Sea ice concentration estimation from satellite SAR imagery using convolutional neural network and stochastic fully connected conditional random field

TitleSea ice concentration estimation from satellite SAR imagery using convolutional neural network and stochastic fully connected conditional random field
Publication TypeConference Paper
Year of Publication2015
AuthorsWang, L., A. Wong, D. A. Clausi, A. K. Scott, L. Xu, M. J. Shafiee, and F. Li
Conference NameCVPR 2015 Earthvision Workshop
Date Published2015
Abstract

Ice mapping is important for numerous applications such
as ship navigation and mining in the Arctic regions. The
need for ice mapping is increasing to support operations
in the Arctic regions. We propose an automatic SAR ice
concentration estimation method using convolutional neural network (CNN) followed by a stochastic fully connected
random field (SFCRF). CNN can generate the proper features for robust ice concentration estimation. The low
boundary accuracy of CNN is overcome by introducing
SAR image structure information into the CNN output using
SFCRF. This method uses ice charts as training data to take
advantage of the abundant ice chart archives, which makes
it appealing for operational ice mapping purposes. It shows
robustness to melting conditions on our test dataset. The
overall precision of the ice concentration estimate is less
than 0.12 (12%) when validated on ice chart. This method
can be naturally extended for ice water classification. An
overall classification precision of 96% is achieved by using
a simple thresholding on the ice concentration estimates.

Related files: