You are here

SEC: Stochastic ensemble consensus approach to unsupervised SAR sea-ice segmentation

TitleSEC: Stochastic ensemble consensus approach to unsupervised SAR sea-ice segmentation
Publication TypeConference Paper
Year of Publication2009
AuthorsWong, A., D. A. Clausi, and P. Fieguth
Conference Name6th Canadian Conference on Computer and Robot Vision
Date Published05/2009
Conference LocationKelowna, British Columbia, Canada
KeywordsCanadian Ice Service, expectation maximization approach, Gaussian mixture model, GMM, image segmentation, K-means clustering, Markov Random Field models, maximum likelihood classification, maximum likelihood estimation, oceanographic techniques, polar regions, probability, probability distribution, RADARSAT-1 imagery, RADARSAT-2 imagery, random samples, remote sensing by radar, SAR sea-ice imagery, sea ice, sea-ice analysis, sea-ice monitoring, stochastic ensemble consensus approach, synthetic aperture radar, tonal characteristics, underlying ice type, unsupervised SAR sea-ice segmentation, weighted median consensus strategy

The use of synthetic aperture radar (SAR) has become an integral part of sea-ice monitoring and analysis in the polar regions. An important task in sea-ice analysis is to segment SAR sea-ice imagery based on the underlying ice type, which is a challenging task to perform automatically due to various imaging and environmental conditions. A novel stochastic ensemble consensus approach to sea-ice segmentation (SEC) is presented to tackle this challenging task. In SEC, each pixel in the SAR sea-ice image is assigned an initial sub-class based on its tonal characteristics. Ensembles of random samples are generated from a random field representing the SAR sea-ice imagery. The generated ensembles are then used to re-estimate the sub-class of the pixels using a weighted median consensus strategy. Based on the probability distribution of the sub-classes, an expectation maximization (EM) approach is utilized to estimate the final class likelihoods using a Gaussian mixture model (GMM). Finally, maximum likelihood (ML) classification is performed to estimate the final class of each pixel within the SAR sea-ice imagery based on the estimated GMM and the assigned sub-classes. SEC was tested using a variety of operational RADARSAT-1 and RADARSAT-2 SAR sea-ice imagery provided by the Canadian Ice Service (CIS) and was shown to produce successfully segmentation results that were superior to approaches based on K-means clustering, Gamma mixture models, and Markov Random Field (MRF) models for sea-ice segmentation.