONG S, et al. Learning rare behaviours [C]//ACCV 2010: Proceedings of the 10th Asian Conference on Computer Vision, LNCS 6493. Berlin: Springer-Verlag, 2011: 293-307.
[11] BAE G T, KWAK S Y, BYUN H R. Motion pattern analysis using partial trajectories for abnormal movement detection in crowded scenes [J]. Electronics Letters. 2013, 49(3): 186-187.
[12] CALDERARA S, HEINEMANN U, PRATI A, et al. Detecting anomalies in people's trajectories using spectral graph analysis [J]. Computer Vision and Image Understanding, 2011, 115(8): 1099-1111.
[13] TUNG F, ZELEK J S, CLAUSI D A. Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance [J]. Image and Vision Computing. 2011, 29(4): 230-240.
[14] LI C, HAN Z, YE Q, et al. Visual abnormal behavior detection based on trajectory sparse reconstruction analysis [J]. Neurocomputing, 2013, 119: 94-100.
[15] LI H, ACHIM A, BULL D. Unsupervised video anomaly detection using feature clustering [J]. IET Signal Processing, 2012, 6(5): 521-533.
[16] LEE J-G, HAN J, LI X. Trajectory outlier detection: A partition-and-detect framework [C]//ICDE 2008: Proceedings of the 2008 IEEE 24th International Conference on Data Engineering. Washington, DC: IEEE Computer Society, 2008:140-149.
[17] HOSPEDALES T M, GONG S, XIANG T. A Markov clustering topic model for mining behaviour in video[C]//ICCV 2009: Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway: IEEE, 2009: 1165-1172.

基于轨迹分段LDA主题模型的视频异常行为检测方法

Trajectory segment-based abnormal behavior detection method using LDA model

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]	胡天杰, 胡文军, 王士同. 分布熵惩罚的支持向量数据描述[J]. 计算机应用, 2021, 41(8): 2212-2218.
[2]	孟凡, 陈广, 王勇, 高阳, 高德群, 贾文龙. 基于多粒度时序结构表示的异常检测算法在储层含油性检测中应用[J]. 计算机应用, 2021, 41(8): 2453-2459.
[3]	李衍志, 范勇, 高琳. 基于形态流的石油钻井水流异常检测[J]. 计算机应用, 2021, 41(6): 1842-1848.
[4]	谢雨, 蒋瑜, 龙超奇. 基于随机子空间的扩展隔离林算法[J]. 计算机应用, 2021, 41(6): 1679-1685.
[5]	姚杰, 程春玲, 韩静, 刘峥. 云工作流中基于多任务时序卷积网络的异常检测方法[J]. 计算机应用, 2021, 41(6): 1701-1708.
[6]	杨丰瑞, 霍娜, 张许红, 韦巍. 基于注意力机制的主题扩展情感对话生成[J]. 计算机应用, 2021, 41(4): 1078-1083.
[7]	杨威亚, 余正涛, 高盛祥, 宋燃. 基于跨语言神经主题模型的汉越新闻话题发现方法[J]. 计算机应用, 2021, 41(10): 2879-2884.
[8]	朱思淼, 魏世伟, 魏思恒, 余敦辉. 基于弹幕情感分析和主题模型的视频推荐算法[J]. 计算机应用, 2021, 41(10): 2813-2819.
[9]	尹春勇, 章荪. 面向短文本情感分类的端到端对抗变分贝叶斯方法[J]. 计算机应用, 2020, 40(9): 2536-2542.
[10]	张晨曦, 唐曙, 唐珂. 迁移学习下的火箭发动机参数异常检测策略[J]. 计算机应用, 2020, 40(9): 2774-2780.
[11]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907.
[12]	王磊. 改进粗糙集属性约简结合K-means聚类的网络入侵检测方法[J]. 计算机应用, 2020, 40(7): 1996-2002.
[13]	胡珉, 白雪, 徐伟, 吴秉键. 多维时间序列异常检测算法综述[J]. 计算机应用, 2020, 40(6): 1553-1564.
[14]	仇媛, 常相茂, 仇倩, 彭程, 苏善婷. 基于长短期记忆网络和滑动窗口的流数据异常检测方法[J]. 计算机应用, 2020, 40(5): 1335-1339.
[15]	霍纬纲, 王慧芳. 基于自编码器和隐马尔可夫模型的时间序列异常检测方法[J]. 计算机应用, 2020, 40(5): 1329-1334.