A 3D discrete curvelet based method for segmenting dynamic textures

Authors:
Sloven Dubois;Renaud Péteri;Michel Ménard
Affiliations:
MIA, Laboratoire Mathématiques, Image et Applications, La Rochelle, France and L3i, Laboratoire Informatique, Image et Interaction, La Rochelle, France;MIA, Laboratoire Mathématiques, Image et Applications, La Rochelle, France;L3i, Laboratoire Informatique, Image et Interaction, La Rochelle, France
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 4
Cited 0

Dynamic Texture Segmentation

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Fast Synthesis of Dynamic Colour Textures

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic texture recognition using normal flow and texture regularity

IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

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.