• Non ci sono risultati.

A Robust Region Merging Technique for Video Sequence Spatio-Temporal Segmentation

N/A
N/A
Protected

Academic year: 2021

Condividi "A Robust Region Merging Technique for Video Sequence Spatio-Temporal Segmentation"

Copied!
12
0
0

Testo completo

(1)

14/07/12 17.15 | Publications: SPIE

Page 1 of 1 http://spie.org/x648.html?product_id=334633

HOME CONFERENCES + EXHIBITIONS PUBLICATIONS EDUCATION MEMBERSHIP INDUSTRY RESOURCES CAREER CENTER NEWS + VIDEOS

Copyright © 2012 SPIE About SPIE | Author Information | Privacy Policy | Sitemap | MySPIE.org | SPIEDigitalLibrary.org

CREATE AN ACCOUNT | SIGN IN ABOUT SPIE | CONTACT US | HELP | SHOPPING CART

Conference Proceedings Journals

SPIE Digital Library Books

Collections Open Access

Contact SPIE Publications

Robust region-merging technique for video

sequences: spatiotemporal segmentation

(Proceedings Paper)

Author(s): Riccardo Leonardi; Pier A. Migliorati; Giuseppe Tofanicchio Date: 28 December 1998 ISBN: 9780819431240 PDF Member: $18.00 | Non-member: $18.00 Hard Copy Member: $24.00 | Non-member: $24.00 Proceedings Vol. 3653

Visual Communications and Image Processing '99, Kiyoharu Aizawa; Robert L. Stevenson; Ya-Qin Zhang, Editors, pp.1258-2827

Date: 28 December 1998 ISBN: 9780819431240 Paper Abstract

The segmentation of video sequences into regions underlying a coherent motion is one of the most important processing in video analysis and coding. In this paper, we propose a reliability measure that indicates to what extent an affine motion model represents the motion of an image region. This reliability measure is then proposed as a criterion to coherently merge moving image regions in a Minimum Description Length (MDL) framework. To overcome the region-based motion estimation and segmentation chicken and egg problem, the motion field estimation and the segmentation task are treated separately. After a global motion compensation, a local motion field estimation is carried out starting from a translational motion model.

Concurrently, a Markov Random Field model based algorithm provides for an initial static image partition. The motion estimation and segmentation problem is then formulated in the view of the MDL principle. A merging stage based on a directed weighted graph gives the final spatio-temporal segmentation. The simulation results show the effectiveness of the proposed algorithm. DOI: 10.1117/12.334633

Current SPIE Digital Library subscribers click here to download this paper. © SPIE - Downloading of the abstract is permitted for personal use only. See Terms of Use

New Titles Update

Sign up for monthly alerts of new titles released.

(2)
(3)
(4)
(5)
(6)
(7)
(8)
(9)
(10)
(11)
(12)

Riferimenti

Documenti correlati

This paper considers specific housing management strategies: the self-management (Zelfbeheer in Dutch) in the Netherlands and the Integrated Social Management

Since EL is a sub-logic of Prob-EL 01 c and classification can be reduced to instance checking, 3 our approach can also find the pinpointing formulas for the different

The large number of trust-based approaches in MASs emerged in the last recent years implies the necessity of clearly understanding what are the advantages and the limitations.. of

The boost , whose purpose is to potentiate the cell-mediated immune response, consists in the administration of autologous dendritic cells transduced in vitro with a

A more exhaustive analysis of the tangential and the axial velocity profiles was conducted investigating the main vortex parameters: the peak tangential velocity (V θ1 ), the

As regards issue 2, we do not work directly on rule- based defeasible reasoning, but we define a revision operator that may remove rules when needed or adapt intervals of time

Controlled Markov chain models are used to describe the temporal evolution of low-level de- scriptors extracted from the MPEG compressed bit- stream.. The proposed algorithm has

Al fine di determinare parzialmente l’enorme eterogeneità strutturale della Zona di Subduzione delle Piccole Antille, il modello minimum 1-D è completato dalle correzioni