Critical Situation Monitoring at Large Scale Events from Airborne Video Based Crowd Dynamics Analysis

被引:5
作者
Almer, Alexander [1 ]
Perko, Roland [1 ]
Schrom-Feiertag, Helmut [2 ]
Schnabel, Thomas [1 ]
Paletta, Lucas [1 ]
机构
[1] Joanneum Res Forsch Gesell mbH, Steyrergasse 17, A-8010 Graz, Austria
[2] AIT Austrian Inst Technol GmbH, Giefinggasse 2, A-1210 Vienna, Austria
来源
GEOSPATIAL DATA IN A CHANGING WORLD: SELECTED PAPERS OF THE 19TH AGILE CONFERENCE ON GEOGRAPHIC INFORMATION SCIENCE | 2016年
关键词
Airborne event monitoring; Automated situation awareness; Video based crowd dynamics analysis; Crowd management; Decision support;
D O I
10.1007/978-3-319-33783-8_20
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Comprehensive monitoring of movement behaviour and raising dynamics in crowds allow an early detection and prediction of critical situations that may arise at large-scale events. This work presents a video based airborne monitoring system enabling the automated analysis of crowd dynamics and to derive potentially critical situations. The results can be used to prevent critical situations by supporting security staff to control the crowd dynamics early enough. This approach enables preventing upraise of panic behaviour by automated early identification of hazard zones and offering a reliable basis for early intervention by security forces. This approach allows the surveillance and analysis of large scale monitored areas of interest and raising specific alarms at the management and control system in case of potentially critical situations. The integrated modules extend classical mission management by providing essential decision support possibilities for assessing the situation and managing security and emergency crews on site within short time frames.
引用
收藏
页码:351 / 368
页数:18
相关论文
共 15 条
[1]  
[Anonymous], PHOTOGRAMMETRY GEOME
[2]  
Cortes C., 1995, Machine learning, DOI [DOI 10.1023/A:1022627411411, DOI 10.1007/BF00994018, 10.1007/BF00994018]
[3]  
Cristiani E, 2014, MS A MOD SIMUL, P1, DOI 10.1007/978-3-319-06620-2
[4]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[5]   Object Detection with Discriminatively Trained Part-Based Models [J].
Felzenszwalb, Pedro F. ;
Girshick, Ross B. ;
McAllester, David ;
Ramanan, Deva .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (09) :1627-1645
[6]  
FRUIN JJ, 1993, ENGINEERING FOR CROWD SAFETY, P99
[7]  
Helbing D, 2009, PEDESTRIAN CROWD EVA, V16
[8]   Dynamics of crowd disasters: An empirical study [J].
Helbing, Dirk ;
Johansson, Anders ;
Al-Abideen, Habib Zein .
PHYSICAL REVIEW E, 2007, 75 (04)
[9]  
Johansson A, 2008, ARXIV08104590
[10]  
Lempitsky V., 2010, ADV NEURAL INFORM PR, V23, P1, DOI DOI 10.5555/2997189.2997337