Sea ice segmentation using Markov random fields

TitleSea ice segmentation using Markov random fields
Publication TypeConference Paper
Year of Publication2001
AuthorsYue, B., and D. A. Clausi
Conference NameIEEE Geoscience and Remote Sensing Symposium
KeywordsBayes methods, Bayesian framework, classes, conditional distribution, discrete model, geophysical signal processing, identification, image classification, image segmentation, image texture, intensity image, Markov processes, Markov Random Field models, maximizing a posteriori distribution, maximum likelihood estimation, oceanographic techniques, optimisation, optimization process, radar imaging, remote sensing by radar, SAR sea ice imagery, sea ice, Segmentation, synthetic aperture radar, texture models, underlying texture label image

Tools are required to assist the identification of pertinent classes in SAR sea ice imagery. Texture models offer a means of performing this task. The texture information in SAR sea ice imagery can be characterized by two Markov random field models: the Gauss model for conditional distribution of the observed intensity image and the discrete model for the underlying texture label image. The segmentation can be implemented as an optimization process of maximizing a posteriori distribution in a Bayesian framework