Abnormal Event Detection Based on Deep Learning

WEN Jia; WANG Hong-jun; DENG Jia; LIU Peng-fei

doi:10.3969/j.issn.0372-2112.2020.02.013

您当前的位置：

首页 >

文章列表页 >

Abnormal Event Detection Based on Deep Learning

更新时间：2025-07-16

- Abnormal Event Detection Based on Deep Learning
- Acta Electronica Sinica Vol. 48, Issue 2, Pages: 308-313(2020)
- 作者机构：
  
  1. 燕山大学信息科学与工程学院,河北,秦皇岛,066004
  2. 河北省计算机虚拟技术与系统集成重点实验室,河北,秦皇岛,066004
  3. 河北省软件工程国家重点实验室,河北,秦皇岛,066004
  4. 燕山大学信息科学与工程学院,河北,秦皇岛,066004
  5. 河北省计算机虚拟技术与系统集成重点实验室,河北,秦皇岛,066004
  6. 河北省软件工程国家重点实验室,河北,秦皇岛,066004
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2020.02.013
  CLC： TP389.1
- Published Online：25 February 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
WEN Jia, WANG Hong-jun, DENG Jia, et al. Abnormal Event Detection Based on Deep Learning[J]. Acta Electronica Sinica, 2020, 48(2): 308-313.
DOI：

WEN Jia, WANG Hong-jun, DENG Jia, et al. Abnormal Event Detection Based on Deep Learning[J]. Acta Electronica Sinica, 2020, 48(2): 308-313. DOI： 10.3969/j.issn.0372-2112.2020.02.013.

摘要

面对复杂场景下异常事件检测的准确率偏低的情况，本文提出一种基于深度学习的异常事件检测方法，并将此方法扩展为异常事件分类方法.利用神经网络模型提取特征，将群体发散聚集事件，群体密集聚集事件，群体逃散事件和追赶事件这4种异常事件进行检测和分类.通过PKU-SVD-B测试集对训练出来的模型进行测试实验，并在UMN数据集上与几种方法做了对比实验，验证了本文提出的基于深度学习的异常事件检测算法，在适应多种不同场景的前提下，对多种异常事件检测的准确率很高，表明训练出来的模型对异常事件检测具有极强的泛化能力.

Abstract

Faced with low accuracy of abnormal event detection in complex scenarios

this paper proposes an abnormal event detection based on deep learning in various public scenes and multiple types of anomalies

and the method has been extended to an abnormal event classification method. The neural network model is used to extract features

and the four kinds of abnormal events

such as group divergence aggregation events

group intensive aggregation events

group escape events and catch-up events

are detected and classified. Test the trained model with PKU-SVD-B test set

compared with various methods on the UMN datasets

and verify the algorithm of abnormal event detection based on deep learning proposed in this paper. Under the premise of adapting to different scenarios

various abnormal events are detected. The high accuracy rate indicates that the trained model has strong ability to generalize abnormal event detection.

关键词

Keywords

references

Views

316

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Survey of Object Detection Based on Deep Learning

MalMKNet: A Multi-Scale Convolutional Neural Network Used for Malware Classification

A Survey of Research and Application of Small Object Detection Based on Deep Learning

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

Related Author

LUO Hui-lan

CHEN Hong-kun

ZHANG Dan-dan

SONG Ya-fei

LIU Shu

SONG Ya-fei

LIU Ying

LIU Hong-yan

Related Institution

School of Information Engineering, Jiangxi University of Science and Technology

Institute of Air Defense and Anti-missile， Air Force Engineering University

Key Laboratory of Electronic Information Application Technology for Scene Investigation, Ministry of Public Security

International Joint Research Center for Wireless Communication and Information Processing,,, Shaanxi

Center for Image and Information Processing, Xi'an University of Posts and Telecommunications

⁰