利用角点历史信息的异常行为识别算法

J4 ›› 2014, Vol. 36 ›› Issue (06): 1127-1131.

利用角点历史信息的异常行为识别算法

刘燕1,2，高云1

（1.中国海洋大学信息科学与工程学院，山东青岛 266071；2.潍坊科技学院中印计算机软件学院，山东寿光 262700）

收稿日期:2013-01-09 修回日期:2013-04-08 出版日期:2014-06-25 发布日期:2014-06-25

Abnormal behavior recognition based on corner motion history

LIU Yan1,2，GAO Yun1

（1.College of Information Science and Engineering,Ocean University of China,Qingdao 266071;
2.College of SinoIndian Computer Software,Weifang Institute of Science and Technology,Shouguang 262700,China）

Received:2013-01-09 Revised:2013-04-08 Online:2014-06-25 Published:2014-06-25

摘要/Abstract

摘要：

针对视频监控场景中的异常行为事件，如突然的奔跑、人群的异常聚集等现象，提出一种利用角点运动历史图策略的行为识别算法，即首先通过角点提取算法进行场景角点提取；然后通过时间累积获取角点的历史图，通过角点历史图将场景中的角点划分为静态角点和动态角点；最后通过动态角点分析完成监控场景异常行为分析识别。新算法充分利用了图像的时空信息，并且克服了场景光照影响，增强了异常行为检测与识别的准确性。通过真实场景实验可以看出，新算法能够对不同监控场景的异常行为进行准确检测，并且其检测速度快，满足实际应用需求。

关键词: 角点检测, 运动历史图, 异常行为, 滑动窗口

Abstract:

In video surveillance scenes, the abnormal events, such as a sudden run, the crowd abnormal aggregation phenomenon, are studied. A corner motion history image strategy is used for behavior recognition. Firstly, the corner extraction algorithm is used as scene corner extraction. Secondly, through time accumulated, the corner historical image is constructed. And all corners are divided into static and dynamic corner point. Finally, through the dynamic corner analysis, the abnormal behavior is under analysis and recognition. The new algorithm makes full use of image information, overcomes the illumination effect, and enhances the abnormal behavior detection and recognition accuracy. Through the real scene experiments show that the new algorithm can be used for different scenes. It can get accurate detection for abnormal behavior, and the detection speed meets the needs of practical application.

Key words: corner detection;motion history image (MHI);abnormal behavior;slide window

刘燕1,2，高云1. 利用角点历史信息的异常行为识别算法[J]. J4, 2014, 36(06): 1127-1131.

LIU Yan1,2，GAO Yun1. Abnormal behavior recognition based on corner motion history [J]. J4, 2014, 36(06): 1127-1131.

参考文献

［1］Datta A, Shah M, da Vitoria, et al. Persononperson violence detection in video data［C］∥Proc of the 16th International Conference on Pattern Recognition, 2002:433438.
［2］Park S, Aggarwal J K. A hierarchical Bayesian network for event recognition of human actions and interactions［J］. Multimedia Systems, 2004,10(2):164179.
［3］Mecocci A, Micheli F. Realtime recognition of violent acts in monocular colour video sequences［C］∥Signal Processing Applications for Public Security and Forensics, 2007:14.
［4］de Souza F D M, Chavez G C, do Valle E A, et al. Violence detection in video using spatiotemporal features［C］∥Graphics, Patterns and Images (SIBGRAPI), 2010:224230.
［5］Lin Jian,Sun Yi,Wang Weiqiang.Violence detection in movies with auditory and visual cues［C］∥Proc of 2010 International Conference on Computational Intelligence and Security, 2010:561565.
［6］Moeslund T B, Hilton A, Krüger V. A survey of advances in visionbased human motion capture and analysis［J］. Computer Vision and Image Understanding, 2006, 104(23):90126.
［7］Davis J W, Bobick A F. The representation and recognition of human movement using temporal templates［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 1997: 928934.
［8］Rosten E,Drummond T.Fusing points and lines for high performance tracking［C］∥Proc of the 10th International Conference on Computer Vision, 2005:15081515.
［9］CAVIAR: EU funded project, IST 2001 37540［EB/OL］.［20041211］.http://homepages.inf.ed.ac.uk/rbf/CAVIAR/).
［10］Blunsden S, Andrade E, Laghaee A, et al. Behave interactions test case scenarios, epsrc project gr/s98146［EB/OL］.［20110505］.http://groups.inf.ed.ac.uk/vision/behavedata/interactions/index.html.

[1]	马驰远, 雷国庆. 一种CDC信号滑动窗口时序分析方法[J]. 计算机工程与科学, 2022, 44(02): 214-219.
[2]	张寅, 蔡旭阳, 许倩倩, 闫钧华, 苏恺, 张琨 . 融合时空上下文的复杂背景下多运动目标检测[J]. 计算机工程与科学, 2020, 42(12): 2186-2192.
[3]	倪尧，鲍宇. 基于目标轮廓几何特征的电容元件定位方法[J]. 计算机工程与科学, 2017, 39(08): 1476-1482.
[4]	何金辉1，薛月菊1，毛亮1，李鸿生2，林焕凯1，张晓1. 基于角点光流与SVM的增氧机工作状态检测[J]. J4, 2015, 37(08): 1566-1572.
[5]	李伟,肖建青. 基于流水化和滑动窗口结构的低功耗指令Cache设计[J]. J4, 2015, 37(06): 1037-1042.
[6]	张友桥1，周武能1，申晔2，刘玉军2. 椭圆曲线密码中抗功耗分析攻击的标量乘改进方案[J]. J4, 2014, 36(04): 644-648.
[7]	谢国波，陈云华，张灵，丁伍洋. 基于嘴巴特征点曲线拟合的哈欠检测[J]. J4, 2014, 36(04): 731-736.
[8]	石红波1，黄山1，2，张洪斌2，田坤3. 基于综合背景提取方法与阴影抑制的智能监控系统[J]. J4, 2012, 34(12): 98-104.
[9]	何丰,胡俊,马浩,吴艳秋. 基于弧思想的改进的角点检测算法[J]. J4, 2011, 33(2): 108-111.
[10]	周德龙,刘〓迎,吴巾一. 基于二维Gabor小波变换的角点匹配算法[J]. J4, 2011, 33(12): 61-65.
[11]	邢长征,张国凯. 基于自适应网格划分的数据流聚类算法[J]. J4, 2011, 33(10): 149-153.
[12]	常战芳1，班晓娟1，刘旭1，周瑜1，何新波2. 基于多源数据融合的注射坯密度分布控制算法[J]. J4, 2010, 32(9): 142-144.
[13]	赵小琴,王玉玫. 基于图像分析的军队标号绘制自动化测试方法研究[J]. J4, 2010, 32(11): 66-70.
[14]	余建军秦本涛蒋晓丹. 基于基因表达式编程的网格主机负载时间序列分析[J]. J4, 2008, 30(8): 105-107.
[15]	吴泉源. 计算机“2000年问题”及其日期处理方法的研究[J]. J4, 1997, 19(4): 73-77.