Polarimetric Synthetic Aperture Research Articles

Object-oriented polarimetric SAR image classification via the combination of a pixel-based classifier and a region growing technique

ABSTRACT Land-cover type interpretation by the use of remote sensing image classification techniques is always a hot topic. In this paper, an object-oriented method is presented for fully polarimetric synthetic aperture radar (SAR) image classification. Differing from most of the traditional object-oriented classification algorithms, the proposed method employs an innovative classification strategy that combines a pixel-based classifier and a region growing technique. Firstly, taking each individual pixel as a seed pixel, the homogeneous areas are extracted by a region growing technique. Then, using the information of the pixel-based classification result, the pixels located in each homogeneous area are all assigned to a certain class. Finally, the majority voting strategy is deployed to determine the final class label of each pixel. The experiments conducted on two fully polarimetric SAR images reveal that the proposed classification scheme can obtain pleasing classification accuracy and can provide the classification maps with more homogeneous regions than pixel-based classification.

Interpreting the Response of Forest Stock Volume with Dual Polarization SAR Images in Boreal Coniferous Planted Forest in the Non-Growing Season

Polarimetric Synthetic Aperture Radar (PolSAR) images with dual polarization modes have great potential to map forest stock volume (FSV) by excellent penetration capabilities and distinct microwave scattering processes. However, the response of these SAR data to FSV is still uncertain in the non-growing season. To further interpret the response of FSV to different dual polarization SAR images, three types of dual polarization SAR images (GF-3, Sentinel-1, and ALOS-2) were initially acquired in coniferous planted forest in the non-growing season. Then, sensitivity between FSV and all alternative features extracted from each type of SAR image was analyzed to express the response of FSV to dual polarization SAR images with bands and polarization modes in the non-growing season in deciduous (Larch) and evergreen (Chinese pine) forests. Finally, mapped FSV using single and combined dual polarization images were derived by optimal feature sets and four machine learning models, respectively. The combined effects were also analyzed to clarify the difference of bands and polarization modes in deciduous and evergreen forests in the non-growing season. The results demonstrated that the backscattering energy from different sensors is significantly different in Chinese pine, and the difference is gradually reduced in Larch forests. It is also implied that the polarization mode is more important than penetration capability in mapping forest FSV in deciduous forest in the non-growing season. By comparing the accuracy of mapped FSV using single and combined images, combined images have more capability to improve the accuracy and reliability of mapped FSV. Meanwhile, it is confirmed that compensation effects with bands and polarization modes not only have great potential to delay the saturation phenomenon, but also have the capability to reduce errors caused by overestimation.

Abandoned Land Mapping Based on Spatiotemporal Features from PolSAR Data via Deep Learning Methods

Monitoring agricultural abandonment is essential in understanding the effects on the environment and food security. Polarimetric synthetic aperture radar (PolSAR) is an efficient approach for the monitoring of large-scale agricultural land cover in cloudy and rainy areas. However, previous studies have not taken advantage of the valuable phase information and not fully utilized the spatiotemporal features of farmland parcels, which has seriously limited the abandoned land identification accuracy. In this study, we developed a new method for the mapping of abandoned land based on the spatiotemporal features from PolSAR Single Look Complex (SLC) images via deep learning methods. First, backscattering coefficients (σ0VV, σ0VH) were derived, and the polarimetric parameters (entropy, anisotropy and mean alpha angle) were obtained based on Cloude–Pottier polarimetric decomposition. Then, the VGG16 deep convolutional network was innovatively used to extract spatial features from both the backscattering coefficients and polarimetric parameters. Next, the separability index was calculated to select the most effective spatial features. Finally, LSTM classifications were conducted based on the time series of backscattering features, the polarimetric parameters, the extracted spatial features and their combinations. The results showed that the introduction of multitemporal polarimetric parameters and spatial features both led to an improvement in the abandoned land identification accuracy. The combination of backscattering features, polarimetric parameters and spatial features yielded the best performance in identifying abandoned land, with producer’s accuracy of 88.29% and user’s accuracy of 84.03%. This study demonstrated the potential of polarimetric parameters and validated the effectiveness of spatiotemporal features in abandoned land identification. It provided a practical method for the production of a highly reliable abandoned land mapping in cloudy and rainy areas.

Difference-guided multiscale graph convolution network for unsupervised change detection in PolSAR images

Image change detection is important in polarimetric synthetic aperture radar (PolSAR) image analysis and interpretation. However, improving its accuracy is challenging because of the interference of multiplicative speckle noise. To address this issue, we propose an unsupervised PolSAR image change detection method based on a multiscale graph convolutional network (GCN). First, a Shannon entropy difference image is introduced and improved to obtain an enhanced difference image (EDI) that can effectively suppress speckle noise while preserving edge information. The generated EDI can be further utilised to construct a pseudo-label set required for unsupervised change detection. Subsequently, a difference constraint joint graph construction (DCJGC) module is proposed to obtain the object-level input information of the network. This uses the joint superpixels of multitemporal PolSAR images as graph nodes, and then introduces the difference information in the EDI to constrain the formation process of the edges between the nodes, efficiently and accurately constructing undirected graphs. Finally, a difference-guided multiscale GCN (DGMGCN) is designed for PolSAR image change detection. The network utilises difference information to eliminate the adverse effect of speckle noise on change detection and fully capture the change-aware features of multitemporal PolSAR images at fine and coarse scales, thereby improving feature discriminability. Experimental results on six real Gaofen-3 PolSAR datasets validate the superiority of the proposed approach over other state-of-the-art methods.

Unsupervised Classification of Non-Gaussian Terrain Based on Polarimetric Decomposition

Polarimetric synthetic aperture radar (PolSAR) can provide complete polarization property of terrain. Terrain classification is the most common application of PolSAR data. In this paper, an unsupervised clustering algorithm based on Freeman-Durden decomposition (FDD) and a non-Gaussian K-Wishart distribution classifier is proposed. This algorithm combines an advanced statistical distribution with spatial polarization scattering information of multi-looks PolSAR data. We use the prior probability characteristics of the Markov random field model to adaptively adjust the cluster center to make the classification more accurate. The experiment result shows that the proposed algorithm based on non-Gaussian models can better retain the polarization information of the target and the clustering accuracy was effectively improved on the real SAR images.

A Review of Forest Height Inversion by PolInSAR: Theory, Advances, and Perspectives

Forests cover approximately one-third of the Earth’s land surface and constitute the core region of the carbon cycle on Earth. The paramount importance and multi-purpose applications of forest monitoring have gained widespread recognition over recent decades. Polarimetric synthetic aperture radar interferometry (PolInSAR) has been demonstrated as a promising technique to retrieve the forest height over large areas with a limited cost. This paper presents an overview of forest height inversion (FHI) techniques based on PolInSAR data. Firstly, we introduce the basic theories of PolInSAR and FHI procedures. Next, we review the established data-based algorithms for single-baseline data and describe innovative techniques related to multi-baseline data. Then, the model-based algorithms are also introduced with their corresponding forest scattering models under multiple data acquisition modes. Subsequently, a case study is presented to demonstrate the applicable scenarios and advantages of different algorithms. Model-based algorithms can provide accurate results when the scene and forest properties are well understood and the model assumptions are valid. Data-based algorithms, on the other hand, can handle complex scattering scenarios and are generally more robust to uncertainties in the input parameters. Finally, the prospect of forest height inversion was analyzed. It is our hope that this review will provide guidelines to future researchers to enhance further FHI algorithmic developments.

Adaptive Speckle Filter for Multi-Temporal PolSAR Image with Multi-Dimensional Information Fusion

Polarimetric synthetic aperture radar (PolSAR) is an important sensor for earth observation. Multi-temporal PolSAR images obtained by successive observations of the region of interest contain rich polarimetric–temporal–spatial information of the land covers, which has wide applications. Speckle filtering becomes a necessary pre-processing for many subsequent applications. Currently, it is common to filter multi-temporal PolSAR data by directly using a speckle filter developed for single SAR or PolSAR data. The cross-correlation between different time series contains rich information in multi-temporal PolSAR images. How to utilize complete polarimetric–temporal–spatial information becomes a large challenge to achieve more satisfied performances of speckle reduction and details preservation simultaneously. This work dedicates to this issue and develops a novel speckle filtering approach for multi-temporal PolSAR data by multi-dimensional information fusion. The core idea is to establish an adaptive and efficient strategy of similar pixel selection based on the similarity test of multi-temporal polarimetric covariance matrices. This similar pixel selection scheme fuses the complete information of multi-temporal PolSAR data. The sensitivity of the proposed scheme is demonstrated with several typical and challenging texture patterns. Then, an adaptive speckle filter is established specifically for multi-temporal PolSAR data. Intensive comparison studies are carried out with airborne UAVSAR datasets and spaceborne ALOS/PALSAR datasets. Quantitative investigations in terms of the equivalent number of looks (ENL) and the figure of merit (FOM) indexes demonstrate and validate the superiority of the proposed method.

A polarimetric projection-based scattering characteristics extraction tool and its application to PolSAR image classification

It is necessary to adequately extract scattering characteristics from polarimetric synthetic aperture radar (PolSAR) data for land-cover classification. Current interpretation technologies, such as target decompositions, polarimetric signatures, and polarimetric coherence patterns, have been widely used to explore polarization information. However, because limited scattering models are used to characterize all ground targets, these methods are occasionally limited in the interpretation of PolSAR data. This may reduce the accuracy of the land-cover classification. In this study, we attempted to extract the scattering characteristics through another novel method. We understand the PolSAR image interpretation as the projection of the scattering model on the measured matrix. Current methods project only a limited series of scattering models onto a measured matrix. To complement current methods of PolSAR image interpretation, we propose a polarimetric projection-based scattering characteristics extraction (PPSCE) method. It projects scattering models consisting of four changing independent polarization parameters onto the measured matrix. These scattering models, associated with the geometric and physical properties of the ground targets, correspond to the entire polarization space. The PPSCE method, meanwhile, extracts polarization information sufficiently. L-band UAVSAR, C-band Radarsat-2, and P-band AIRSAR images of classical experimental areas are used to validate the PPSCE method. The results show that the proposed PPSCE method can present polarization information that is difficult to investigate by the existing methods. In addition, the scattering features derived using the PPSCE method are superior for land-cover classification. Compared to the classification results based on the coherency matrix and Wishart classifier, the proposed method improves the overall classification accuracy by 23.56% for UAVSAR data. Compared to target decompositions and polarization signatures, the overall classification accuracy of the proposed method is increased by 29.32% (RF) and 22.63% (SVM) for UAVSAR data, 7.96% (RF) and 4.36% (RF) for Radarsat-2 and AIRSAR datasets, respectively. Furthermore, the proposed method has significant potential for soil moisture inversion. https://rgdoi.net/10.13140/RG.2.2.14091.26409.

Solid Angle Geometry-Based Modeling of Volume Scattering with Application in the Adaptive Decomposition of GF-3 Data of Sea Ice in Antarctica

Over the last two decades, spaceborne polarimetric synthetic aperture radar (PolSAR) has been widely used to penetrate sea ice surfaces to achieve fully polarimetric high-resolution imaging at all times of day and in a range of weather conditions. Model-based polarimetric decomposition is a powerful tool used to extract useful physical and geometric information about sea ice from the matrix datasets acquired by PolSAR. The volume scattering of sea ice is usually modeled as the incoherent average of scatterings of a large volume of oriented ellipsoid particles that are uniformly distributed in 3D space. This uniform spatial distribution is often approximated as a uniform orientation distribution (UOD), i.e., the particles are uniformly oriented in all directions. This is achieved in the existing literature by ensuring the canting angle φ and tilt angle τ of particles uniformly distributed in their respective ranges and introducing a factor cos⁡τ in the ensemble average. However, we find this implementation of UOD is not always effective, while a real UOD can be realized by distributing the solid angles of particles uniformly in 3D space. By deriving the total solid angle of the canting-tilt cell spanned by particles and combining the differential relationship between solid angle and Euler angles φ and τ, a complete expression of the joint probability density function pφ,τ that can always ensure the uniform orientation of particles of sea ice is realized. By ensemble integrating the coherency matrix of φ,τ-oriented particle with pφ,τ, a generalized modeling of the volume coherency matrix of 3D uniformly oriented spheroid particles is obtained, which covers factors such as radar observation geometry, particle shape, canting geometry, tilt geometry and transmission effect in a multiplicative way. The existing volume scattering models of sea ice constitute special cases. The performance of the model in the characterization of the volume behaviors was investigated via simulations on a volume of oblate and prolate particles with the differential reflectivity ZDR, polarimetric entropy H and scattering α angle as descriptors. Based on the model, several interesting orientation geometries were also studied, including the aligned orientation, complement tilt geometry and reflection symmetry, among which the complement tilt geometry is specifically highlighted. It involves three volume models that correspond to the horizontal tilt, vertical tilt and random tilt of particles within sea ice, respectively. To match the models to PolSAR data for adaptive decomposition, two selection strategies are provided. One is based on ZDR, and the other is based on the maximum power fitting. The scattering power that reduces the rank of coherency matrix by exactly one without violating the physical realizability condition is obtained to make full use of the polarimetric scattering information. Both the models and decomposition were finally validated on the Gaofen-3 PolSAR data of a young ice area in Prydz Bay, Antarctica. The adaptive decomposition result demonstrates not only the dominant vertical tilt preference of brine inclusions within sea ice, but also the subordinate random tilt preference and non-negligible horizontal tilt preference, which are consistent with the geometric selection mechanism that the c-axes of polycrystallines within sea ice would gradually align with depth. The experiment also indicates that, compared to the strategy based on ZDR, the maximum power fitting is preferable because it is entirely driven by the model and data and is independent of any empirical thresholds. Such soft thresholding enables this strategy to adaptively estimate the negative ZDR offset introduced by the transmission effect, which provides a novel inversion of the refractive index of sea ice based on polarimetric model-based decomposition.

Region-Based Sea Ice Mapping Using Compact Polarimetric Synthetic Aperture Radar Imagery with Learned Features and Contextual Information

Operational sea ice maps are usually generated manually using dual-polarization (DP) synthetic aperture radar (SAR) satellite imagery, but there is strong interest in automating this process. Recently launched satellites offer compact polarimetry (CP) imagery that provides more comprehensive polarimetric information compared to DP, which compels the use of CP for automated classification of SAR sea ice imagery. Existing sea ice scene classification algorithms using CP imagery rely on handcrafted features, while neural networks offer the potential of features that are more discriminating. We have developed a new and effective sea ice classification algorithm that leverages the nature of CP data. First, a residual-based convolutional neural network (ResCNN) is implemented to classify each pixel. In parallel, an unsupervised segmentation is performed to generate regions based on CP statistical properties. Regions are assigned a single class label by majority voting using the ResCNN output. For testing, quad-polarimetric (QP) SAR sea ice scenes from the RADARSAT Constellation Mission (RCM) are used, and QP, DP, CP, and reconstructed QP modes are compared for classification accuracy, while also comparing them to other classification approaches. Using CP achieves an overall accuracy of 96.86%, which is comparable to QP (97.16%), and higher than reconstructed QP and DP data by about 2% and 10%, respectively. The implemented algorithm using CP imagery provides an improved option for automated sea ice mapping.

Crop classification based on multi-temporal PolSAR images with a single tensor network

Accurate and reliable discrimination of crop categories is a significant data source for agricultural monitoring and food security evaluation research. The convolutional neural network (CNN) model is one of the most popular classifiers for crop discrimination based on polarimetric synthetic aperture radar (PolSAR) data. However, it is better to avoid directly using large amounts of raw features that extracted from PolSAR data for CNN models because of the “dimension disaster” problem caused by multiple periods and various feature extraction schemes. Consequently, an extra feature compression model has to be incorporated to mitigate the “dimension disaster” problem. However, ill coupling of the two models may result in degraded classification performance, thus the combination of two models has to be further optimized. In this paper, we propose a novel single tensor affine transformation network (TATN) for crop classification using multi-temporal PolSAR data, where the input sample of the network is a higher order tensor formed by raw features, and the hidden layers of the network adopt the tensor affine transformation rather than convolution to extract discriminative features for classification. Since the tensor affine transformation preserves the structural information of the original input tensor samples, the TATN is expected to achieve a higher crop classification accuracy. Moreover, the TATN holds less amount of parameters than most of deep learning models, which enables to avoid the extra feature compression procedure. The experimental results validate the merits of our model.

A type of polarimetric parameter for evaluating the reliability of model-based decomposition result and its application

ABSTRACT The reliability of the model-based decomposition result, which is seldom investigated, is a key factor in determining whether decomposition parameters can be effectively applied to polarimetric synthetic aperture radar (PolSAR) applications. In this paper, a type of polarimetric parameter for evaluating the reliability of model-based decomposition result is proposed. It originates from the degree of correlation between the scattering models. The main idea is whether the measured power can be assigned to the corresponding scattering model. The more the measured power that can be allocated to the corresponding scattering model, the more reliable the decomposition result. The C-band Radarsat-2, L-band UAVSAR, X-band TerraSAR-X, and L-band E-SAR PolSAR data are selected for experiments. The results show that the type of polarimetric parameter can effectively represent the reliability of the decomposition result. The reliabilities of surface and double-bounce scattering are high in the ocean and orthogonal buildings, respectively. For oriented buildings, the reliability of the decomposition result is lower owing to the overestimation of volume scattering. For forested areas, reliability is generally higher if volume scattering is not overestimated. Furthermore, the results show that the reliability of soil moisture retrieval is positively correlated with surface scattering reliability.

MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification

Vision transformers (ViT) have the characteristics of massive training data and complex model, which cannot be directly applied to polarimetric synthetic aperture radar (PolSAR) image classification tasks. Therefore, a mixed convolutional parallel transformer (MCPT) model based on ViT is proposed for fast PolSAR image classification. First of all, a mixed depthwise convolution tokenization is introduced. It replaces the learnable linear projection in the original ViT to obtain patch embeddings. The process of tokenization can reduce computational and parameter complexity and extract features of different receptive fields as input to the encoder. Furthermore, combining the idea of shallow networks with lower latency and easier optimization, a parallel encoder is implemented by pairing the same modules and recombining to form parallel blocks, which can decrease the network depth and computing power requirement. In addition, the original class embedding and position embedding are removed during tokenization, and a global average pooling layer is added after the encoder for category feature extraction. Finally, the experimental results on AIRSAR Flevoland and RADARSAT-2 San Francisco datasets show that the proposed method achieves a significant improvement in training and prediction speed. Meanwhile, the overall accuracy achieved was 97.9% and 96.77%, respectively.

Improved General Polarimetric Model-Based Decomposition for Coherency Matrix

A representative general polarimetric model-based decomposition framework was proposed by Chen et al., which implements a simultaneous full-parameter inversion by using complete polarimetric information and solves several limitations in previous decomposition methods. However, there are still shortcomings in Chen’s work. Firstly, only the real part of the parameter β in the generalized surface scattering model is considered. Secondly, inappropriate initial input values may lead to local optima in the nonlinear least squares optimization algorithm. Thirdly, the volume scattering component is underestimated in the volume scattering-dominated scene, but overestimated in buildings with large orientation (LOB) areas. Finally, nonlinear optimization is time-consuming computationally. To overcome those issues, an improved generalized polarimetric model-based decomposition method is proposed in this paper. The imaginary part of the parameter β is incorporated into the decomposition framework of the proposed method. Ingeniously utilizing the internal relationship in the generic equations composed of coherent matrix elements, the model parameters can be inversed by simplifying the nonlinear equations to linear equations. Therefore, compared with Chen’s method, the proposed method does not rely on the initial input values, and improves the computational efficiency. In addition, a hierarchical decomposition scheme is presented to solve the problem of underestimation or overestimation of volume scattering component mentioned above. The performance and advantages of this method are evaluated with L-band and C-band polarimetric synthetic aperture radar (PolSAR) data sets. Comparison studies are carried out with other model-based decomposition methods, demonstrating that the proposed method can further improve decomposition performance, especially in LOB areas.

Performance evaluation of DFT based speckle reduction framework for synthetic aperture radar (SAR) images at different frequencies and image regions

Polarimetric Synthetic Aperture Radar (PolSAR) images are widely used for remote sensing and geoscience applications. However, the coherent processing of radar signals in PolSAR imaging leads to the presence of speckle noise, which can significantly degrade image quality and limit the accuracy of subsequent analyses. To address this issue, speckle reduction frameworks are often applied to PolSAR images to reduce the noise level and enhance image quality. In this paper, the performance of Discrete Fourier Transform (DFT) based speckle reduction framework is evaluated on different bands (L, C, and P band) against various evaluation metrics like CV, SD, SNR, ENL, SSI and SMPI. The proposed framework is evaluated by comparing filtered and unfiltered images across different parameters, such as mean, standard deviation, coefficient of variation, equivalent number of looks (ENL), variance, and signal-to-noise ratio (SNR) on all three bands for the diagonal elements (T11, T22, and T33) of T3 matrix. These metrics provide a comprehensive evaluation of the proposed framework’s ability to (i) smoothen homogeneous regions, (ii) preserve contours, and (iii) retain polarimetric information. The framework’s ability to reduce speckle noise and improve image quality is demonstrated through a significant reduction in standard deviation, coefficient of variation, and improvement in SNR and ENL values. The proposed framework successfully preserved polarimetric information while effectively suppressing speckle noise. These results suggest that the proposed framework could be a valuable tool for improving PolSAR image quality and enhancing subsequent processing of PolSAR data.

Polarimetric Decomposition and Machine Learning‐Based Classification of L‐ and S‐Band Airborne SAR (LS‐ASAR) Data

AbstractThe polarimetric Synthetic Aperture Radar (SAR) data sets have been widely exploited for land use land cover (LULC) classification due to their sensitivity to the structural and dielectric properties of the imaging target. In this study, the potential of fully polarimetric L‐ and S‐band Airborne SAR (LS‐ASAR) data sets were explored for the machine‐learning‐based classification of Urban, Vegetation, Waterbody, and Open Ground. This work was done by utilizing dual‐frequency L‐ and S‐band airborne data of Santa Barbara, California, USA, acquired under the Airborne SAR (LS ASAR) campaign, a precursor airborne mission to the space‐borne NASA‐ISRO (NISAR) mission. The LS‐ASAR polarimetric information was utilized for LULC classification using the SVM classifier. The roll‐invariant Barnes, and eigenvalue/eigenvector‐based Cloude and H/A/Alpha decomposition were implemented to retrieve the scattering parameters. The backscatter response of classes was studied, and separability analysis was done to reduce the misclassification error between six class pairs‐ Vegetation—Urban, Vegetation—Waterbody, Vegetation—Open Ground, Urban—Waterbody, Urban—Open Ground, and Water—Open Ground. The decomposition models failed to achieve the desirable separability index for all six class pairs; consequently, the classification of Barnes, Cloude, H/A/Alpha decomposition showed misclassification between vegetation‐urban class, and waterbody‐open ground class for both L‐ and S‐band data sets. The effort was made toward improving the classification accuracy by integrating the roll‐invariant and eigenvalue‐eigenvector scattering parameters of the multifrequency L‐ and S‐band data set. This method presented the desirable separability index for all class‐pair; eventually highest classification accuracy was achieved i.e. 93.35% ( = 0.91) by significantly reducing the misclassification error between class pairs.

Fine Resolution Classification of New Ice, Young Ice, and First-Year Ice Based on Feature Selection from Gaofen-3 Quad-Polarization SAR

A new method of sea ice classification based on feature selection from Gaofen-3 polarimetric Synthetic Aperture Radar (SAR) observations was proposed. The new approach classifies sea ice into four categories: open water (OW), new ice (NI), young ice (YI), and first-year ice (FYI). Seventy parameters that have previously been applied to sea ice studies were re-examined for sea ice classification in the Okhotsk Sea near the melting point on 28 February 2020. The ‘separability index (SI)’ was used for the selection of optimal features for sea ice classification. Full polarization parameters (the backscatter intensity contains the horizontal transmit-receive intensity (σhh0), Shannon entropy (SEi), the spherical scattering component of Krogager decomposition (Ks)), and hybrid polarization parameters (horizontal receive intensity(σrh0), hybrid-pol Shannon entropy (CPSEi), the correlation coefficient (ρrh−rv) between the σrh0 and σrv0, and the surface scattering component of m − α decomposition αs) were determined as the optimal parameters for the different work modes of SAR. The selected parameters were used to classify sea ice by the random forest classifier (RFC), and classification results were validated by manually interpreted ice maps derived from Landsat-8 data. The classification accuracy of OW, NI, YI and FYI reached 95%, 96%, 98% and 85%, respectively.

Estimating Forest Above-Ground Biomass in Central Amazonia Using Polarimetric Attributes of ALOS/PALSAR Images

Polarimetric synthetic aperture radar (SAR) images are essential to understand forest structure and plan forest inventories with the purpose of natural resource management and environmental conservation efforts. We developed a method for estimating above-ground biomass (AGB) from power and phase-radar attributes in L-band images. The model was based on the variables “Pv” (from Freeman–Durden decomposition) and “σ°HH”, complemented by the attributes of Touzi decomposition “αS2”, “τm”, “ ΦS3”, and “ ΦS2”. The analyses demonstrated the contribution of volumetric, multiple, and direct scattering resulting from the interaction between the signal and the random structure of canopies and their forest biomass. The proposed model had good predictive capacity and a positive correlation (R2 = 0.67 and = 0.81, respectively), with Syx = 56.9 Mg ha−1 and a low average estimation error of 7.5% at R2 = 0.81 in the validation. An additional exploratory analysis of the parallel polarimetric responses did not reveal a defined pattern for the different phytophysiognomies—although all indicated a predominance of multiple and/or volumetric scattering. This fact can be related to the floristic and structural variation in the primary forest units, the degree of human intervention in legal logging, and the differences among succession stages.

PolSAR Image Classification Based on Relation Network with SWANet

Deep learning and convolutional neural networks (CNN) have been widely applied in polarimetric synthetic aperture radar (PolSAR) image classification, and satisfactory results have been obtained. However, there is one crucial issue that still has not been solved. These methods require abundant labeled samples and obtaining the labeled samples of PolSAR images is usually time-consuming and labor-intensive. To obtain better classification results with fewer labeled samples, a new attention-based 3D residual relation network (3D-ARRN) is proposed for PolSAR image. Firstly, a multilayer CNN with residual structure is used to extract depth polarimetric features. Secondly, to extract more important feature information and improve the classification results, a spatial weighted attention network (SWANet) is introduced to concentrate the feature information, which is more favorable for a classification task. Then, the features of training and test samples are integrated and CNN is utilized to compute the score of similarity between training and test samples. Finally, the similarity score is used to determine the category of test samples. Studies on four different PolSAR datasets illustrate that the proposed 3D-ARRN model can achieve higher classification results than other comparison methods with few labeled data.

Few-Shot PolSAR Ship Detection Based on Polarimetric Features Selection and Improved Contrastive Self-Supervised Learning

Deep learning methods have been widely studied in the field of polarimetric synthetic aperture radar (PolSAR) ship detection over the past few years. However, the backscattering of manmade targets, including ships, is sensitive to the relative geometry between target orientation and radar line of sight, which makes the diversity of polarimetric and spatial features of ships. The diversity of scattering leads to a relative increase in the scarcity of PolSAR-labeled samples, which are difficult to obtain. To solve the abovementioned issue and extract the polarimetric and spatial features of PolSAR images better, this paper proposes a few-shot PolSAR ship detection method based on the combination of constructed polarimetric input data selection and improved contrastive self-supervised learning (CSSL) pre-training. Specifically, eight polarimetric feature extraction methods are adopted to construct deep learning network input data with polarimetric features. The backbone is pre-trained with un-labeled PolSAR input data through an improved CSSL method without negative samples, which enhances the representation capability by the multi-scale feature fusion module (MFFM) and implements a regularization strategy by the mix-up auxiliary pathway (MUAP). The pre-trained backbone is applied to the downstream ship detection network; only a few labeled samples are used for fine-tuning and the construction method of polarimetric input data with the best detection effect is studied. The comparison and ablation experiment results on the self-established PolSAR ship detection dataset verify the superiority of the proposed method, especially in the case of few-shot learning.