Space-time spectral model for object detection in dynamic textured background

Imtiaz Ali Julien Mille 1 Laure Tougne 2, 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Background models are used for object detection in many computer vision algorithms.In this article, we propose a novel background modeling method basedon frequency for spatially varying and time repetitive textured background.The local Fourier Transform is applied to construct a pixel-wise representationof local frequency components. We apply our method for object detection inmoving background conditions. Experimental results of our frequency-basedbackground model are evaluated both qualitatively and quantitatively.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01353023
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, August 10, 2016 - 4:19:24 PM
Last modification on : Tuesday, February 26, 2019 - 3:52:26 PM

Identifiers

  • HAL Id : hal-01353023, version 1

Citation

Imtiaz Ali, Julien Mille, Laure Tougne. Space-time spectral model for object detection in dynamic textured background. Pattern Recognition Letters, Elsevier, 2012, 13, 33, pp.1710-1716. ⟨hal-01353023⟩

Share

Metrics

Record views

211