Name
Abstract | ||
|---|---|---|
With the development of target decomposition theorems for polarimetric synthetic aperture radar (PolSAR) data, various informative polarimetric descriptors could be obtained. The redundancy among these descriptors poses a hindrance to accurate classification. In this paper, we propose a tensor-based dimension reduction technique, which aims to obtain a lower-dimensional intrinsic feature set from the high-dimensional polarimetric manifold. We combine 48 polarimetric features together and formulate them as a third-mode tensor. The spatial information is taken into consideration for feature reduction. Experimental results in comparison with principal component analysis (PCA), independent component analysis (ICA) and Laplacian Eigenmaps (LE) proves its effectiveness. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/IGARSS.2014.6947058 | IGARSS |
Keywords | Field | DocType |
geophysical techniques,synthetic aperture radar,informative polarimetric descriptors,tensor decomposition,lower-dimensional intrinsic feature set,tensor-based dimension reduction technique,feature reduction,independent component analysis,remote sensing by radar,polarimetric sar data,feature extraction,geophysical image processing,laplacian eigenmaps,high-dimensional polarimetric manifold,dimension reduction,principal component analysis,target decomposition theorems,radar polarimetry,accuracy,vectors,tensile stress,matrix decomposition | Spatial analysis,Dimensionality reduction,Tensor,Computer science,Remote sensing,Redundancy (engineering),Artificial intelligence,Computer vision,Polarimetry,Pattern recognition,Independent component analysis,Principal component analysis,Laplace operator | Conference |
ISSN | Citations | PageRank |
2153-6996 | 0 | 0.34 |
References | Authors | |
5 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mingliang Tao | 1 | 68 | 10.49 |
| Feng Zhou | 2 | 2189 | 158.01 |
| Zi-jing Zhang | 3 | 135 | 15.74 |