Data-driven Crowd Analysis in Videos - École des Ponts ParisTech Access content directly
Conference Papers Year : 2011

Data-driven Crowd Analysis in Videos


In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm works by first learning a set of crowd behavior priors off-line. During testing, crowd patches are matched to the database and behavior priors are transferred. We adhere to the insight that despite the fact that the entire space of possible crowd behaviors is infinite, the space of distinguishable crowd motion patterns may not be all that large. For many individuals in a crowd, we are able to find analogous crowd patches in our database which contain similar patterns of behavior that can effectively act as priors to constrain the difficult task of tracking an individual in a crowd. Our algorithm is data-driven and, unlike some crowd characterization methods, does not require us to have seen the test video beforehand. It performs like state-ofthe-art methods for tracking people having common crowd behaviors and outperforms the methods when the tracked individual behaves in an unusual way.
Fichier principal
Vignette du fichier
ICCV11b.pdf (2.89 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00654256 , version 1 (22-12-2011)



Mikel Rodriguez, Josef Sivic, Ivan Laptev, Jean-Yves Audibert. Data-driven Crowd Analysis in Videos. ICCV 2011 - 13th International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.1235 - 1242, ⟨10.1109/ICCV.2011.6126374⟩. ⟨hal-00654256⟩
603 View
1652 Download



Gmail Mastodon Facebook X LinkedIn More