Classification of Sea Ice Types in ENVISAT Synthetic Aperture Radar Images
Authors:
Open Access
- 24 September 2012
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 51 (5) , 2587-2600
Abstract
In this paper, sea ice in the Central Arctic has been classified in synthetic aperture radar (SAR) images from ENVISAT using a neural network (NN)-based algorithm and a Bayesian algorithm. Since different sea ice types can have similar backscattering coefficients at C-band HH polarization, it is necessary to use textural features in addition to the backscattering coefficients. The analysis revealed that the most informative texture features for the classification of multiyear ice (MYI), deformed first-year ice (FYI) (DFYI), and level FYI (LFYI) and open water/nilas are correlation, inertia, cluster prominence, energy, homogeneity, and entropy, as well as third and fourth central statistical moments of image brightness. The optimal topology of the NN, trained for ENVISAT wide-swath SAR sea ice classification, consists of nine neurons in input layer, six neurons in hidden layer, and three neurons in output layer. The classification results for a series of 20 SAR images, acquired in the central part of the Arctic Ocean during winter months, were compared to expert analysis of the images and ice charts. The results of the NN classification show that the average correspondences with the expert analysis amount to 85 $\%$, 83$\%$, and 80$\%$ for LFYI, DFYI, and MYI, respectively. The Bayesian pixel-based method can provide a higher resolution in the classified image and, therefore, better capability to identify leads compared to the NN method. Both methods may be effectively used in the Central Arctic where MYI is predominant.
Keywords
This publication has 34 references indexed in Scilit:
- ARKTOS: An Intelligent System for SAR Sea Ice Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2004
- Improved neural network scatterometer forward modelsJournal of Geophysical Research: Oceans, 2001
- Texture analysis of SAR sea ice imagery using gray level co-occurrence matricesIEEE Transactions on Geoscience and Remote Sensing, 1999
- Laboratory measurements of sea ice: connections to microwave remote sensingIEEE Transactions on Geoscience and Remote Sensing, 1998
- Detection of features in first-year pack ice by synthetic aperture radar (SAR)International Journal of Remote Sensing, 1998
- Application of neural networks for sea ice classification in polarimetric SAR imagesIEEE Transactions on Geoscience and Remote Sensing, 1995
- An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parametersIEEE Transactions on Geoscience and Remote Sensing, 1995
- Backscatter characteristics of the winter ice cover in the Beaufort SeaJournal of Geophysical Research: Oceans, 1994
- Radar backscatter signatures of thin sea ice in the central ArcticInternational Journal of Remote Sensing, 1994
- Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing DataIEEE Transactions on Geoscience and Remote Sensing, 1990