Video-based pedestrian grouping model considering longspan space in a big hall

查看全文 作　　者：Rongyong [1]Zhao;Yan [1]Wang;Ping [1]Jia;Cuiling [1]Li;Daheng [1]Dong;Yunlong [1]Ma 机构地区：[1]College of Electronic and Information Engineering,Tongji University,Shanghai,201804,China 出　　处：《Journal of Management Science and Engineering》索引2023年第8卷第3期,共15页 基　　金：support of the National Natural Science Foundation of China(No.72074170). 摘　　要：Pedestrian group detection is a challenging but significant issue in pedestrian flow control and public safety management.To address the issue that most conventional pedestrian grouping models(PGMs)can only identify a pedestrian group at a limited distance of less than 2 m,this study extended the pedestrian distance constraint of conventional PGMs with a reconstruction of the normal group detection criterion and development of a novelgroup detection criterion suitable for long-span space.To measure the movement behaviorsimilarity with normal distance,five necessary constraints:velocity difference,moving direction offset,distance limitation,distance fluctuation,and group-keeping duration were studied quantitatively to form the criterion to detect normal groups.Meanwhile,a long-span group detection criterion was proposed with extended distance and direction con-sistency constraints.Therefore,this study proposed an improved PGM that considers long-span spaces(PGMLS).In the PGMLS workflow,the MMTrack algorithm was used to obtainpedestrian trajectories.A difference measurement method based on sequential pattern analysis(SPA)was adopted to analyze the velocity similarity of pedestrians.To validate the proposed grouping model,experiments based on pedestrian movement videos in the exit hall of the Shanghai Hongqiao International Airport were conducted.The results indicate that the proposed model can detect both normal and widely separated pedestrian groups,with a long span range of 2-12 m. 关 键 词：Pedestrian grouping Long-span space Video tracking algorithm Sequential pattern analysis Safety management