Title :
Sea ice segmentation using Markov random fields
Author :
Yue, B. ; Clausi, D.A.
Author_Institution :
Dept. of Syst. Design Eng., Waterloo Univ., Ont., Canada
Abstract :
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
Keywords :
Bayes methods; Markov processes; geophysical signal processing; image classification; image segmentation; image texture; maximum likelihood estimation; oceanographic techniques; optimisation; radar imaging; remote sensing by radar; sea ice; synthetic aperture radar; Bayesian framework; Markov random field models; SAR sea ice imagery; classes; conditional distribution; discrete model; identification; intensity image; maximizing a posteriori distribution; optimization process; segmentation; texture models; underlying texture label image; Bayesian methods; Degradation; Image processing; Image segmentation; Image texture analysis; Markov random fields; Pixel; Random variables; Remote monitoring; Sea ice;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-7031-7
DOI :
10.1109/IGARSS.2001.977102
