KIT | KIT-Bibliothek | Impressum | Datenschutz

Integrating pedestrian simulation, tracking and event detection for crowd analysis

Butenuth, Matthias; Burkert, Florian; Kneidl, Angelika; Borrmann, André; Schmidt, Florian; Hinz, Stefan; Sirmacek, Beril; Hartmann, Dirk

Abstract:

In this paper, an overall framework for crowd analysis is presented. Detection and tracking of pedestrians as well as detection of dense crowds is performed on image sequences to improve simulation models of pedestrian flows. Additionally, graph-based event detection is performed by using Hidden Markov Models on pedestrian trajectories utilizing knowledge from simulations. Experimental results show the benefit of our integrated framework using simulation and real-world data for crowd analysis.


Volltext §
DOI: 10.5445/IR/1000029293
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2011
Sprache Englisch
Identifikator urn:nbn:de:swb:90-292931
KITopen-ID: 1000029293
Erschienen in First IEEE ICCV Workshop on Modeling, Simulation and Visual Analysis of Large Crowds, 6-13 November, 2011, Barcelona, Spain
Seiten 150-157
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page