Abnormal Crowd Behavior Detection Using Optimized Pyramidal Lucas-Kanade Technique

作     者：G.Rajasekaran J.Raja Sekar 

作者机构：Department of information technologymepco schlenk engineering collegesivakasi626005india Department of computer science and engineeringmepco schlenk engineering collegesivakasi626005india 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第35卷第2期

页      面：2399-2412页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Crowd behavior analysis anomaly detection Motion Information 

摘      要：Abnormal behavior detection is challenging and one of the growing research areas in computer *** main aim of this research work is to focus on panic and escape behavior detections that occur during unexpected/uncertain *** this work,Pyramidal Lucas Kanade algorithm is optimized using EME-HOs to achieve the *** stage,OPLKT-EMEHOs algorithm is used to generate the opticalflow from *** stage,the MIIs opticalflow is applied as input to 3 layer CNN for detect the abnormal crowd *** of Minnesota(UMN)dataset is used to evaluate the proposed *** experi-mental result shows that the proposed method provides better classification accu-racy by comparing with the existing *** method provides 95.78%of precision,90.67%of recall,93.09%of f-measure and accuracy with 91.67%.