PolSAR Image Classification Based on DBN and Tensor Dimensionality Reduction
Authors:
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8448-8450
Abstract
This paper proposes a new semi-supervised PolSAR image classification method using deep belief network (DBN) and tensor dimensionality reduction, which uses multilinear principle component analysis (MPCA) to reduce the dimension of tensor form PolSAR data, and regards the multiple features of PolSAR data as the input of DBN. In order to take full advantage of neighborhood information of each pixel of PolSAR data, we take each pixel and its neighborhood as tensor form. For PolSAR data, simple feature has been proven not to be able to effectively classify complex terrains. Therefore, we combine multiple features of PolSAR data to obtain more abundant information, which can reflect some spatial structure of PolSAR data. The experimental results show that the overall classification accuracy based on the proposed method outperforms the traditional classification strategies.Keywords
This publication has 9 references indexed in Scilit:
- POL-SAR Image Classification Based on Wishart DBN and Local Spatial InformationIEEE Transactions on Geoscience and Remote Sensing, 2016
- Gaussian-Bernoulli deep Boltzmann machine2013
- Evolutionary RBF classifier for polarimetric SAR imagesExpert Systems with Applications, 2012
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- MPCA: Multilinear Principal Component Analysis of Tensor ObjectsIEEE Transactions on Neural Networks, 2008
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Quantitative comparison of classification capability: fully polarimetric versus dual and single-polarization SARIEEE Transactions on Geoscience and Remote Sensing, 2001
- Physical reality of radar targets1993
- Imaging Radar PolarimetryProgress In Electromagnetics Research, 1990