Unsupervised Land Cover/Land Use Classification Using PolSAR Imagery Based on Scattering Similarity

Chen, Qiang; Kuang, Gangyao; Li, J.; Sui, Lichun; Li, Diangang

doi:10.1109/tgrs.2012.2205389

Cited by 38 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this sense, f ref is a similarity and the corresponding GD is a dissimilarity. In PolSAR literature, Yang et al [21], Touzi and Charboneau [22], and Chen et al [23] discuss similarity-based approaches for describing scattering phenomenon from PolSAR images. Thus, the GD is advantageous in terms of its physical significance with parallel definitions across all data representations in PolSAR.…”

Section: B Gd For Other Polsar Data Representationsmentioning

confidence: 99%

A PolSAR Scattering Power Factorization Framework and Novel Roll-Invariant Parameter-Based Unsupervised Classification Scheme Using a Geodesic Distance

Ratha

Pottier

Bhattacharya

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

We propose a generic Scattering Power Factorization Framework (SPFF) for Polarimetric Synthetic Aperture Radar (PolSAR) data to directly obtain N scattering power components along with a residue power component for each pixel. Each scattering power component is factorized into similarity (or dissimilarity) using elementary targets and a generalized random volume model. The similarity measure is derived using a geodesic distance between pairs of 4 × 4 real Kennaugh matrices. In standard model-based decomposition schemes, the 3 × 3 Hermitian positive semi-definite covariance (or coherency) matrix is expressed as a weighted linear combination of scattering targets following a fixed hierarchical process. In contrast, under the proposed framework, a convex splitting of unity is performed to obtain the weights while preserving the dominance of the scattering components. The product of the total power (Span) with these weights provides the non-negative scattering power components. Furthermore, the framework along the geodesic distance is effectively used to obtain specific roll-invariant parameters which are then utilized to design an unsupervised classification scheme. The SPFF, the roll invariant parameters, and the classification results are assessed using C-band RADARSAT-2 and L-band ALOS-2 images of San Francisco.T ARGET decomposition (TD) theorems are an essential avenue of research in the study of Polarimetric Synthetic Aperture Radar (PolSAR) imagery. In this context, the study of light scattering by small anisotropic particles by Chandrasekhar [1] was the first instance of a TD. Later, Huynen [2] rigorously formulated this notion and laid the foundations of the modern day TDs.According to Huynen, the objective of TD is to identify the average scattering mechanism within the pixel in the form of a rank-1 covariance/coherency matrix. The interpretation of this information is achieved by obtaining a set of unique parameters often roll-invariant in nature for a description of the target under study. On the one hand, this approach is utilized in the eigenvalue/eigenvector based decomposition schemes. On the other hand, model-based decompositions interpret the observation as a weighted linear combination of specific scattering mechanisms. In the later, the scattering components can be rank-1 or distributed (rank ≥ 1, e.g. volume scattering models) targets [3].The extraction of a desirable rank-1 (pure or coherent) target is often synonymous with the most dominant scattering mechanism component from the observation [4]. However, retaining all the components (in decreasing order of dominance) is more useful for a complete and more realistic characterization of the target. This task is leveraged for better interpretation of the observation by model-based decompositions [5], [6], and for uniqueness, by the eigenvalue-eigenvector based decompositions [7], [8].Recently, Xu et al.[9] brought together rank-1 PolSAR decomposition, model-based decomposition, and image clustering under the single umbrella of image factorization...

show abstract

Section: B Gd For Other Polsar Data Representationsmentioning

confidence: 99%

A PolSAR Scattering Power Factorization Framework and Novel Roll-Invariant Parameter-Based Unsupervised Classification Scheme Using a Geodesic Distance

Ratha

Pottier

Bhattacharya

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Let = ; then the matrix follows a complex Wishart distribution, which is listed in formula (5). In formula (5), the function ( , ) is defined as formula (6). Consider…”

Section: Probabilistic Model and Wishartmentioning

confidence: 99%

“…It had been demonstrated in this paper that the final classification could be substantially different from initial classified results and pixels of different scattering mechanisms could be mixed together. Chen et al [6] present a new unsupervised land cover/land-use classification scheme based on polarimetric scattering similarity. It identifies the major and minor scattering mechanisms automatically based on the relative 2 Journal of Electrical and Computer Engineering magnitude of multiple-scattering similarities.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Classification Method for Polarimetric Synthetic Aperture Radar Imagery Based on Yamaguchi Four-Component Decomposition Model

Sun

Liu

Wen

2015

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

For improving the accuracy of unsupervised classification based on scattering models, the four-component Yamaguchi model is introduced, which is an improved version of the best-known three-component Freeman model. Therewith, the four-component model is combined with the Wishart distance model. The new proposed algorithm of clustering is rolled out thereafter and the procedure of this new method is listed. In experiments, seven areas of various homogeneities are singled out from the Flevoland sample image in AIRSAR dataset. Qualitative and quantitative experiments are performed for a comparative study. It can be easily seen that the resolution and details are remarkably upgraded by the new proposed method. The accuracy of classification in homogeneous areas has also increased significantly by adopting the new iterative algorithm.

show abstract

“…Rignot et al [4] assumed complex Gaussian class distributions to unsupervised segmentation of polarimetric SAR data. Recently, Chen et al [5] presented a method based on polarimetric scattering similarity, which used the major and minor scattering mechanisms to increase the accuracy of classification.…”

Section: Introductionmentioning

confidence: 99%

Classification of Polarimetric SAR Images Using Multilayer Autoencoders and Superpixels

Hou

Kou

Jiao

2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

113

View full text Add to dashboard Cite

A new polarimetric synthetic aperture radar (Pol-SAR) images classification method based on multilayer autoencoders and superpixels is proposed in this paper. First, in order to explore the spatial relations between pixels in PolSAR data, the RGB image formed with Pauli decomposition is used to produce superpixels to integrate contextual information of neighborhood. Second, multilayer autoencoders network is used to learning the features used for distinguishing the multiple categories for each pixel, and a softmax regression is applied to produce the predicted probability distributions over all the classes of each pixel. Finally, the probability distributions is regarded as a new probabilistic metric and introduced to k-nearest neighbor to improve the accuracy of classification based on superpixels, which takes spatial relationship between pixels into consideration, and it is robust to speckle noise. The proposed method makes good use of the scattering characteristics in each pixel and spatial information of PolSAR data. Compared with other state-of-the-art methods, the results of proposed method show better agreement with the ground truth and significant improvement in classification accuracy and discriminability of small differences between different categories.

show abstract

Unsupervised Land Cover/Land Use Classification Using PolSAR Imagery Based on Scattering Similarity

Cited by 38 publications

References 24 publications

A PolSAR Scattering Power Factorization Framework and Novel Roll-Invariant Parameter-Based Unsupervised Classification Scheme Using a Geodesic Distance

A PolSAR Scattering Power Factorization Framework and Novel Roll-Invariant Parameter-Based Unsupervised Classification Scheme Using a Geodesic Distance

Unsupervised Classification Method for Polarimetric Synthetic Aperture Radar Imagery Based on Yamaguchi Four-Component Decomposition Model

Classification of Polarimetric SAR Images Using Multilayer Autoencoders and Superpixels

Contact Info

Product

Resources

About