摘要
监控视频在社会安全领域具有重要应用。该文对经典和新兴的监控视频异常检测算法进行分类和总结。首先,依据算法的3个属性,算法的发展阶段、算法的模型类型、算法的异常判别标准,将算法分类并逐类概述。然后,将不同类别的算法进行关联对比,分析不同模型的优缺点以及聚类判别与重构判别在不同发展阶段的特点。最后,提炼了领域内常用的模型假设与相关知识、汇总了不同算法的异常检测效果,并对未来的研究方向进行了探讨和展望。
Surveillance videos are important for maintaining social welfare. This paper classifies and summarizes the traditional and advanced video anomaly detection algorithms. First, the algorithms are classified into different classes according to their development stages, model categories and detection criteria and then they are summarized by class. Then, the advantages and the disadvantages of the different algorithms are identified by comparing the algorithms belonging to different classes. This paper specifically analyses the characteristics of the cluster criterion and the reconstruction criterion in different development stages. Finally, this paper identifies the commonly used model assumptions and the domain knowledge and summarizes the accuracies of the various algorithms. Future research directions are also discussed.
作者
王志国
章毓晋
WANG Zhiguo;ZHANG Yujin(Image Engineering Laboratory,Department of Electronic Engineering,Tsinghua University,Beijing 100084,China)
出处
《清华大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2020年第6期518-529,共12页
Journal of Tsinghua University(Science and Technology)
基金
国家自然科学基金项目(U1636124,61673234)。
关键词
监控视频
异常检测
深度学习
机器学习
算法对比
surveillance video
anomaly detection
deep learning
machine learning
algorithm comparison