By Topic

Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Shang Tan Tu ; Signal Processing Laboratory, School of Electronic Information, Wuhan University, Wuhan, China ; Jia Yu Chen ; Wen Yang ; Hong Sun

In this paper, we propose a novel scheme of polarimetric synthetic aperture radar (PolSAR) image classification. We apply Laplacian eigenmaps (LE), a nonlinear dimensionality reduction (NDR) technique, to a high-dimensional polarimetric feature representation for PolSAR land-cover classification. A wide variety of polarimetric signatures are chosen to construct a high-dimensional polarimetric manifold which can be mapped into the most compact low-dimensional structure by manifold-based dimensionality reduction techniques. This NDR technique is employed to obtain a low-dimensional intrinsic feature vector by the LE algorithm, which is beneficial to PolSAR land-cover classification owing to its local preserving property. The effectiveness of our PolSAR land-cover classification scheme with LE intrinsic feature vector is demonstrated with the RadarSat-2 C-band PolSAR data set and the 38th Research Institute of China Electronics Technology Group Corporation X-band PolInSAR data set. The performance of our method is measured by the separability in the feature space and the accuracy of classification. Comparisons on the feature space show that the LE intrinsic feature vector is more separable than different original feature vectors. Our LE intrinsic feature vector also improves the classification accuracy.

Published in:

IEEE Transactions on Geoscience and Remote Sensing  (Volume:50 ,  Issue: 1 )