In this paper we propose a method for the motion-congruent segmentation of image sequences based on both motion field and luminance information. In order to do so, the affine motion models are determined by analyzing the motion field through a clustering procedure, while their regions of validity are determined by an MRF-based region estimator. This last block performs a pixel-wise re-assignment of a limited number of affine models (those determined via clustering).
Combined motion and edge analysis for a layer-based representation of image sequences / F. Pedersini, A. Sarti, S. Tubaro - In: Proceedings of 3rd IEEE International Conference on Image Processing 1996 (ICIP 96)[s.l] : IEEE, 1996. - ISBN 0-7803-3259-8. - pp. 921-924 (( convegno International Conference on Image Processing (ICIP) nel 1996.
Combined motion and edge analysis for a layer-based representation of image sequences
F. PedersiniPrimo
;
1996
Abstract
In this paper we propose a method for the motion-congruent segmentation of image sequences based on both motion field and luminance information. In order to do so, the affine motion models are determined by analyzing the motion field through a clustering procedure, while their regions of validity are determined by an MRF-based region estimator. This last block performs a pixel-wise re-assignment of a limited number of affine models (those determined via clustering).Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.