|Title||Pixel-based sea ice classification using the MAGSIC system|
|Publication Type||Conference Paper|
|Year of Publication||2006|
|Authors||Maillard, P., and D. A. Clausi|
|Conference Name||International Society for Photogrammetry and Remote Sensing|
|Conference Location||Enschede, The Netherlands|
|Keywords||Classification, navigation, Radarsat, Reasoning, Segmentation, Snow Ice, texture|
MAGSIC is an operation-oriented system in development dedicated to map-guided classification of sea ice for navigation route planning and meteorological modeling. It has already produced promising results in difficult situations such as the Gulf of Saint-Lawrence in late winter. The Canadian Ice Service (CIS) produces ice maps made of large regions with relatively homogeneous concentrations of different ice types. MAGSIC uses the information of these maps to produce a pixel-based (rather than region-based) ice map by labeling a Markov random field (MRF) segmentation of RADARSAT-1 data along with its derived texture features. The system uses a novel implementation of MRF segmentation in combination with a unique labeling approach based on “cognitive reasoning”. Although reasonably successful, the system often had difficulties identifying ice type that required cues based on the shape recognition of large ice floes or leads. This article aims at thoroughly testing the MAGSIC system using validation data acquired during the “2003 Gulf of Saint-Lawrence SAR Validation Field Program” performed by CIS. Some new features were also added to MAGSIC and were evaluated. Results suggest a reasonable success and that the errors can be partially attributed to the generalized nature of the analysts ́interpretation and to the difficulties of obtaining concurring ground and image data. They suggest that classification metrics that can compare sample distributions were slightly superior for labeling purposes but this could not be confirmed statistically.