Crowd abnormal behavior detection based on motion similar entropy

Fei LI; Ken CHEN; Meng LI; Chunmei GUO

doi:10.11959/j.issn.1000−0801.2017117

您当前的位置：

首页 >

文章列表页 >

Crowd abnormal behavior detection based on motion similar entropy

research and development | 更新时间：2024-06-05

- Crowd abnormal behavior detection based on motion similar entropy
- Telecommunications Science Vol. 33, Issue 5, Pages: 90-98(2017)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000−0801.2017117
  CLC： TP391
- Published Online：2017-05，
  
  Published：15 May 2017
- 稿件说明：
移动端阅览
Fei LI, Ken CHEN, Meng LI, et al. Crowd abnormal behavior detection based on motion similar entropy[J]. Telecommunications science, 2017, 33(5): 90-98.
DOI：

Fei LI, Ken CHEN, Meng LI, et al. Crowd abnormal behavior detection based on motion similar entropy[J]. Telecommunications science, 2017, 33(5): 90-98. DOI： 10.11959/j.issn.1000−0801.2017117.

摘要

实现对人群异常事件的检测是图形处理在智能视频监控领域的重要研究内容。提出了一种基于运动相似性熵（EMS）的人群异常行为检测算法。该算法在对视频图像进行光流计算的基础上，以底层光流块为基本单位获取场景运动信息，根据社会网络模型的概念，提出构建场景的运动网络模型（MNM），完成对场景粒子运动相似性的划分，并在时间域上计算MNM的粒子分布熵值EMS，最后将得到的图像熵与设置合理的阈值相比，判断异常行为是否发生。实验证明，该算法可有效检测异常行为，与其他经典检测算法相比有较大优势。

Abstract

It is an important research content of graphic processing in the field of intelligent video surveillance to detect abnormal events.An algorithm based on entropy of motion similarity (EMS) to detect abnormal behavior was proposed.Based on the optical flow algorithm

taking the bottom flow block as the basic unit to get the scene motion information

according to the concept of social network model

the construction scene of the motion network model (MNM) was proposed

the division of the scene particles motion similarity was completed

and the distribution EMS of MNM was calculated in the time domain.Finally

the obtained image entropy was compared with the reasonable threshold

to determine whether abnormal behavior occured.Experimental results indicate that the proposed algo-rithm can detect abnormal behavior effectively and show promising performance while comparing with the state of the art methods.

关键词

Keywords

references

WANG W H , WANG X J . Research on the human motion anal-ysis and key technology based on intelligent video surveillance [J ] . Sensors＆Transducers , 2013 , 161 ( 12 ): 98 - 106 .

ZHANG J , CHU Y X . Study on anomaly detection in crowd scene [C ] // 4th International Conference on Mechatronics,Mate-rials,Chemistry and Computer Engineering (ICMMCCE 2015),December 12−13,2015,Xi'an,China.[S.l.:s.n.] , 2015 : 604 - 609 .

WANG H , FU R Q , LI N N , et al . Anomaly detection in crowds assisted by scene perspective projection correction [C ] // IEEE International Conference on Information Science and Technol-ogy,April 26-28,2014,Shenzhen,China , New Jersey : IEEE Press , 2014 : 686 - 689 .

PATHAN S S , ALHAMADI A , MICHAELIS B . Incorporating social entropy for crowd behavior detection using SVM [J ] . Lecture Notes in Computer Science , 2010 ( 6453 ): 153 - 162 .

REN W Y , LI G H , CHEN J , et al . Abnormal crowd behavior detection using behavior entropy model [J ] . Wavelet Analysis and Pattern Recognition , 2012 : 212 - 221 .

SUSAN S , HANMANDLU M . Unsupervised detection of non-linearity in motion using weighted average of non-extensive en-tropies [J ] . Signal,Image and Video Processing , 2015 , 9 ( 3 ): 511 - 525 .

潘磊 . 基于图像熵的密集人群异常事件实时检测方法 [J ] . 计算机科学与探索， 2016 , 10 ( 7 ): 1044 - 1050 .

PAN L . Real-time detection method of abnormal event in crowds [J ] . Computer Science and Exploration , 2016 , 10 ( 7 ): 1044 - 1050 .

CHAKER R , AGHBARI Z A , JUNEJO I N . Social network model for crowd anomaly detection and localization [J ] . Pattern Recognition , 2016 ( 61 ): 266 - 281 .

BAUER N , PATHIRANA P , HODGSON P . Robust optical flow with combined lucas-kanade/horn-schunck and automatic neighborhood selection [C ] // International Conference on Infor-mation and Automation,December 15−17,2006,Hong Kong,China . New Jersey : IEEE Press , 2006 : 378 - 383 .

WANG D , ABDELZAHER T , KAPLAN L . Chapter 8-understanding the social network [M ] . Amsterdam:Social Sensing Elsevier Inc , 2015 : 129 - 151 .

LI LY , LI D R . Fuzzy entropy image segmentation based on particle swarm optimization [J ] . Progress in Natural Science:Materials International , 2008 , 18 ( 9 ): 1167 - 1171 .

劳义 . 我国男子百米技术差异分析——以亚运会男子100米冠军劳义和世界纪录保持者博尔特为比较案例 [D ] . 南昌：江西师范大学， 2015 > .

LAO Y . Analysis of the different between the men's 100 meter technology in China—in the asian games in the men's 100 me-ters champion of LAO Yi and world record holder BOLT as a comparison case [D ] . Nanchang:Jiangxi Normal University , 2015 .

科学网 . 空中漫步助力宇航服设计 [J ] . 科技创新导报， 2014 ( 30 ): 2 .

Science network . Space walk booster space suit design [J ] . Science and Technology Innovation Herald , 2014 ( 30 ): 2 .

周洁，郭立君，张荣 . 基于粒子熵值的异常行为检测 [J ] . 无线电通信技术， 2015 , 41 ( 3 ): 66 - 68 .

ZHOU J , GUO L J , ZHANG R . Abnormal behavior detection based on particle entropy [J ] . Radio communication technology , 2015 , 41 ( 3 ): 66 - 68 .

University of minnesota . Unusual crowd activity dataset of university of minnesota [EB/OL ] .( 2006 - 10 - 25 )[ 2015 - 08 - 29 ] . http://mha.cs.umn.edu/movies/crowdactivity-all.avi http://mha.cs.umn.edu/movies/crowdactivity-all.avi .

OZTURK A , ARSLAN A . Classification of transcranial doppler signals using their chaotic invariant measures [J ] . Computer Methods＆Programs in Biomedicine , 2007 , 86 ( 2 ): 171 - 180 .

MEHRAN R , OYAMA A , SHAH M . Abnormal crowd beha-viordetection using social force model [C ] // IEEE Conference on Computer Vision and Pattern Recognition,June 20−25,2009,Miami,USA . New Jersey : IEEE Press , 2009 : 935 - 942 .

王汗三 , 陈杰 . 稀疏重构算法 [J ] . 电子科技， 2013 , 26 ( 5 ): 106 - 108 .

WANG H S , CHEN J . Sparse reconstruction slgorithm [J ] . Elec-tronic Science＆Technology , 2013 , 26 ( 5 ): 106 - 108 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰