Spatio-Temporal Segmentation Using 3D Morphological Tools

Authors:
Agnus Vincent
Affiliations:
-
Venue:
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Year:
2000

Citing 0
Cited 7

Topological Reconstruction of Occluded Objects in Video Sequences

DGCI '02 Proceedings of the 10th International Conference on Discrete Geometry for Computer Imagery
Morphology on Label Images: Flat-Type Operators and Connections

Journal of Mathematical Imaging and Vision
Flat Morphology on Power Lattices

Journal of Mathematical Imaging and Vision
Geodesy and connectivity in lattices

Fundamenta Informaticae
Geodesy on label images, and applications to video sequence processing

Journal of Visual Communication and Image Representation
Flat morphological operators on arbitrary power lattices

Proceedings of the 11th international conference on Theoretical foundations of computer vision
Geodesy and connectivity in lattices

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel morphological approach to image simplification by flat zones which, applied to a temporal image sequence, leads to a method for spatio-temporal segmentation. Our approach considers a sequence as a single 3-dimensional image, rather than as a succession of 2D images. An extension of recent tools of 2D mathematical morphology, to the spatio-temporal (2D+t) volume allows a fast detection of moving objects, a tracking of moving regions across time as well as a classification of motion.