A multi-layer MRF model for video object segmentation

Authors:
Zoltan Kato;Ting-Chuen Pong
Affiliations:
Institute of Informatics, University of Szeged, Szeged, Hungary;Computer Science Department, Hong Kong University of Science and Technology, Kowloon, Hong Kong, China
Venue:
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Year:
2006

Citing 6
Cited 2

Determination of optical flow and its discontinuities using non-linear diffusion

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Region-based parametric motion segmentation using color information

Graphical Models and Image Processing
Motion segmentation and tracking with edge relaxation and optimization using fully parallel methods in the cellular nonlinear network architecture

Real-Time Imaging
Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Direct Model-Based Image Motion Segmentation for Dynamic Scene Analysis

ACCV '95 Invited Session Papers from the Second Asian Conference on Computer Vision: Recent Developments in Computer Vision
A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)

Detection of object motion regions in aerial image pairs with a multilayer Markovian model

IEEE Transactions on Image Processing
Lip segmentation and tracking under MAP-MRF framework with unknown segment number

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel video object segmentation method is proposed which aims at combining color and motion information. The model has a multi-layer structure: Each feature has its own layer, called feature layer, where a classical Markov random field (MRF) image segmentation model is defined using only the corresponding feature. A special layer is assigned to the combined MRF model, called combined layer, which interacts with each feature layer and provides the segmentation based on the combination of different features. Unlike previous methods, our approach doesn’t assume motion boundaries being part of spatial ones. Therefore a very important property of the proposed method is the ability to detect boundaries that are visible only in the motion feature as well as those visible only in the color one. The method is validated on synthetic and real video sequences.