Polarimetric Synthetic Aperture Radar Applications Research Articles

Channel Imbalance Calibration Based on the Zero Helix of Bragg-like Targets

The calibration of channel imbalances is currently the main concern in polarimetric calibration (POLCAL) since the crosstalk of recent polarimetric synthetic aperture radar (Pol-SAR) systems is lower than −20 dB. The existing channel imbalance calibration method without corner reflectors utilizes both volume-dominated and Bragg-like targets. However, there are two limitations to using volume-dominated targets. One is that the inaccurate selection of volume-dominated areas in the uncalibrated Pol-SAR images has a negative influence on the estimation of cross-polarization (x-pol) channel imbalance, which subsequently impacts the estimation of copolarization (copol) channel imbalance. The other is that there are minimal volume-dominated areas in some special applications of Pol-SAR, such as planetary exploration. Thus, only selecting Bragg-like targets to estimate the values of both transmitting and receiving channel imbalances, which is proposed in this paper, can avoid the uncertainty brought about by selecting other distributed targets in an uncalibrated imaginary. In addition, the reciprocity assumption and characteristics corresponding to H/α¯ decomposition are introduced to eliminate the phase ambiguity for the first time. Compared with previous methods, our method had an obvious advantage in terms of universality, since Bragg-like targets are common in the most illuminating areas. The novel method was applied to both the simulated data from the L-band Advanced Land Observing Satellite (ALOS) and C-band GaoFen-3 (GF-3), and to real data with corner reflectors on site. The results from the simulated data showed that the errors of the amplitude and phase estimation were less than 0.5 dB and 5.0° in most topographical features. Meanwhile, the VV/HH terms from all trihedral corner reflectors were less than 0.3 dB for amplitude, and 5.5° for phase after calibration by using the estimated channel imbalances.

A Generalized Geodesic Distance-Based Approach for Analysis of SAR Observations Across Polarimetric Modes

Present and future sensors are diversifying from traditional quad polarimetric mode of synthetic aperture radar acquisition. Thus, an approach that is interpretative in nature and applicable across polarimetric modes is required. In this context, the geodesic distance (GD)-based approach within the polarimetric synthetic aperture radar (PolSAR) literature is seen as an eigenvalue-decomposition free approach to interpret and analyze quad PolSAR data. This approach is highly adaptive toward applications due to its ability to compare the SAR observation with a known scatterer/model, or with another SAR observation in general providing a means for direct interpretation. In this work, we show that the GD (originally defined for the quad polarization mode) is generalizable across any arbitrary SAR polarimetric mode while retaining its simple form for ready computation. We show that the GD-based approach provides level ground for comparison of different polarimetric modes given a fixed application. We demonstrate it using change detection as the chosen application. In addition, we show how the behavior of the three roll-invariant GD-based parameters change under different polarimetric modes (e.g., quad, dual, and compact polarization modes). We also discuss how the GD-based approach can also be adapted to ground range detected (GRD) product data, which is presently available from Sentinel-1 and widely used in many applications. However, in this case, we show that only one of the three GD-derived parameters can be defined. We believe this work will make the GD-based approach important for present and future PolSAR applications cutting across sensors and its available polarimetric modes.

A hybrid network for PolSAR image classification based on polarization orientation angles

ABSTRACT Polarimetric synthetic aperture radar (PolSAR) image classification is a significant task of PolSAR applications. In recent years, deep learning-based methods using spatial features have achieved satisfactory results in PolSAR classification. However, there are still some important features left to be exploited. One is the target scattering orientation diversity feature that contains rich hidden information. In this letter, a hybrid network is proposed to model the target scattering orientation diversity feature and spatial feature. First, the polarimetric scoherency matrix is expanded to polarization coherency matrix sequence by different polarization orientation angles (POAs). Then, the long short-term memory (LSTM) network and the convolutional neural networks (CNN) are proposed to process the polarization coherency matrix sequence and the square neighbourhood of pixels, respectively. Finally, the features of the two sub-networks are combined to improve the classification accuracy. The experiments demonstrate that the proposed method can obtain superior and robust performance.

Exploring Vision Transformers for Polarimetric SAR Image Classification

As one of the most popular topics in polarimetric synthetic aperture radar (PolSAR) community, PolSAR image classification has always been an important way for PolSAR applications. Constructing representations is the most critical part of PolSAR image classification. With the maturity of deep learning technique, many data-driven PolSAR representation methods have been proposed, most of which are based on convolutional neural networks (CNNs). Despite some achievements, the bottleneck of CNN-based methods may be related to the locality induced by their inductive biases. Considering this problem, the state-of-the-art method in natural language processing, i.e., transformer, is introduced into PolSAR image classification for the first time. Specifically, a vision transformer (ViT)-based representation learning framework is proposed in this article, which covers both supervised learning and unsupervised learning. For supervised learning, we use self-attention to replace convolution, which shifts the focus from the information in local neighborhoods to the long-range interactions between each pixel. Beyond supervised learning, we introduce an improved contrastive-based strategy to implement simple unsupervised representation learning. Compared with CNN and its variants, ViT constructs more global representations by explicitly modeling the relationship between each pixel, so as to improve the classification performance. Experimental results on four widely used PolSAR image datasets indicate that the representation obtained by the ViT-based methods is better for PolSAR image classification, whether supervised (up to about 5% accuracy improvement) or unsupervised (up to about 4%). In addition, we also prove the robustness of ViT to the initial input form. These discoveries may arouse rethinking of the dominance of CNNs in PolSAR image classification.

A Dual-Band Dual-Polarized Antenna with Improved Isolation Characteristics for Polarimetric SAR Applications

A dual-band dual-polarized antenna with high isolation characteristics is proposed for polarimetric synthetic aperture radar (PolSAR) applications. The antenna consists of four dipole antennas and 2 × 2 patch antenna arrays operating at the P-band (450–730 MHz) and Ka-band (34–36 GHz), respectively. The dipole antennas and the patch antenna arrays need dual-linear polarization characteristics to acquire PolSAR data. Improvements in the isolation characteristics at the P-band are achieved by inserting a metamaterial absorber with a fractal geometry between the transmitting (Tx) and receiving (Rx) dipole antennas. Without the absorber, the simulated isolation characteristics between the Tx and Rx antennas are lower than 19.2 dB over the target band. On the other hand, with the absorbers, the simulated isolation characteristics are higher than 23.44 dB over the target band, and remarkable improvement is achieved around the resonance frequency of the absorber. The measured results are in good agreement with the simulated ones, showing that the proposed antenna can be a good candidate for PolSAR applications.

A General Feature Paradigm for Unsupervised Cross-Domain PolSAR Image Classification

Limited labels and increasing multisource data promote domain adaptation (DA) problem as a challenging study for polarimetric synthetic aperture radar (PolSAR) interpretation. Existing DAs for optical images cannot generalize over PolSAR imagery due to its special side-imaging characteristics and complex distribution shifts. In this letter, a general feature paradigm (GFP) is proposed for unsupervised cross-domain PolSAR image classification. The GFP is based on a key observation that interclass aggregation is optimized after four-step feature transformations. This key observation leads to GFP that not only reduces the domain shifts but also compatible with typical DA methods. The GFPs are conducted on both source and target domain by unsupervised manner, including polarimetric basis extraction, the Wishart clustering, histogram statistics, and dimensionality reduction. After these transformations, the unlabeled target PolSAR image can be classified based on obtained GFP, DA, and limited labeled samples only from the source domain. Extensive unsupervised cross-domain experiments on 27 scenarios verified that GFP leads to at most 93.76% accuracy for full- and dual-polarized synthetic aperture radar (SAR) images’ classification. Moreover, the GFP shed light on extensive cross-domain PolSAR applications about built-up areas, vegetation, and bare land analysis.

Scattering Feature-Driven Superpixel Segmentation for Polarimetric SAR Images

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a fundamental role in various PolSAR applications. Subject to the intrinsic limitations, the existing methods generally produce over or undersegmented superpixels in highly complex scenes of PolSAR images. In this article, we propose an efficient and effective scattering feature-driven superpixel segmentation method for PolSAR images, which is capable of preserving the global structure information and producing superpixels with both high boundary adherence and visual compactness. First, a hierarchical version of the refined five-component decomposition is proposed. The derived scattering features along with other well-used features are then combined to construct a low-dimensional feature vector. Second, a modified normalized cuts formulation using a distance measurement is presented, in which the feature similarity and the space proximity are both considered. During the superpixel segmentation, the edge information derived from our scattering mechanism-optimal contrast-based edge detector is incorporated. On this basis, a tradeoff factor according to the edge information and the equivalent number of looks is determined, which balances the relationship of feature similarity and space proximity so as to adaptively control the size and shape of superpixels. The performance of the proposed method is demonstrated and evaluated with fully PolSAR data over different test sites. The outputs show that the proposed method outperforms the state-of-the-art methods and the produced superpixels scale well especially for heterogeneous scattering cases.

Satellite Imagery for Classification of Rice Growth Phase Using Freeman Decomposition in Indramayu, West Java, Indonesia

Monitoring at every growth of rice plants is an important information for determining the grain pro-duction estimation of rice. Monitoring must to be have timely work on the rice plant development. However, timely monitoring and the high accuracy of information is a challenge in remote sensing based on rice agriculture monitoring and observation. With increased quality of synthetic aperture radar (SAR) systems utilizing polarimetric information recently, the development and applications of polarimetric SAR (PolSAR) are one of the current major topics in radar remote sensing. The ad-vantages provided by PolSAR data for agricultural monitoring have been extensively studied for applications such as crop type classification and mapping, crop phenology monitoring, productivity assessment based on the sensitivity of polarimetric parameters to indicators of crop conditions. Freeman and Durden successfully decomposed fully PolSAR data into three components: Single bounce, double bounce, and volume scattering. The three-component scattering provide features for distinguishing between different surface cover types. These sensitivities assist in the identification of growing phase. The observed growing phase development in time series, reflected in the consistent temporal trends in scattering, was generally in agreement with crop phenological development stages. Supervised classification was performed on repeat-pass Radarsat-2 images, with an overall classification accuracy of 77.27% achieved using time series Fine beam data. The study demonstrated that Radarsat-2 Fine mode data provide useful information for crop monitoring and classification of rice plants.

Enhanced edge detection for polarimetric SAR images using a directional span-driven adaptive window

ABSTRACTAutomatic edge detection for polarimetric synthetic aperture radar (PolSAR) images plays a fundamental role in various PolSAR applications. The classic methods apply the fixed-shape windows to detect the edges, whereas their performance is limited in heterogeneous areas. This article presents an enhanced edge detection method for PolSAR data based on the directional span-driven adaptive (DSDA) window. The DSDA window has variable sizes and flexible shapes, and is constructed by adaptively selecting samples that follow the same statistical distribution. Therefore, it can overcome the limitation of classic fixed-shape windows. To obtain refined and reliable edge detection results in heterogeneous urban areas, we adopt the spherically invariant random vector (SIRV) product model since the complex Wishart distribution is often not met. In addition, a span ratio is combined with the SIRV distance to highlight the dissimilarity measure and to improve the robustness of the proposed method. The simulated PolSAR data and three real data sets from experimental synthetic aperture radar, electromagnetics institute synthetic aperture radar, and Radarsat-2 systems are used to validate the performance of the enhanced edge detector. Both quantitative evaluation and visual presentation of the results demonstrate the effectiveness of the proposed method and its superiority over the classic edge detectors.

Radar Image Colorization: Converting Single-Polarization to Fully Polarimetric Using Deep Neural Networks

Numerous radar polarimetry theories and polarimetric synthetic aperture radar (PolSAR) processing methods have been developed. However, the vast majority of SAR images are not fully polarimetric (full-pol). This paper proposes “radar image colorization” to reconstruct a full-pol image from a non-full-pol image, so that existing PolSAR methods, such as model-based decomposition and unsupervised classification, can be directly applied to the reconstructed full-pol SAR images. It proposes to train a specially designed deep neural network to convert a single polarization gray-scale SAR image to full-pol. It consists of two components: a feature extractor network to extract hierarchical multi-scale spatial features of the gray-scale SAR image, followed by a feature translator network to map spatial feature to polarimetric feature with which the polarimetric covariance matrix of each pixel can be reconstructed. Both qualitative and quantitative experiments with real full-pol data are conducted to show the efficacy of the proposed method. The reconstructed full-pol SAR image agrees well with the true full-pol image, not only in the sense of visual similarity but also in the sense of real PolSAR applications, such as target decomposition and terrain classification.

Polarimetric synthetic aperture radar application for tropical peatlands classification: a case study in Siak River Transect, Riau Province, Indonesia

Mapping spatial distributions of tropical peatlands is important for properly estimating carbon emissions and for providing information that aids in the sustainable management of tropical peatlands, particularly in Indonesia. This study evaluated the performance of phased array type L-band synthetic aperture radar (SAR) (PALSAR) dual-polarization and fully polarimetric data for tropical peatlands classification. The study area was in Siak River Transect, Riau Province, Indonesia, a rapidly developing region, where the peatland has been intensively converted mostly into oil palm plantations over the last two decades. Thus, polarimetric features derived after polarimetric decompositions, backscatter coefficients measurements, and the radar vegetation index were evaluated to classify tropical peatlands using the decision tree classifier. Overall, polarimetric features generated by the combination of dual-polarization and fully polarimetric data yielded an overall accuracy (OA) of 69% and a kappa coefficient (K) of 0.57. The integration of an additional feature, “distance to river,” to the algorithm increased the OA to 76% and K to 0.66. These results indicated that the methodology in this study might serve as an efficient tool in tropical peatlands classification, especially when involving the use of L-band SAR dual-polarization and fully polarimetric data.

Analysis of different polarimetric target decomposition methods in forest density classification using C band SAR data

ABSTRACTThe ability of synthetic aperture radar (SAR) C-band microwave energy to penetrate within forest vegetation makes it possible to extract information on crown components, which in turn gives a better approximation of relative canopy density than optical data-derived canopy density. Many studies have been reported to estimate forest biomass from SAR data, but the scope of C-band SAR in characterizing forest canopy density has not been adequately understood with polarimetric techniques. Polarimetric classification is one of the most significant applications of polarimetric SAR in remote sensing. The objective of the present study was to evaluate the feasibility of different polarimetric SAR data decomposition methods in forest canopy density classification using C-band SAR data. Landsat (Land Satellite) 5 TM (Thematic Mapper) data of the same area has been used as optical data to compare the classification result. RADARSAT (Radar Satellite)-2 image with fine quad-pol obtained on 27 October 2011 over tropical dry forests of Madhav National Park, India, was used for the analysis of full polarimetric data. Six decomposition methods were selected based on incoherent decomposition for generating input images for classification, i.e. Huynen, Freeman and Durden, Yamaguchi, Cloude, Van zyl, and H/A/α. The performance of each decomposition output in relation to each land cover unit present in the study area was assessed using a support vector machine (SVM) classifier. Results show that Yamaguchi 4-component decomposition (overall accuracy 87.66% and kappa coefficient (κ) 0.86) gives better classification results, followed by Van Zyl decomposition (overall accuracy 87.20% and κ 0.85) and Freeman and Durden (overall accuracy 86.79% and κ 0.85) in forest canopy density classification. Both model-based decompositions (Freeman and Durden and Yamaguchi4) registered good classification accuracy. In eigenvector or eigenvalue decompositions, Van zyl registered the second highest accuracy among different decompositions. The experimental results obtained with polarimetric C-band SAR data over a tropical dry deciduous forest area imply that SAR data have significant potential for estimating canopy density in operational forestry. A better forest density classification result can be achieved within the forest mask (without other land cover classes). The limitations associated with optical data such as non-availability of cloud-free data and misclassification because of gregarious occurrence of bushy vegetation such as Lantana can be overcome by using C-band SAR data.