A 3D discrete curvelet based method for segmenting dynamic textures

Author

Dubois, Sloven ; Péteri, Renaud ; Ménard, Michel

Author_Institution

Lab. Math., Image et Applic. (MIA), La Rochelle, France

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

1373

Lastpage

1376

Abstract

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.

Keywords

discrete wavelet transforms; image segmentation; image sequences; image texture; octrees; 2D+T curvelet transform; 3D discrete curvelet based method; dynamic texture segmentation; motion coherence; octree hierarchical representation; spatio-temporal segmentation method; spatio-temporal structures; video sequence segmentation; Discrete transforms; Discrete wavelet transforms; Frequency domain analysis; Image segmentation; Image sequences; Layout; Signal processing; Surface texture; Video sequences; 2D+T discrete curvelet transform; dynamic textures; octree structure; video segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5413352

Filename

5413352