基于自反馈最优子类挖掘的视频异常检测算法  

Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining

作　　者：侯春萍[1] 赵春月 王致芃 HOU Chun-ping;ZHAO Chun-yue;WANG Zhi-peng(School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China)

机构地区：[1]天津大学电气与信息工程学院,天津300072

出　　处：《计算机科学》2021年第7期199-205,共7页Computer Science

基　　金：国际合作与交流NFSC项目(61520106002);国家自然科学基金(61731003)。

摘　　要：视频异常检测算法是视频处理领域的研究热点之一,用于检测视频中是否包含异常事件。然而,由于没有异常样本参与训练过程,且异常样本与正常样本之间存在一定程度的相似性,因此很难设计出一种有辨识力的异常检测模型。为了解决上述问题,文中首先提出了一种基于相似度保持和样本恢复的特征选择方法,该方法能够保留正常样本的相似关系,进而可以学习到能够准确描述正常事件的特征。其次,将异常事件检测任务转化为分类任务,并提出了一种自反馈最优子类挖掘方法来获得最优分类器。如果一个测试样本被所有分类器判断为异常,则该样本最终将被判定为异常。在公共视频数据集(Avenue数据集、UCSD Ped2数据集)上进行的大量实验的结果表明,所提异常事件检测算法可以取得很好的结果。Video anomaly detection algorithm is one of the hot issues in the field of video processing,and it is used to detect whether an abnormal event is contained in the video.However,since abnormal samples are not involved in the training process,and there is a certain degree of similarity between abnormal samples and normal samples,it is difficult to design an abnormal detection model with discrimination.In order to solve the above problems,firstly,this paper proposes a feature selection method based on similarity preservation and sample recovery.This method can retain the similarity of normal samples,and then learn features that can accurately describe normal events.Secondly,it formalizes the abnormal event detection as classification problem,and proposes a self-feedback optimal subclass mining method to find optimal classifier.The sample will be labeled as anomaly if all classifiers label it as anomaly.Extensive experiments on public video surveillance datasets(i.e.Avenue Dataset and UCSD Ped2 Dataset)demonstrate that the proposed abnormal event detection method can achieve good results.

关 键 词：视频异常事件检测 特征选择 自反馈 最优子类挖掘 一类支持向量机 

分 类 号：TN911.73[电子电信—通信与信息系统]