Hierarchical segmentation of Polarimetric SAR images using heterogeneous clutter models

Bombrun, Lionel; Beaulieu, Jean-Marie; Vasile, Gabriel; Ovarlez, Jean‐Philippe; Pascal, Frédéric; Gay, Michel

doi:10.1109/igarss.2009.5418271

Cited by 24 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, since the ground objects in PolSAR images are with various scales and orientations, filters with multiple scales and orientations are constructed for edge and line detections of PolSAR images. The weighted CFAR edge and line energies of a pixel are given by: 12 2 log edge EQ   (1) 12 13…”

Section: Polarimetric Hybrid Edge-line Detection: a Polarimetric Hybrmentioning

confidence: 99%

“…To take the spatial information into account, the image segmentation techniques are involved for PolSAR classification in recent years. There are plenty of segmentation methods to exploit spatial information which can be mainly divided into four categories: 1) approaches based on superpixels which are over-segmented regions, such as the hierarchical segmentation [12] and region-based methods [13][14][15]; 2) approaches based on textural modeling [16], such as gray level co-occurrences matrices (GLCM) [17] and Gabor [18] or wavelet features [19]; 3) approaches with regularization criterion, such as Markov Random Field(MRF) [20] [21] and contour criterion [22] [23]; 4) approaches based on statistical modeling, such as the non-Gaussian modeling method [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical semantic model and scattering mechanism based PolSAR image classification

Liu

Shi

Jiao

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

Section: Polarimetric Hybrid Edge-line Detection: a Polarimetric Hybrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hierarchical semantic model and scattering mechanism based PolSAR image classification

Liu

Shi

Jiao

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

“…b) Divide the quantized image into K × K non-overlapping blocks. c) Calculate the GLCM and entropy by (15) and (16 by the Fisher distribution [26], [27]. It can be seen from Table 2 that this method underestimates the ENL for most of the test SAR images especially for those images where the assumption does not hold.…”

Section: Input: Sar Image(intensity Image)mentioning

confidence: 99%

Unsupervised Speckle Level Estimation of SAR Images Using Texture Analysis and AR Model

Cui

Zhou

et al. 2014

IEICE Trans. Commun.

View full text Add to dashboard Cite

In this paper, a new method is proposed for unsupervised speckle level estimation in synthetic aperture radar (SAR) images. It is assumed that fully developed speckle intensity has a Gamma distribution. Based on this assumption, estimation of the equivalent number of looks (ENL) is transformed into noise variance estimation in the logarithmic SAR image domain. In order to improve estimation accuracy, texture analysis is also applied to exclude areas where speckle is not fully developed (e.g., urban areas). Finally, the noise variance is estimated by a 2-dimensional autoregressive (AR) model. The effectiveness of the proposed method is verified with several SAR images from different SAR systems and simulated images. key words: AR model, equivalent number of looks (ENL), synthetic aperture radar (SAR), texture analysis.

show abstract

“…The segmented image is presented in Figure 5(a); each segment is shown in a color defined by associating the RGB channels to the means of each intensity polarization (HH, HV and VV). The classification procedure described by equation (12) was applied for L-band SIR-C data using this segmented image. The tests statistics are given in equations (6)-(10), assuming the Wishart law, as well as equation (11), assuming the Gaussian law for amplitude data.…”

Section: Assessing the Classification Procedures Using Sir-c Polarimentioning

confidence: 99%

Classification of Segments in PolSAR Imagery by Minimum Stochastic Distances Between Wishart Distributions

Silva

Freitas²,

Sant’Anna³

et al. 2013

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

View full text Add to dashboard Cite

A new classifier for Polarimetric SAR (PolSAR) images is proposed and assessed in this paper. Its input consists of segments, and each one is assigned the class which minimizes a stochastic distance. Assuming the complex Wishart model, several stochastic distances are obtained from the h-φ family of divergences, and they are employed to derive hypothesis test statistics that are also used in the classification process. This article also presents, as a novelty, analytic expressions for the test statistics based on the following stochastic distances between complex Wishart models: Kullback-Leibler, Bhattacharyya, Hellinger, Rényi, and Chi-Square; also, the test statistic based on the Bhattacharyya distance between multivariate Gaussian distributions is presented. The classifier performance is evaluated using simulated and real PolSAR data. The simulated data are based on the complex Wishart model, aiming at the analysis of the proposal well controlled data. The real data refer to the complex L-band image, acquired during the 1994 SIR-C mission. The results of the proposed classifier are compared with those obtained by a Wishart per-pixel/contextual classifier, and we show the better performance of the region-based classification. The influence of the statistical modeling is assessed by comparing the results using the Bhattacharyya distance between multivariate Gaussian distributions for amplitude data. The results with simulated data indicate that the proposed classification method has a very good performance when the data follow the Wishart model. The proposed classifier also performs better than the per-pixel/contextual classifier and the Bhattacharyya Gaussian distance using SIR-C PolSAR data.

show abstract

Hierarchical segmentation of Polarimetric SAR images using heterogeneous clutter models

Cited by 24 publications

References 29 publications

Hierarchical semantic model and scattering mechanism based PolSAR image classification

Hierarchical semantic model and scattering mechanism based PolSAR image classification

Unsupervised Speckle Level Estimation of SAR Images Using Texture Analysis and AR Model

Classification of Segments in PolSAR Imagery by Minimum Stochastic Distances Between Wishart Distributions

Contact Info

Product

Resources

About