High-resolution Polarimetric Synthetic Aperture Radar Images Research Articles

Low-Resolution Fully Polarimetric SAR and High-Resolution Single-Polarization SAR Image Fusion Network

The data fusion technology aims to aggregate the characteristics of different data and to obtain products with multiple data advantages. To solve the problem of reduced resolution of polarimetric synthetic aperture radar (PolSAR) images due to system limitations, we propose a fully PolSAR images and single-polarization synthetic aperture radar (SinSAR) images fusion network to generate high-resolution PolSAR (HR-PolSAR) images. To take advantage of the polarimetric information of the low-resolution PolSAR (LR-PolSAR) images and the spatial information of the high-resolution single-polarization SAR (HR-SinSAR) images, we propose a fusion framework for joint LR-PolSAR images and HR-SinSAR images and design a cross-attention mechanism to extract features from the joint input data. Besides, based on the physical imaging mechanism, we designed the PolSAR polarimetric loss functions for constrained network training. The experimental results confirm the superiority of the fusion network over traditional algorithms. The average peak signal-to-noise ratio (PSNR) is increased by more than 3.6 dB, and the average mean absolute error (MAE) is reduced to less than 0.07. Experiments on polarimetric decomposition and polarimetric signature show that it maintains polarimetric information well.

MP-ResNet: Multipath Residual Network for the Semantic Segmentation of High-Resolution PolSAR Images

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the inference of speckle noises. The Gaofen contest has provided open access of a high-quality PolSAR semantic segmentation dataset. Taking this chance, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to make the best use of the features learned from its different branches. Ablation studies show that the MPResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, whereas its computational costs are not much increased. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

SIRV-Based High-Resolution PolSAR Image Speckle Suppression via Dual-Domain Filtering

This paper presents a spherically invariant random vector (SIRV)-based dual-domain filter for polarimetric synthetic aperture radar (PolSAR) speckle suppression. The SIRV model is a simple clutter decomposition model designed for heterogeneous scenes that decomposes the clutter into two independent domains: the texture domain and the polarimetric domain (also known as the speckle domain). The dual-domain filter takes full advantage of the SIRV model to decompose the task of PolSAR speckle suppression into polarimetric domain filtering and texture domain filtering. The polarimetric domain filtering involves estimating a stable state of the normalized coherency matrix with similar samples via fixed-point iteration. For this purpose, the nonlocal patch matching distance measure and the cutoff threshold in the SIRV model case are defined to select similar samples. The texture domain filtering involves reconstructing a sparse texture image without the effect of speckle. For this purpose, patch ordering-based SAR image despeckling via transform-domain filtering (SAR-POTDF), which is based on simultaneous sparse coding (SSC), is applied for the texture filtering. After the dual-domain filtering, a speckle-free PolSAR image can be reconstructed by the product of the texture and the normalized coherency matrix. The effectiveness and robustness of the proposed method was demonstrated by experiments undertaken with CETC-38 X-band, DLR F-SAR S-band, and IECAS C-band high-resolution PolSAR images. The DLR E-SAR L-band medium-resolution data were also used for comparison. The results showed that the dual-domain filtering is effective for the speckle suppression of high-resolution PolSAR images with heterogeneous and detailed scenes.

High-Resolution PolSAR Image Interpretation Based on Human Image Cognition Mechanism

Since the all-day and all-weather working characteristics, polarimetric synthetic aperture radar (PolSAR) has been widely used in many application for earth observation. PolSAR system can acquire targets scattering information under different polarization patterns and obtain detailed information, such as physical characteristics, spatial distribution and direction of the targets, etc. However, in high-resolution PolSAR images, the scattering characteristics of targets are very sophisticated, and different parts of the same target may present different scattering mechanisms. As a result, traditional interpretation technologies are sometimes not applicable in a high-resolution PolSAR scenario. Recently, many artificial intelligence algorithms that simulate the scheme of human cognition have been developed and they have great significance for efficient, intelligent, and accurate images interpretation. In this paper, based on human cognition theory and taking into account the characteristics of targets in PolSAR images, an algorithm for the interpretation of various targets in high-resolution PolSAR images is presented. In this paper, a “perception–reasoning–decision” cognition model is built following the cognition process of professional PolSAR image interpreters. In addition, with the help of theories such as multilevel image segmentation, fuzzy logic, neural network, and the context semantic characteristics, the mathematical model is established and implemented. The proposed method is performed on several sets of PolSAR images obtained under different imaging conditions and is validated by comparing with existing classification methods. The results show that the proposed method can effectively improve the identification of targets from PolSAR images.

Iceberg Detection in Open and Ice-Infested Waters Using C-Band Polarimetric Synthetic Aperture Radar

Icebergs can cause a significant threat to shipping, offshore oil and gas production facilities, and subsea pipelines. Synthetic aperture radar (SAR) is a well-established tool for detecting and monitoring sea-ice objects in the often dark and cloud-covered polar regions. However, detection of small icebergs floating in nonhomegeous sea clutter environments is still a challenging task. We propose a new methodology for automatic identification of potential icebergs in high-resolution polarimetric SAR images. The algorithm adopts to various sea-ice conditions and it tackles high iceberg density situations and heterogeneous background conditions in the marginal ice zone. Results from a time series of RADARSAT-2 data containing numerous icebergs broken off from glaciers in Kongsfjorden on Svalbard demonstrate that the approach is viable.

Level Set Segmentation Algorithm for High-Resolution Polarimetric SAR Images Based on a Heterogeneous Clutter Model

In this paper, a heterogeneous clutter model named ${\mathcal L}$ distribution is introduced into the level set method for segmentation of high-resolution polarimetric synthetic aperture radar (PolSAR) images. Level set methods are robust and effective techniques for segmentation. However, traditional level set methods for PolSAR data are based on the complex Wishart distribution, which is not an applicable model to high-resolution PolSAR images and heterogeneous regions such as forest and urban areas. The ${\mathcal L}$ distribution is proved to be a highly flexible model for multilook PolSAR data, which is based on the product model with a generalized-gamma-distributed texture component. The ${\mathcal L}$ -model-based level set segmentation method is assessed using C-band, X-band, and L-band PolSAR data acquired by RADARSAT-2, TerraSAR-X, and ESAR sensors, respectively. Experimental results show that the ${\mathcal L}$ -distribution model has a better capacity for characterizing high-resolution PolSAR data, especially for extremely heterogeneous regions. Compared with the Wishart-model-based and Kummer-U-model-based level set methods and Markov random field based methods, it is observed that the proposed level set algorithm can obtain more precise segmentation results.

Effects of BOW Model With Affinity Propagation and Spatial Pyramid Matching on Polarimetric SAR Image Classification

The bag of visual words (BOW) model has attracted a great deal of attention in high-resolution remote sensing image classification. Related studies based on polarimetric synthetic aperture radar (PolSAR) image classification are also still challenging. This paper presents a new method of PolSAR image classification based on the BOW model and supplemented by an affinity propagation clustering algorithm (AP), as well as a spatial pyramid matching (SPM) technique (AP_SPM_BOW). Its classification effect is analyzed compared to those of BOW models with other clustering algorithms (e.g., K -means, meanshift, Gaussian mixture model), as well as the ML classification method by using two types of PolSAR images with different resolutions collected from EMISAR and RADARSAT-2 sensors. These results demonstrate that the proposed AP_SPM_BOW model is not only a stable and effective tool for PolSAR image classification but also more suitable for the analysis of high-resolution PolSAR images. In addition, the use of polarimetric information in BOW models can effectively improve the classification accuracy.

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Segmentation techniques play an important role in understanding high-resolution polarimetric synthetic aperture radar (PolSAR) images. PolSAR image segmentation is widely used as a preprocessing step for subsequent classification, scene interpretation and extraction of surface parameters. However, speckle noise and rich spatial features of heterogeneous regions lead to blurred boundaries of high-resolution PolSAR image segmentation. A novel segmentation algorithm is proposed in this study in order to address the problem and to obtain accurate and precise segmentation results. This method integrates statistical features into a fractal net evolution algorithm (FNEA) framework, and incorporates polarimetric features into a simple linear iterative clustering (SLIC) superpixel generation algorithm. First, spectral heterogeneity in the traditional FNEA is substituted by the G0 distribution statistical heterogeneity in order to combine the shape and statistical features of PolSAR data. The statistical heterogeneity between two adjacent image objects is measured using a log likelihood function. Second, a modified SLIC algorithm is utilized to generate compact superpixels as the initial samples for the G0 statistical model, which substitutes the polarimetric distance of the Pauli RGB composition for the CIELAB color distance. The segmentation results were obtained by weighting the G0 statistical feature and the shape features, based on the FNEA framework. The validity and applicability of the proposed method was verified with extensive experiments on simulated data and three real-world high-resolution PolSAR images from airborne multi-look ESAR, spaceborne single-look RADARSAT-2, and multi-look TerraSAR-X data sets. The experimental results indicate that the proposed method obtains more accurate and precise segmentation results than the other methods for high-resolution PolSAR images.

Application of Mixture Regression for Improved Polarimetric SAR Speckle Filtering

Speckle filtering is an indispensable operation in synthetic aperture radar (SAR) image processing but one which inevitably reduces image resolution. In order to preserve the intrinsic target features, adaptive speckle filters have been developed using weighted averages commensurate with the similarity of the target statistics. The target statistics are commonly derived from a prefiltering step which suffers from residue speckle contamination and feature smearing. In this paper, we adopted finite mixture models to characterize the observed in-scene variation and proposed a rigorous and progressive mixture regression method to better estimate the target statistics. The mixture model once fitted is able to capture the statistical properties of the highly textured and heterogeneous target variation, which is often observed in high-resolution SAR images. A nonlocal mean method is used for robust similarity evaluation of the local variation patterns between small image patches. The goal is to develop an improved polarimetric SAR (PolSAR) speckle filter that can accomplish a solid balance between speckle suppression and feature preservation. With the proposed filter, distinct scattering mechanisms and small-scale target features are retained from the start, even with single-look complex PolSAR observations. We test the algorithm using simulated data and single-look high-resolution PolSAR images: one acquired by DLR's F-SAR system and one by DLR's E-SAR system.

Spherical Symmetry of Complex Stochastic Models in Multivariate High-Resolution PolSAR Images

The multiplicative model, expressed as a product between the square root of a scalar positive quantity (texture) and the description of an equivalent homogeneous surface (speckle), is one of the most appropriate and disseminated models used to describe high-resolution polarimetric synthetic aperture radar (PolSAR) clutter. Generally, the texture is assumed polarization independent, which causes PolSAR data to present a spherical symmetry property, allowing for the usage of most of the algorithms present in the literature. Nevertheless, the existence of polarization-dependent clutter has also been reported, for which specific algorithms need to be derived. Therefore, it becomes clear that the first step in SAR data analysis should be the validation of the model employed. Within this context, this paper presents a new methodological framework to assess the conformity of multivariate high-resolution SAR data with respect to the product model in terms of asymptotic statistics. More precisely, spherical symmetry is investigated by applying statistical hypothesis testing on the structure of the quadricovariance matrix. Simulated data, data from the P-band airborne data set acquired by the Office National d'Etudes et de Recherches Aerospatiales (ONERA) over the French Guiana in 2009 in the frame of the European Space Agency campaign TropiSAR and a RAMSES X-band image acquired over Bretigny, France, are taken into consideration to investigate the performance of the derived test. The detection results are qualitatively and quantitatively analyzed, and some important conclusions are drawn regarding the methodology employed in analyzing SAR data.

Classification of Terrain by Implementing the Correlation Coefficient in the Circular Polarization Basis Using X-Band POLSAR Data

Classification of terrain is one of the most important applications of Polarimetric Synthetic Aperture Radar (POLSAR) image analysis. This paper presents a simple method to classify terrain by the use of the correlation coefficients in the circular polarization basis together with the total power of the scattering matrix in the X-band. The reflection symmetry condition that the co-polarized and the cross-polarized correlations are close to zero for natural distributed scatterers is utilized to extract characteristic parameters of small forests or cluster of trees, and oriented urban building blocks with respect to the direction of the radar illumination. Both of these kinds of scatterers are difficult to identify in high resolution POLSAR images of complex urban areas. The indices employed here are the correlation coefficient, a modified coefficient normalized by the reflection symmetric conditional case, and the total power. It is shown that forest areas and oriented building blocks are easily detected and identified. The terrain classification yielded by these combinations is very accurate as confirmed by photographic ground truth images.