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
SARTI, AUGUSTO;TUBARO, STEFANO
1996-01-01
Abstract
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)File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
1996_IEEE_ICIP_motion-edge_analysis_layer-based_representation_image_sequences.pdf
Accesso riservato
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
632.35 kB
Formato
Adobe PDF
|
632.35 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.