An improved method based on LHMM for gathering abnormal event realtime detection

DENG De-ying 1; TANG Xiao-hui 2

doi:10.13873/j.1000-97872012.07.016

Chinese

您当前的位置：

首页 >

文章列表页 >

An improved method based on LHMM for gathering abnormal event realtime detection

更新时间：2025-09-11

- An improved method based on LHMM for gathering abnormal event realtime detection
- Vol. 31, Issue 7, Pages: 39-41(2012)
- 作者机构：
  
  1. 桂林电子科技大学信息与通信学院
  2. 桂林航天工业高等专科学校电子工程系
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872012.07.016
  CLC： TN911.73
- Published：2012
- 稿件说明：
移动端阅览
[1]邓德迎,唐晓辉.基于LHMM的聚众异常事件实时检测改进方法[J].传感器与微系统,2012,31(07):39-41.

DENG De-ying 1, TANG Xiao-hui 2. An improved method based on LHMM for gathering abnormal event realtime detection[J]. 2012, 31(7): 39-41.
[1]邓德迎,唐晓辉.基于LHMM的聚众异常事件实时检测改进方法[J].传感器与微系统,2012,31(07):39-41. DOI： 10.13873/j.1000-97872012.07.016.

DENG De-ying 1, TANG Xiao-hui 2. An improved method based on LHMM for gathering abnormal event realtime detection[J]. 2012, 31(7): 39-41. DOI： 10.13873/j.1000-97872012.07.016.

摘要

提出了一种改进的分层隐马尔科夫模型（LHMM）结合熵值的聚众异常事件实时检测方法。使用直方图均衡化对视频帧做预处理

增加图像质量;以分块区域中的人数和总速度作为观察值分两层训练出聚众事件的LHMM。当观察值序列与模型的相似度大于设定阈值时

利用光流法计算该帧熵值

当熵值大于设定阈值时

则认为聚众事件发生;否则

为非聚众事件

继续下一帧的处理。大量实验结果表明:改进的方法具有较高的识别率、较好的鲁棒性和高的处理速度

并且应用环境更广。

Abstract

An improved layered hidden Markov model（LHMM） and entropy value of real-time detection method for gathering abnormal event detection is presented.The video frame is preprocessed using histogram equalization to increase image quality;the number of people and the total speed of people in block area as the observed values

then gathering event’s LHMM in two levels is trained.When the similarity between observation sequences and the model is greater than certain threshold

then calculate the entropy of the frame by using optical flow method.When the entropy value is greater than the certain threshold

a gathering event is judged to happen;otherwise

it is not a gathering event and continues to process next frame.A large number of experimental results show that the proposed method has higher recognition rate

better robustness and high processing speed and wider applications.

关键词

Keywords

references

LHMM熵的聚众事件实时检测 [J]. 欧阳宁,宁瑞芳,莫建文,张彤,刘丽群. 计算机工程 . 2011(20)

基于分层隐马尔科夫模型的聚众事件实时检测 [D]. 王臻. 桂林电子科技大学 2010

图像工程[M]. 清华大学出版社 , 章毓晋编著, 2006

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image haze removal algorithm based on histogram equalization and dark channel prior

Detection of approximately duplicated records based on entropy feature selection grouping clustering

Game fusion modeling based on Bayes network

Method of fusion for multi-sensor data based on entropy

Related Author

ZHANG Bao-shan

YANG Yan

CHEN Gao-ke

ZHOU Jie

ZHANG Ping1

DANG Xuan-ju1

CHEN Hao2

YANG Wen-lei2

Related Institution

School of Electronic and Information Engineering, Lanzhou Jiaotong University

School of Electronic Engineering and Automation,Guilin University of Electronic Technology

School of Computer Science and Engineering,Guilin University of Electronic Technology

School of Electrical and Information Engineering,South China University ofTechnology

College of Physics & Electronic Engineering,Guangzhou University

⁰