Data-Driven Motion Pattern Segmentation in a Crowded Environments - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Data-Driven Motion Pattern Segmentation in a Crowded Environments

Jana Trojanova
  • Function : Author
  • PersonId : 990742
Karel Křehnač
  • Function : Author

Abstract

Motion is a strong clue for unsupervised grouping of individuals in a crowded environment. We show that collective motion in the crowd can be discovered by temporal analysis of points trajectories. First k-NN graph is constructed to represent the topological structure of point trajectories detected in crowd. Then the data-driven graph seg-mentation helps to reveal the interaction of individuals even when mixed motion is presented in data. The method was evaluated against the latest state-of-the-art methods and achieved better performance by more than 20 percent.
Fichier principal
Vignette du fichier
janaCentaurW-eccv16.pdf (3.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01849288 , version 1 (25-07-2018)

Identifiers

  • HAL Id : hal-01849288 , version 1

Cite

Jana Trojanova, Karel Křehnač, François Bremond. Data-Driven Motion Pattern Segmentation in a Crowded Environments. ECCV workshop on Crowd, Oct 2016, Amsterdam,, Netherlands. ⟨hal-01849288⟩
77 View
90 Download

Share

Gmail Facebook Twitter LinkedIn More