Unsupervised classification of polarimetric SAR imagery using large-scale spectral clustering with spatial constraints

Abstract

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.

Superpixel-Based Classification Using K Distribution and Spatial Context for Polarimetric SAR Images

“…Among the many superpixel-generating algorithms, the SLIC algorithm is designed to generate a set of compact superpixels efficiently [36] and has been successfully applied for PolSAR images [33,34,37]. Thus, a modified SLIC algorithm is proposed for PolSAR images in the present study.…”

“…In recent years, superpixel-based classification methods have achieved fair results in PolSAR image. The SLIC algorithm is able to generate compact, approximately homogeneous superpixels with high computational efficiency and has been successfully utilized in optical and PolSAR images [33,34,37]. We modify the SLIC algorithm to control the superpixel generation in PolSAR images, and the main steps are as follows: …”

“…Liu et al [32] used the normalized cuts algorithm to generate superpixels and conducted classification experiments based on superpixels. Feng et al [33] and Song et al [34] used superpixels generated by the simple linear iterative clustering (SLIC) algorithm as their classification elements. These works demonstrate the feasibility of superpixels.…”

Superpixel Segmentation for Polsar Images With Local Iterative Clustering and Heterogeneous Statistical Model

“…Similarly, in (Song et al 2015;Fachao, Jiming, and Fengkai 2015;Feng, Cao, and Pi 2014), this parameter is also chosen to be a constant to balance the polarimetric and spatial similarity. This parameter is usually set manually by trial and error, which might cause over-or under-superpixel segmentation in some spatially complicated areas.…”

“…For PolSAR data, Liu et al (Liu et al 2013) incorporated the revised Wishart distance and edge map into the Normalized cuts algorithm to produce superpixels. On the basis of SLIC, Feng et al (Feng, Cao, and Pi 2014), Song et al (Song et al 2015), and Qin et al (Fachao, Jiming, and Fengkai 2015) utilized the symmetric revised Wishart distance, Bartlett distance and revised Wishart distance respectively as the similarity measures instead of the original one to generate superpixels. It can be seen that these methods are all designed based on the assumption of Wishart distribution, which can well describe the backscatters of natural areas.…”