Unsupervised classification of polarimetric SAR imagery using large-scale spectral clustering with spatial constraints
Spectral clustering is a very popular approach which has been successfully used in unsupervised classification of polarimetric synthetic aperture radar (PolSAR) imagery. However, due to its high computational complexity, spectral clustering can only be applied to small data sets. This article provides a framework for spectral clustering of large-scale PolSAR data. As computing and processing the pairwise-based affinity matrix is the bottleneck of the spectral clustering approach, we first introduce a representative points-based scheme in which a memory-saving and computationally tractable affinity matrix is designed. The subsequent spectral analysis can be solved efficiently. Second, a simple one-parameter superpixel algorithm is introduced to generate representative points. Through these superpixels, spatial constraints are also naturally integrated into the classification framework. We test the proposed approach on both airborne and space-borne PolSAR images. Experimental results demonstrate its effectiveness.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations: School of Electronic Information, Wuhan University, Wuhan, 430072, China
Publication date: June 3, 2015