Unsupervised Wishart Classifications of Sea-Ice using Entropy, Alpha and Anisotropy decompositions
Room 1058, A8 Building,
Farnborough, Hants. GU14 0LX,
(2) Vexcel UK, Arrowfield House, Newbury, Berkshire. RG14 6AA, United Kingdom
Sea-ice classification based on scattering mechanisms is investigated using the Unsupervised Wishart Classification with Entropy, Alpha and Anisotropy decomposition parameters. L and C Band JPL AIRSAR fully polarimetric data from the Beaufort Sea during winter/freeze conditions are used for testing the algorithm. Initial results show that, within specified ranges of incidence angles, there is good discrimination between the major ice classes, with L-Band generating better results in general than C band.