A multi-level SAR sea ice image classification method by incorporating egg-code-based expert knowledge

Identification of sea ice types is of crucial importance to ship navigation and climatic research. This paper presents a multi-level SAR sea ice image classification method by incorporating expert knowledge from egg codes associated with the sea ice images. First, subimages which correspond to egg codes are segmented by using the region-level MRF model. The egg code regions in which partial concentrations of sea ice types are not equal respectively are considered, thus the reference vectors of intensity mean of some sea ice types are determined. Then, other egg code regions are classified in a hierarchical way and the intensity mean of each class can be computed, hence sea ice classification in the whole SAR scene can be finished based on the Euclidean distance discriminant method. The efficiency of the proposed method is demonstrated on the classification of real SAR sea ice images.