Sea Ice SAR Feature Extraction by Non-Negative Matrix and Tensor Factorization

Author

Karvonen, Juha ; Kaarna, Arto

Author_Institution

Finnish Instit. of Marine Res., Helsinki

Volume

4

fYear

2008

fDate

7-11 July 2008

Abstract

We have studied the feature extraction from sea ice SAR images based on non-negative factorization methods. The methods reported here are the sparseness-constrained non-negative matrix factorization (SC-NMF) and Non-negative tensor factorization (NTF). The studies performed show that these methods can be used to extract meaningful features from SAR images and that they can be used in sea ice SAR classification.

Keywords

feature extraction; image classification; remote sensing by radar; sea ice; synthetic aperture radar; Baltic Sea; Gulf of Finland; NTF; Non-negative Tensor Factorization; SC-NMF; Sparseness-Constrained Non- negative Matrix Factorization; edge classification; feature extraction; image classification; non-negative factorization method; sea ice SAR image; sea ice classification algorithm; synthetic aperture radar; Data mining; Error correction; Feature extraction; Image reconstruction; Independent component analysis; Marine technology; Navigation; Sea ice; Sparse matrices; Tensile stress; Classification; Feature Extraction; NMF; NTF; SAR; Sea Ice;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International

Conference_Location

Boston, MA

Print_ISBN

978-1-4244-2807-6

Electronic_ISBN

978-1-4244-2808-3

Type

conf

DOI

10.1109/IGARSS.2008.4779917

Filename

4779917