Search Results (371)

Polarimetric Synthetic Aperture Radar (PolSAR) image classification is one of the most important applications in remote sensing. The impressive superpixel generation approaches can improve the efficiency of the subsequent classification task and restrain the influence of the speckle noise to an extent. Most of the classical PolSAR superpixel generation approaches use the features extracted manually and even only consider the pseudocolor images. They do not make full use of polarimetric information and do not necessarily lead to good enough superpixels. The deep learning methods can extract effective deep features but they are difficult to combine with superpixel generation to achieve true end-to-end training. Addressing the above issues, this study proposes an end-to-end fully convolutional superpixel generation network for PolSAR images. It integrates the extraction of polarization information features and the generation of PolSAR superpixels into one step. PolSAR superpixels can be generated based on deep polarization feature extraction and need no traditional clustering process. Both the performance and efficiency of generations of PolSAR superpixels can be enhanced effectively. The experimental results on various PolSAR datasets show that the proposed method can achieve impressive superpixel segmentation by fitting the real boundaries of different types of ground objects effectively and efficiently. It can achieve excellent classification performance by connecting a very simple classification network, which is helpful to improve the efficiency of the subsequent PolSAR image classification tasks. Full article

Compared to traditional real-valued neural networks, which process only amplitude information, complex-valued neural networks handle both amplitude and phase information, leading to superior performance in polarimetric synthetic aperture radar (PolSAR) image classification tasks. This paper proposes a multi-scale feature extraction (MSFE) method based on a 3D complex-valued network to improve classification accuracy by fully leveraging multi-scale features, including phase information. We first designed a complex-valued three-dimensional network framework combining complex-valued 3D convolution (CV-3DConv) with complex-valued squeeze-and-excitation (CV-SE) modules. This framework is capable of simultaneously capturing spatial and polarimetric features, including both amplitude and phase information, from PolSAR images. Furthermore, to address robustness degradation from limited labeled samples, we introduced a multi-scale learning strategy that jointly models global and local features. Specifically, global features extract overall semantic information, while local features help the network capture region-specific semantics. This strategy enhances information utilization by integrating multi-scale receptive fields, complementing feature advantages. Extensive experiments on four benchmark datasets demonstrated that the proposed method outperforms various comparison methods, maintaining high classification accuracy across different sampling rates, thus validating its effectiveness and robustness. Full article

The coherency matrix serves as a valuable tool for explaining the intricate details of various terrain targets. However, a significant challenge arises when analyzing ground targets with similar scattering characteristics in polarimetric synthetic aperture radar (PolSAR) target decomposition. Specifically, the overestimation of volume scattering (OVS) introduces ambiguity in characterizing the scattering mechanism and uncertainty in deciphering the scattering mechanism of large oriented built-up areas. To address these challenges, based on the generalized five-component decomposition (G5U), we propose a hierarchical extension of the G5U method, termed ExG5U, which incorporates orientation and phase angles into the matrix rotation process. The resulting transformed coherency matrices are then subjected to a five-component decomposition framework, enhanced with four refined volume scattering models. Additionally, we have reformulated the branch conditions to facilitate more precise interpretations of scattering mechanisms. To validate the efficacy of the proposed method, we have conducted comprehensive evaluations using diverse PolSAR datasets from Gaofen-3, Radarsat-2, and ESAR, covering varying data acquisition timelines, sites, and frequency bands. The findings indicate that the ExG5U method proficiently captures the scattering characteristics of ambiguous regions and shows promising potential in mitigating OVS, ultimately facilitating a more accurate portrayal of scattering mechanisms of various terrain types. Full article

Soil salinization poses a significant threat to agricultural productivity, food security, and ecological sustainability in arid and semi-arid regions. Effectively and timely mapping of different degrees of salinized soils is essential for sustainable land management and ecological restoration. Although deep learning (DL) methods have been widely employed for soil salinization extraction from remote sensing (RS) data, the integration of multi-source RS data with DL methods remains challenging due to issues such as limited data availability, speckle noise, geometric distortions, and suboptimal data fusion strategies. This study focuses on the Keriya Oasis, Xinjiang, China, utilizing RS data, including Sentinel-2 multispectral and GF-3 full-polarimetric SAR (PolSAR) images, to conduct soil salinization classification. We propose a Dual-Modal deep learning network for Soil Salinization named DMSSNet, which aims to improve the mapping accuracy of salinization soils by effectively fusing spectral and polarimetric features. DMSSNet incorporates self-attention mechanisms and a Convolutional Block Attention Module (CBAM) within a hierarchical fusion framework, enabling the model to capture both intra-modal and cross-modal dependencies and to improve spatial feature representation. Polarimetric decomposition features and spectral indices are jointly exploited to characterize diverse land surface conditions. Comprehensive field surveys and expert interpretation were employed to construct a high-quality training and validation dataset. Experimental results indicate that DMSSNet achieves an overall accuracy of 92.94%, a Kappa coefficient of 79.12%, and a macro F1-score of 86.52%, positively outperforming conventional DL models (ResUNet, SegNet, DeepLabv3+). The results confirm the superiority of attention-guided dual-branch fusion networks for distinguishing varying degrees of soil salinization across heterogeneous landscapes and highlight the value of integrating Sentinel-2 optical and GF-3 PolSAR data for complex land surface classification tasks. Full article

Tropical forests harbor a significant portion of global biodiversity but are increasingly degraded by human activity. Assessing restoration efforts requires the systematic monitoring of tropical ecosystem status and recovery. Satellite-borne synthetic aperture radar (SAR) supports monitoring changes in vegetation structure and is of particular utility in tropical regions where clouds obscure optical satellite observations. To characterize tropical forest recovery in the Lowland Chocó Biodiversity Hotspot of Ecuador, we apply over a decade of dual-polarized (HH + HV) L-band SAR datasets from the Japanese Space Agency’s (JAXA) PALSAR and PALSAR-2 sensors. We assess the complementarity of the dual-polarized imagery with less frequently available fully-polarimetric imagery, particularly in the context of their respective temporal and informational trade-offs. We examine the radar image texture associated with the dual-pol radar vegetation index (DpRVI) to assess the associated determination of forest and nonforest areas in a topographically complex region, and we examine the equivalent performance of texture measures derived from the Freeman–Durden polarimetric radar decomposition classification scheme applied to the fully polarimetric data. The results demonstrate that employing a dual-polarimetric decomposition classification scheme and subsequently deriving the associated gray-level co-occurrence matrix mean from the DpRVI substantially improved the classification accuracy (from 88.2% to 97.2%). Through this workflow, we develop a new metric, the Radar Forest Regeneration Index (RFRI), and apply it to describe a chronosequence of a tropical forest recovering from naturally regenerating pasture and cacao plots. Our findings from the Lowland Chocó region are particularly relevant to the upcoming NASA-ISRO NISAR mission, which will enable the comprehensive characterization of vegetation structural parameters and significantly enhance the monitoring of biodiversity conservation efforts in tropical forest ecosystems. Full article

For tropical forests characterized by tall and densely packed trees, even long-wavelength SAR signals may fail to achieve full penetration, posing a significant challenge for retrieving sub-canopy terrain using polarimetric interferometric SAR (InSAR)(PolInSAR) techniques. This paper proposes a single-baseline PolInSAR-based correction method for sub-canopy terrain estimation based on a one-dimensional lookup table (LUT) that links forest height to unpenetrated depth. The approach begins by applying an optimal normal matrix approximation to constrain the complex coherence measurements. Subsequently, the difference between the PolInSAR Digital Terrain Model (DTM) derived from the Random Volume over Ground (RVoG) model and the LiDAR DTM is defined as the unpenetrated depth. A nonlinear iterative optimization algorithm is then employed to estimate forest height, from which a fundamental mapping between forest height and unpenetrated depth is established. This mapping can be used to correct the bias in sub-canopy terrain estimation based on the PolInSAR RVoG model, even with only a small amount of sparse LiDAR DTM data. To validate the effectiveness of the method, experiments were conducted using fully polarimetric P-band airborne SAR data acquired by the European Space Agency (ESA) during the AfriSAR campaign over the Mabounie region in Gabon, Africa, in 2016. The experimental results demonstrate that the proposed method effectively mitigates terrain estimation errors caused by insufficient signal penetration or the limitation of single-interferometric geometry. Further analysis reveals that the availability of sufficient and precise forest height data significantly improves sub-canopy terrain accuracy. Compared with LiDAR-derived DTM, the proposed method achieves an average root mean square error (RMSE) of 5.90 m, representing an accuracy improvement of approximately 38.3% over traditional RVoG-derived InSAR DTM retrieval. These findings further confirm that there exist unpenetrated phenomena in single-baseline low-frequency PolInSAR-derived DTMs of tropical forested areas. Nevertheless, when sparse LiDAR topographic data is available, the integration of fully PolInSAR data with LUT-based compensation enables improved sub-canopy terrain retrieval. This provides a promising technical pathway with single-baseline configuration for spaceborne missions, such as ESA’s BIOMASS mission, to estimate sub-canopy terrain in tropical-rainforest regions. Full article

The debate surrounding the optimal polarimetric modes—compact polarimetry (CP) versus dual polarization (DP)—for PolSAR ship detection persists. This study pioneers a systematic investigation into Generalized Compact Polarimetry (GCP) for this application. By synthesizing and evaluating 143 distinct GCP configurations from fully polarimetric data, this study presents the first comprehensive comparison of their ship detection performance against conventional modes using Target-to-Clutter Ratio (TCR) and deep learning-based accuracy (AP50). Experiments on the FPSD dataset reveal that an optimized GCP mode (e.g., ellipse/orientation: [−10, −5]) consistently outperforms traditional CP and DP modes, yielding TCR gains of 0.2–2.7 dB. This translates to AP50 improvements of 0.5–4.7% (Faster R-CNN) and 0.1–5.5% (RetinaNet) over five common baseline modes. Crucially, this enhancement arises from optimizing the interaction between the polarization mode and target/clutter scattering characteristics rather than algorithmic improvements, supporting the proposed “optimization from the information source” strategy. These findings offer significant implications for future PolSAR system design and operational mode selection. Full article

This study aims to elucidate the optimal exploitation of polarimetric scattering information in dual-pol SAR data. For an effective comparison of the flood detection performance between dual-pol parameters, we presented a simple fuzzy-based flood detection algorithm. Scattering characteristics of water surface and non-water land can vary depending on the region and flood conditions. Therefore, the flood detection performance of the dual-pol parameters was evaluated across three datasets with different geographic, climatic, and land cover conditions. The results demonstrated that accurate and stable performance in the detection of inundated areas under different surface conditions can be achieved by combining water body information from dual-pol channels in a disjunctive way. It also suggests that synergy in flood detection can be expected when using polarization observation data by considering each polarimetric channel as an independent information source and combining them rather than deriving the most relevant polarization parameter. Furthermore, combining common information from two dual-pol channels in a conjunctive way could provide the most reliable SAR flood detection results with minimum false alarms from the user’s perspective. Based on these experimental results, a two-class flood classification scheme was proposed for improving the applicability of SAR remote sensing in identifying flooded areas. Full article

Limited labels and detailed changed land-cover interpretation requirements pose challenges for time-series PolSAR change monitoring research. Accurate labels and supervised models are difficult to reuse between massive unlabeled time-series PolSAR data due to the complex distribution shifts caused by different imaging parameters, scene changes, and random noises. Moreover, many related methods can only detect binary changes in PolSAR images and struggle to track the detailed land cover changes. In this study, an unsupervised cross-domain method based on limited-label transfer learning and a vision transformer (LLTL-ViT) is proposed for PolSAR land-cover change monitoring, which effectively alleviates the problem of difficult label reuse caused by domain shift in time-series SAR data, significantly improves the efficiency of label reuse, and provides a new paradigm for the transfer learning of time-series polarimetric SAR. Firstly, based on the polarimetric scattering characteristics and manifold-embedded distribution alignment transfer learning, LLTL-ViT transfers the limited labeled samples of source-domain PolSAR data to unlabeled target-domain PolSAR time-series for initial classification. Secondly, the accurate samples of target domains are further selected based on the initial transfer classification results, and the deep learning network ViT is applied to classify the time-series PolSAR images accurately. Thirdly, with the reliable secondary classification results of time-series PolSAR images, the detailed changes in land cover can be accurately tracked. Four groups of cross-domain change monitoring experiments were conducted on the Radarsat-2, Sentinel-1, and UAVSAR datasets, with about 10% labeled samples from the source-domain PolSAR. LLTL-ViT can reuse the samples between unlabeled target-domain time-series and leads to a change detection accuracy and specific land-cover change tracking accuracy of 85.22–96.36% and 72.18–88.06%, respectively. Full article

Existing forest height estimation methods based on polarimetric interferometric synthetic aperture radar (PolInSAR) typically process each pixel independently, potentially introducing inconsistent estimates and additional decorrelation in the covariance matrix estimation. To address these limitations and effectively exploit the spatial context information, this paper proposes the first patch-based inversion method named joint pixel optimization inversion (JPO). By leveraging the smoothness and regularity of homogeneous pixels, a joint-pixel optimization problem is constructed, incorporating a first-order regularization on the ground phase. To solve the non-parallelizable problem of the alternating direction method of multipliers (ADMM), we devise a new parallelizable ADMM algorithm and prove its sublinear convergence. With the contextual information of neighboring pixels, JPO can provide more reliable forest height estimation and reduce the overestimation caused by additional decorrelation. The effectiveness of the proposed method is verified using spaceborne L-band repeat-pass SAOCOM acquisitions and LiDAR heights obtained from ICESat-2. Quantitative evaluations in forest height estimation show that the proposed method achieves a lower mean error (1.23 m) and RMSE (3.67 m) than the existing method (mean error: 3.09 m; RMSE: 4.70 m), demonstrating its improved reliability. Full article

In synthetic aperture radar (SAR) image sea ice classification, the polarization decomposition techniques are used to enhance classification accuracy. However, traditional methods, such as Freeman–Durden (FD) and H/A/α decomposition, struggle to accurately characterize complex scattering mechanisms, limiting their ability to differentiate between various sea ice types. This paper proposes using the Modified Reflection Symmetry Decomposition (MRSD) method to extract polarization features from Gaofen-3 (GF-3) satellite fully polarimetric SAR data for sea ice classification tests. The study data included three types of sea surface: open water (OW), young ice (YI), and first-year ice (FYI). In this research, backscattering coefficients were combined with FD, H/A/α, and MRSD polarization features to create eight feature combinations for comparative analysis. Three machine learning algorithms, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machines (SVM), were also used for the comparative analysis. The results show that MRSD polarization features significantly improve model performance, particularly distinguishing among sea ice categories. Compared to using only the backscatter coefficient, MRSD polarization features increased model classification accuracy by approximately 4% to 13%, outperforming FD and H/A/α polarization features. The XGBoost model trained with MRSD polarization features achieves excellent classification results, with classification accuracies of 0.9630, 0.9126, and 0.9451 for OW, YI, and FYI. Additionally, the model achieved a Kappa coefficient of 0.9105 and an F1-score of 0.9403. Feature importance and SHapley Additive exPlanations (SHAP) analysis further demonstrate the physical significance of the MRSD polarization features and their role in model decision-making, suggesting that the scattered component power plays a crucial role in the model’s classification decision. Compared to traditional decomposition methods, MRSD provides a more detailed characterization of scattering mechanisms, offering a comprehensive understanding of the physical properties of sea ice. This paper systematically demonstrates the superior effectiveness of MRSD polarization features for sea ice classification, presenting a new scheme for more accurate classification. Full article

The Yuanjiang Basin in Northwestern Hunan is a landslide-prone region due to its complex geological features and dense vegetation. Conventional single-polarization muti-temporal InSAR (MT-InSAR) methods often fail in such areas because of severe decorrelation, leading to reduced accuracy and coverage in monitoring. To address these limitations, this study proposes an innovative landslide detection framework using the muti-temporal polarimetric InSAR (MT-PolInSAR) method. This approach improves the density and precision of deformation measurements by optimizing polarimetric and temporal dimensions. Leveraging fully polarimetric ALOS-2 data acquired from May 2021 to June 2022, 32 potential deformation sites were identified, including 18 landslide-prone areas and 8 sites showing other deformation types, with average deformation rates between −4 and −2 cm/year. Field validation confirmed an identification accuracy of 81.25%, demonstrating the robustness of fully polarimetric long-wavelength SAR data for landslide monitoring in densely vegetated regions. This method offers a significant advancement in the detection and assessment of landslide hazards in challenging environments. Full article

Deep learning has shown significant potential in multi-band Polarimetric Synthetic Aperture Radar (PolSAR) land cover classification. However, the existing methods face two main challenges: accurately modeling the complex nonlinear relationships between multiple bands and balancing classifier parameter efficiency with classification accuracy. To address these challenges, this paper proposes a novel decision-level multi-band fusion framework that leverages the synergistic optimization of the Vision Transformer (ViT) and Kolmogorov–Arnold Network (KAN). This innovative architecture effectively captures global spatial–spectral correlations through ViT’s cross-band self-attention mechanism and achieves parameter-efficient decision-level probability space mapping using KAN’s spline basis functions. The proposed method significantly enhances the model’s generalization capability across different band combinations. The experimental results on the quad-band (P/L/C/X) Hainan PolSAR dataset, acquired by the Aerial Remote Sensing System of the Chinese Academy of Sciences, show that the proposed framework achieves an overall accuracy of 96.24%, outperforming conventional methods in both accuracy and parameter efficiency. These results demonstrate the practical potential of the proposed method for high-performance and efficient multi-band PolSAR land cover classification. Full article

Polarimetric Synthetic Aperture Radar (PolSAR) is an advanced remote sensing technology that provides rich polarimetric information. Deep learning methods have been proved an effective tool for PolSAR image classification. However, relying solely on source data input makes it challenging to effectively classify all land cover targets, especially heterogeneous targets with significant scattering variations, such as urban areas and forests. Besides, multiple features can provide more complementary information, while feature selection is crucial for classification. To address these issues, we propose a novel attention mechanism-based multi-feature lightweight DeeplabV3+ network for PolSAR image classification. The proposed method integrates feature extraction, learning, selection, and classification into an end-to-end network framework. Initially, three kinds of complementary features are extracted to serve as inputs to the network, including polarimetric original data, statistical and scattering features, textural and contour features. Subsequently, a lightweight DeeplabV3+ network is designed to conduct multi-scale feature learning on the extracted multidimensional features. Finally, an attention mechanism-based feature selection module is integrated into the network model, adaptively learning weights for multi-scale features. This enhances discriminative features but suppresses redundant or confusing features. Experiments are conducted on five real PolSAR data sets, and experimental results demonstrate the proposed method can achieve more precise boundaries and smoother regions than the state-of-the-art algorithms. In this paper, we develop a novel multi-feature learning framework, achieving a fast and effective classification network for PolSAR images. Full article

The Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) system is a combination of polarimetric SAR and interferometric SAR, which can simultaneously obtain the power information, polarimetric information, and interferometric information of land cover. Traditional land cover classification methods fail to fully utilize these information types, resulting in limited classification types and low accuracy. This paper proposes a PolInSAR land cover classification method that fuses power information, polarimetric information, and interferometric information, aiming to enrich the classification types and improve the classification accuracy. Firstly, the land cover is divided into strong scattering areas and weak scattering areas by using the power information to avoid the influence of weak scattering areas on the classification results. Then, the weak scattering areas are distinguished into shadows and water bodies by combining the interferometric information and image corners. For the strong scattering areas, the polarimetric information is utilized to distinguish vegetation, buildings, and bare soil. For the vegetation area, the concept of vegetation ground elevation is put forward. By combining with the anisotropy parameter, the vegetation is further subdivided into tall coniferous vegetation, short coniferous vegetation, tall broad-leaved vegetation, and short broad-leaved vegetation. The effectiveness of the method has been verified by the PolInSAR data obtained from the N-SAR system developed by Nanjing Research Institute of Electronics Technology. The overall classification accuracy reaches 90.2%, and the Kappa coefficient is 0.876. Full article