Crowd Behavior Characterization for Scene Tracking - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Crowd Behavior Characterization for Scene Tracking


In this work, we perform an in-depth analysis of the specific difficulties a crowded scene dataset raises for tracking algorithms. Starting from the standard characteristics depicting the crowd and their limitations, we introduce six en-tropy measures related to the motion patterns and to the appearance variability of the individuals forming the crowd, and one appearance measure based on Principal Component Analysis. The proposed measures are discussed on synthetic configurations and on multiple real datasets. These criteria are able to characterize the crowd behavior at a more detailed level and may be helpful for evaluating the tracking difficulty of different datasets. The results are in agreement with the perceived difficulty of the scenes.
Fichier principal
Vignette du fichier
FranchiAVSS19.pdf (1.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02472760 , version 1 (10-02-2020)



Gianni Franchi, Emanuel Aldea, Séverine Dubuisson, Isabelle Bloch. Crowd Behavior Characterization for Scene Tracking. 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Sep 2019, Taipei, Taiwan. pp.1-8, ⟨10.1109/AVSS.2019.8909893⟩. ⟨hal-02472760⟩
4630 View
98 Download



Gmail Facebook X LinkedIn More