This paper proposes a custom convolutional deep belief network for polarimetric synthetic aperture radar (PolSAR) data feature extraction. The proposed architecture stands out through the interesting features it shows, starting with the fact that it is adapted to fully polarimetric SAR data. Then, the multilayer approach allows the stepwise discovery of higher-level features. The convolutional approach allows the discovery of local, spatially invariant features and makes the architecture scalable to fully sized PolSAR images. The network is trained in an unsupervised manner, without using labeled data and then it succeeds to extract powerful features from PolSAR patches. This fact is demonstrated by applying supervised and unsupervised classification algorithms on features extracted from patches of a fully polarimetric multi-look F-SAR image over Kaufbeuren airfield, Germany.
[1]
Geoffrey E. Hinton.
A Practical Guide to Training Restricted Boltzmann Machines
,
2012,
Neural Networks: Tricks of the Trade.
[2]
Mohammad Norouzi,et al.
Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning
,
2009,
CVPR.
[3]
Christian Igel,et al.
An Introduction to Restricted Boltzmann Machines
,
2012,
CIARP.
[4]
Yee Whye Teh,et al.
A Fast Learning Algorithm for Deep Belief Nets
,
2006,
Neural Computation.
[5]
Honglak Lee,et al.
Unsupervised learning of hierarchical representations with convolutional deep belief networks
,
2011,
Commun. ACM.