Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos

Fida El Baf (1) , Thierry Bouwmans (1) , Bertrand Vachon (1)

1 MIA - Mathématiques, Image et Applications - EA 3165

Mixture of Gaussians (MOG) is the most popular technique for background modeling and presents some limitations when dynamic changes occur in the scene like camera jitter and movement in the background. Furthermore, the MOG is initialized using a training sequence which may be noisy and/or insufficient to model correctly the background. All these critical situations generate false classification in the foreground detection mask due to the related uncertainty. In this context, we present a background modeling algorithm based on Type-2 Fuzzy Mixture of Gaussians which is particularly suitable for infrared videos. The use of the Type-2 Fuzzy Set Theory allows to take into account the uncertainty. The results using the OTCBVS benchmark/test dataset videos show the robustness of the proposed method in presence of dynamic backgrounds.

Mots clés: Background Modeling; Foreground Detection; Mixture of Gaussians

Domaines: Traitement des images [eess.IV]

Fida El Baf, Thierry Bouwmans, Bertrand Vachon. Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos. CVPR Workshop: International Workshop on Object Tracking and Classification in and Beyond the Visible Spectrum,, Jun 2009, Miami, United States. pp.60-65, ⟨10.1109/CVPR.2009.5204109⟩. ⟨hal-00452812⟩