计算机科学

计算机科学 ›› 2018, Vol. 45 ›› Issue (9): 314-319.doi: 10.11896／j.issn.1002-137X.2018.09.053

• 图形图像与模式识别 • 上一篇    

基于群组运动模式变化分析的群体骚乱行为检测

黄金国1, 刘涛1, 周先春2, 严锡君3   

  1. 江苏开放大学信息与机电工程学院 南京2100171
    南京信息工程大学电子与信息工程学院 南京2100172
    河海大学计算机与信息学院 南京2100983
  • 收稿日期:2017-08-30 出版日期:2018-09-20 发布日期:2018-10-10
  • 作者简介:黄金国(1976-),男,硕士,副教授,主要研究方向为数据挖掘技术;刘 涛(1980-),男,硕士,副教授,主要研究方向为数据挖掘、无线传感网络等;周先春(1974-),男,博士,副教授,主要研究方向为信号与信息处理;严锡君(1963-),男,博士,副教授,主要研究方向为数据挖掘与无线传感器网络。
  • 基金资助:
    本文受国家自然科学基金项目(11202106,61201444),江苏省高校自然科学研究面上基金项目(15KJD520003)资助。

Detection for Group Riot Activity Based on Change Analysis of Group Motion Pattern

HUANG Jin-guo1, LIU Tao1, ZHOU Xian-chun2, YAN Xi-jun3   

  1. School of Information Mechanical and Electrical Engineering,Jiangsu Open University,Nanjing 210017,China1
    School of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210017,China2
    College of Computer and Information,Hohai University,Nanjing 210098,China3
  • Received:2017-08-30 Online:2018-09-20 Published:2018-10-10

PDF (PC)

1055

摘要： 群体骚乱行为对社会公共安全的危害极大,是智能视频监控防范的重点之一。针对现有群体骚乱行为检测算法运算效率和检测正确率均较低的问题,提出了一种基于群组运动模式变化分析的行为检测算法。该方法提取前景像素点的光流特征作为行为分析的依据,采用K均值聚类和贝叶斯准则实现场景中不同人群的群组划分。在此基础上,分析场景中所有群组的运动模式变化,构建最大变化因子,计算最大变化因子变化量,检测群体骚乱行为。实验结果表明,采用所提方法检测群体骚乱行为的虚警率和漏警率均较低,平均检测耗时短。

关键词: K均值, 光流, 群体行为, 行为检测, 运动模式

Abstract: Group riot activity is the main precaution point of intelligent video surveillance because of its large hazards for social public safety.In view of the problem of low efficiency and low detection accuracy of the existing group riot activity detection algorithms,an activity detection algorithm for group riot activity based on change analysis of group motion pattern was proposed.This method extracts the optical flow features of foreground pixels as the basis of the activity analysis,and uses K-means clustering and Bayesian criterion to realize the grouping division of different groups in the scene.On this basis,it analyzes the changes in motion patterns of all groups,builds the maximum change factors,and computes the variation of the maximum change factors to detect the group riot activities.The experimental results show that this method used for detecting group riot activities has low false-alarm rate and miss-alarm rate and less average detection time.

Key words: Activity detection, Group activity, K mean, Motion pattern, Optical flow

中图分类号: 

  • TP391
[1]SHAN Y H,ZHANG Z,HUANG K Q.The study of human behavior recognition visual review,current situation and Prospect of [J].Computer Research and Development,2016,53(1):93-112.(in Chinese)
单言虎,张彰,黄凯奇.人的视觉行为识别研究回顾、现状及展望[J].计算机研究与发展,2016,53(1):93-112.
[2]OKEYO G,CHEN L,WANG H,et al.Dynamic sensor data segmentation for real-time knowledge-driven activity recognition[J].Pervasive & Mobile Computing,2014,10(2):155-172.
[3]XIA L,AGGARWAL J K.Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera[J].Computer Vision & Pattern Recognition,2013,9(4):2834-2841.
[4]BULLING A,BLANKE U,SCHIELE B.A tutorial on human
activity recognition using body-worn inertial sensors[J].ACM Computing Surveys(CSUR),2014,46(3):1-33.
[5]AGGARWAL J K,XIA L.Human activity recognition from 3D data:A review[J].Pattern Recognition Letters,2014,48(1):70-80.
[6]SHOAIB M,BOSCH S,INCEL O D,et al.A Survey of Online Activity Recognition Using Mobile Phones[J].Sensors,2015,15(1):2059-2069.
[7]LI G,LIN W,ZHANG S,et al.A New Network-Based Algorithm for Human Group Activity Recognition in Videos[C]∥International Conference on Multimedia Modeling.Springer Berlin Heidelberg,2013:163-173.
[8]DENG Z,VAHDAT A,HU H,et al.Structure Inference Ma-chines:Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition[C]∥Computer Vision and Pattern Recognition.IEEE,2016:4772-4781.
[9]HE C Y,WANG P,ZHANG X H,et al.Detection of abnormal behavior in small and medium population based on intelligent surveillance [J].Computer Application,2016,36(6):1724-1729.(in Chinese)
何传阳,王平,张晓华,等.基于智能监控的中小人群异常行为检测[J].计算机应用,2016,36(6):1724-1729.
[10]SONG D N,WANG P,ZHANG X H,et al.Detection of abnormal behavior in small and medium groups based on video surveillance [J].Computer Engineering and Design,2016,37(9):2507-2514.(in Chinese)
宋丹妮,王平,张晓华,等.基于视频监控的中小群体异常行为检测[J].计算机工程与设计,2016,37(9):2507-2514.
[11]LIN J,LIN L.Detection method of group disturbance behavior based on optical flow modulus change frequency [J].Computer Science,2016,43(5):283-287.(in Chinese)
林杰,林拉.基于光流模值变化频率的群体骚乱行为检测方法[J].计算机科学,2016,43(5):283-287.
[12]KRYJAK T,GORGON M.Real-time implementation of the ViBe foreground object segmentation algorithm[C]∥Computer Science and Information Systems.IEEE,2013:591-596.
[13]CEBECI Z,YI Z,LDI F.Comparison of K-means and fuzzy C-means algorithms on different cluster structures[J].Journal of Agricultural Informatics,2015,6(3):13-23.
[1] 冷佳旭, 谭明圮, 胡波, 高新波.
基于隐式视角转换的视频异常检测
Video Anomaly Detection Based on Implicit View Transformation
计算机科学, 2022, 49(2): 142-148. https://doi.org/10.11896/jsjkx.210900266
[2] 徐涛, 田崇阳, 刘才华.
基于深度学习的人群异常行为检测综述
Deep Learning for Abnormal Crowd Behavior Detection:A Review
计算机科学, 2021, 48(9): 125-134. https://doi.org/10.11896/jsjkx.201100015
[3] 孟祥玉, 薛昕惟, 李汶霖, 王祎.
基于运动估计与时空结合的多帧融合去雨网络
Motion-estimation Based Space-temporal Feature Aggregation Network for Multi-frames Rain Removal
计算机科学, 2021, 48(5): 170-176. https://doi.org/10.11896/jsjkx.210100104
[4] 王昆仑, 刘文璨, 何小海, 卿粼波, 吴晓红.
一种用于异常行为检测的运动特征描述子
Motion Feature Descriptor for Abnormal Behavior Detection
计算机科学, 2020, 47(4): 119-124. https://doi.org/10.11896/jsjkx.190300392
[5] 饶梦,苗夺谦,罗晟.
一种粗糙不确定的图像分割方法
Rough Uncertain Image Segmentation Method
计算机科学, 2020, 47(2): 72-75. https://doi.org/10.11896/jsjkx.190500177
[6] 马露, 裴伟, 朱永英, 王春立, 王鹏乾.
基于深度学习的跌倒行为识别
Fall Action Recognition Based on Deep Learning
计算机科学, 2019, 46(9): 106-112. https://doi.org/10.11896/j.issn.1002-137X.2019.09.014
[7] 王正宁, 周阳, 吕侠, 曾凡伟, 张翔, 张锋军.
一种基于2D和3D联合信息的改进MDP跟踪算法
Improved MDP Tracking Method by Combining 2D and 3D Information
计算机科学, 2019, 46(3): 97-102. https://doi.org/10.11896/j.issn.1002-137X.2019.03.013
[8] 徐登, 黄晓东.
基于改进双流卷积网络的火灾图像特征提取方法
Fire Images Features Extraction Based on Improved Two-stream Convolution Network
计算机科学, 2019, 46(11): 291-296. https://doi.org/10.11896/jsjkx.180901640
[9] 刘璐, 赵国庆.
多媒体系统群体行为的雾计算智能激励机制
Intelligent Incentive Mechanism for Fog Computing-based Multimedia Systems with Swarming Behavior
计算机科学, 2019, 46(11): 94-99. https://doi.org/10.11896/jsjkx.181001975
[10] 胡燕花,唐鹏,金炜东,何正伟.
铁路视频序列的FOE的估计
Estimation of FOE for Railway Video Sequences
计算机科学, 2018, 45(7): 226-229. https://doi.org/10.11896／j.issn.1002-137X.2018.07.039
[11] 郝俊生,李冰锋,陈曦,高文娟.
基于Android平台的高校网络订餐系统的设计与实现
Design and Implementation of Network Subscription System Based on Android Platform
计算机科学, 2018, 45(6A): 591-594.
[12] 郁湧,康庆怡,陈长赓,阚世林,骆永军.
基于内聚度和耦合度的二分K均值方法
Bisecting K-means Clustering Method Based on Cohesion and Coupling
计算机科学, 2018, 45(6A): 460-464.
[13] 陈诚,常侃,莫彩网,李天亦,覃团发.
基于非局部均值和总变分最小化的单视频超分辨率算法
Single Video Super-resolution Algorithm Based on Non-local Means and Total Variation Minimization
计算机科学, 2018, 45(3): 263-267. https://doi.org/10.11896/j.issn.1002-137X.2018.03.042
[14] 刘国奇,李晨静.
基于贝塞尔滤波的水平集正则化图像分割方法
Image Segmentation Method of Level Set Regularization Based on Bessel Filter
计算机科学, 2018, 45(3): 283-287. https://doi.org/10.11896/j.issn.1002-137X.2018.03.046
[15] 牛雷,孙忠林.
PCA-AKM算法及其在入侵检测中的应用
PCA-AKM Algorithm and Its Application in Intrusion Detection System
计算机科学, 2018, 45(2): 226-230. https://doi.org/10.11896/j.issn.1002-137X.2018.02.039
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发