Please use this identifier to cite or link to this item:
Author(s): Jaime S. Cardoso
Jorge C. S. Cardoso
Luís Corte-Real
Title: Object-based spatial segmentation of video guided by depth and motion information
Issue Date: 2007
Abstract: Automatic spatial video segmentation is a problem withouta general solution at the current state-of-the-art. Mostof the difficulties arise from the process of capturing images,which remain a very limited sample of the scene they represent.The capture of additional information, in the form ofdepth data, is a step forward to address this problem. Westart by investigating the use of depth data for better imagesegmentation; a novel segmentation framework is proposed,with depth being mainly used to guide a segmentationalgorithm on the colour information. Then, we extendthe method to also incorporate motion information in thesegmentation process. The effectiveness and simplicity ofthe proposed method is documented with results on a selectedset of images sequences. The achieved quality raisesthe expectation for a significant improvement on operationsrelying on spatial video segmentation as a pre-process.
Subject: Processamento de imagem
Source: 2007 IEEE Workshop on Motion and Video Computing, WMVC 2007
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: openAccess
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
66199.pdf1.07 MBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons