Abnormal event detection via the analysis of multi-frame optical flow information  

作　　者：Tian WANG Meina QIAO Aichun ZHU Guangcun SHAN Hichem SNOUSSI 

机构地区：[1]School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191,China [2]School of Computer Science and Technology,Nanjing University of Technology,Nanjing 210094,China [3]School of Instrumentation Science and Opto-electronics Engineering,Beihang University,Beijing 100191,China [4]Institute Charles Delaunay-LM2S-UMR STMR 6281 CNRS,University of Technology of Troyes,Troyes 10010,France

出　　处：《Frontiers of Computer Science》2020年第2期304-313,共10页中国计算机科学前沿（英文版）

基　　金：the National Key R&D Program of China(2016YFE0204200);the National Natural Science Foundation of China(Grant Nos.61503017,U1435220);the Fundamental Research Funds for the Central Universities(YWF-14-RSC-102);the Aeronautical Science Foundation of China(2016ZC51022);the ANR AutoFerm project,the Platform CAPSEC funded by Region Champagne-Ardenne and FEDER.

摘　　要：Security surveillance of public scene is closely relevant to routine safety of individual.Under the stimulus of this concern,abnormal event detection is becoming one of the most important tasks in computer vision and video processing.In this paper,we propose a new algorithm to address the visual abnormal detection problem.Our algorithm decouples the problem into a feature descriptor extraction process,followed by an AutoEncoder based network called cascade deep AutoEncoder(CDA).The movement information is represented by a novel descriptor capturing the multi-frame optical flow information.And then,the feature descriptor of the normal samples is fed into the CDA network for training.Finally,the abnormal samples are distinguished by the reconstruction error of the CDA in the testing procedure.We validate the proposed method on several video surveillance datasets.

关 键 词：ABNORMAL EVENT detection MULTI-FRAME optical FLOW CASCADE DEEP autoencoder 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]