A 3D discrete curvelet based method for segmenting Dynamic Textures

Sloven Dubois (1, 2) , Renaud Péteri (1) , Michel Ménard (2)

1 MIA - Mathématiques, Image et Applications - EA 3165
2 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

This paper presents a new approach for segmenting a video sequence containing dynamic textures. The proposed method is based on a 2D+T curvelet transform and an octree hierarchical representation. The curvelet transform enables to outline spatio-temporal structures of a given scale and orientation. The octree structure based on motion coherence enables a better spatio-temporal segmentation than a direct application of the 2D+T curvelet transform. Our segmentation method is successfully applied on video sequences of dynamic textures. Future prospects are finally exposed.

Mots clés: 2D+T discrete curvelet transform; video segmentation; octree structure; dynamic textures

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Sloven Dubois, Renaud Péteri, Michel Ménard. A 3D discrete curvelet based method for segmenting Dynamic Textures. IEEE International Conference on Image Processing (ICIP 2009), Nov 2009, Cairo, Egypt. pp 1373-1376. ⟨hal-00414658⟩