Unsupervised Segmentation of Synthetic Aperture Radar Sea Ice Imagery Using MRF Models

Authors:
Affiliations:
Venue:
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Year:
2004

Citing 5
Cited 0

Unsupervised segmentation of noisy and textured images using Markov random fields

CVGIP: Graphical Models and Image Processing
Markov random field modeling in computer vision

Markov random field modeling in computer vision
Unsupervised image segmentation using a simple MRF model with a new implementation scheme

Pattern Recognition
Double Markov random fields and Bayesian image segmentation

IEEE Transactions on Signal Processing
A finite mixtures algorithm for finding proportions in SAR images

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Due to both environmental and sensor reasons,it is challenging to develop computer-assisted algorithmsto segment SAR (synthetic aperture radar)sea ice imagery. In this research, images containingeither ice and water or multiple ice classes aresegmented. This paper proposes to use the imageintensity to discriminate ice from water and to usetexture features to separate different ice types. In orderto seamlessly combine spatial relationship informationin an ice image with various image features,a novel Bayesian segmentation approach is developed.Experiments demonstrate that the proposedalgorithm is able to segment both types of sea iceimages and achieves an improvement over the standardMRF (Markov random field) based method, thefinite Gamma mixture model and the K-means clusteringmethod.