001003812 001__ 1003812
001003812 005__ 20230307201804.0
001003812 0247_ $$2Handle$$a2128/34078
001003812 037__ $$aFZJ-2023-01262
001003812 041__ $$aEnglish
001003812 1001_ $$0P:(DE-Juel1)185971$$aAlia, Ahmed$$b0$$eCorresponding author
001003812 1112_ $$aConference for Research Software Engineering in Germany$$cPaderborn$$d2023-02-20 - 2023-02-22$$gdeRSE23$$wGermany
001003812 245__ $$aDL4PuDe: Deep-Learning Framework for Pushing Detection in Pedestrian Dynamics
001003812 260__ $$c2023
001003812 3367_ $$033$$2EndNote$$aConference Paper
001003812 3367_ $$2DataCite$$aOther
001003812 3367_ $$2BibTeX$$aINPROCEEDINGS
001003812 3367_ $$2DRIVER$$aconferenceObject
001003812 3367_ $$2ORCID$$aLECTURE_SPEECH
001003812 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1678165499_17993$$xAfter Call
001003812 520__ $$aAt crowded event entrances, some pedestrians start pushing others to gain faster access to the events, resulting in dangerous situations. Pushing identification in video recordings of events is crucial for understanding pushing dynamics, thereby managing entrances safely. This talk presents a deep-learning framework to help researchers automatically identify pushing in videos of crowds. The framework consists of four modules: (1) Optical Flow Estimator that uses a pre-trained optical flow model to estimate the dense displacement fields from input video. (2) Wheel Visualization for generating motion information maps from the displacement fields. (3) EfficientNet-B0 Classifier that aims to identify pushing behavior from the maps. (4) A False Reduction and Annotation module; to reduce the number of false identifications of the classifier, annotate the regions of pushing and output the annotated video. We used five real-world ground truth of pushing behavior videos for the evaluation. Experimental results show that the framework achieves 86% accuracy. The framework is open-source and available at https://github.com/PedestrianDynamics/DL4PuDe.
001003812 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001003812 536__ $$0G:(BMBF)01DH16027$$aPilotprojekt zur Entwicklung eines palästinensisch-deutschen Forschungs- und Promotionsprogramms 'Palestinian-German Science Bridge' (01DH16027)$$c01DH16027$$x1
001003812 7001_ $$0P:(DE-HGF)0$$aMaree, Mohammed$$b1
001003812 7001_ $$0P:(DE-Juel1)132077$$aChraibi, Mohcine$$b2
001003812 8564_ $$uhttps://pad.gwdg.de/deRSE23-session-pads-ai-and-ml
001003812 8564_ $$uhttps://juser.fz-juelich.de/record/1003812/files/Abstract-DL4PuDe.pdf$$yOpenAccess
001003812 8564_ $$uhttps://juser.fz-juelich.de/record/1003812/files/Alia-Ahmed-DL4PuDe.pdf$$yRestricted
001003812 909CO $$ooai:juser.fz-juelich.de:1003812$$popenaire$$popen_access$$pVDB$$pdriver
001003812 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185971$$aForschungszentrum Jülich$$b0$$kFZJ
001003812 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132077$$aForschungszentrum Jülich$$b2$$kFZJ
001003812 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001003812 9141_ $$y2023
001003812 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001003812 920__ $$lyes
001003812 9201_ $$0I:(DE-Juel1)IAS-7-20180321$$kIAS-7$$lZivile Sicherheitsforschung$$x0
001003812 980__ $$aconf
001003812 980__ $$aVDB
001003812 980__ $$aUNRESTRICTED
001003812 980__ $$aI:(DE-Juel1)IAS-7-20180321
001003812 9801_ $$aFullTexts