Search Results (139)

In the semantic segmentation tasks of polarimetric SAR images, deep learning has become an important end-to-end method that uses convolutional neural networks (CNNs) and other advanced network architectures to extract features and classify the target region pixel by pixel. However, applying original networks used to optical images for PolSAR image segmentation directly will result in the loss of rich phase information in PolSAR data, which leads to unsatisfactory classification results. In order to make full use of polarization information, the complex-valued BiSeNetV2 with a bilateral-segmentation structure is studied and expanded in this work. Then, considering further improving the ability to extract semantic features in the complex domain and alleviating the imbalance of polarization channel response, the complex-valued BiSeNetV2 with a lightweight attention module (LAM-CV-BiSeNetV2) is proposed for the semantic segmentation of PolSAR images. LAM-CV-BiSeNetV2 supports complex-valued operations, and a lightweight attention module (LAM) is designed and introduced at the end of the Semantic Branch to enhance the extraction of detailed features. Compared with the original BiSeNetV2, the LAM-CV-BiSeNetV2 can not only more fully extract the phase information from polarimetric SAR data, but also has stronger semantic feature extraction capabilities. The experimental results on the Flevoland and San Francisco datasets demonstrate that the proposed LAM has better and more stable performance than other commonly used attention modules, and the proposed network can always obtain better classification results than BiSeNetV2 and other known real-valued networks. Full article

Coastal wetlands are a critical buffer between land and water that are threatened by land use and climate change, necessitating improved monitoring for management and resilience planning. The recently launched NASA-ISRO L- and S-band SAR satellite (NISAR) will provide regular collections of fully polarimetric SAR imagery over the Great Lakes, allowing for unprecedented remote monitoring of the large expanses of coastal wetlands in the region. Prior research with polarimetric C-band SAR showed inconsistencies with common polarimetric analysis techniques, including the erroneous misattribution of double-bounce scattering in three-component scattering models. To prepare for NISAR and determine whether SAR-based coastal wetland analysis methods established with the C-band are applicable to the L- and S-bands, the NASA-ISRO airborne system (ASAR) collected imagery over western Lake Erie and Lake St. Clair coincident with a field data collection campaign. ASAR data were analyzed to identify common Great Lakes coastal wetland vegetation species, assess the extent of inundation, and derive biomass retrieval algorithms. Co-polarized phase difference histograms were also analyzed to assess the validity of three-component scattering decompositions. The L- and S-bands allowed for the production of wetland type maps with high accuracies (92%), comparable to those produced using a fusion of optical and SAR data. Both frequencies could assess the extent of flooded vegetation, with the S-band correctly identifying inundated vegetation at a slightly higher rate than the L-band (83% to 78%). Marsh vegetation biomass retrieval algorithms derived from L-band data had the best correlation with field data (R² = 0.71). Three component scattering models were found to misattribute double-bounce scattering at incidence angles shallower than 35°. The L- and S-band results were compared with satellite RADARSAT-2 imagery collected close to the ASAR acquisitions. This study provides an advanced understanding of polarimetric SAR for monitoring wetlands and provides a framework for utilizing forthcoming NISAR data for effective monitoring. Full article

Remote sensing of moving targets, particularly pedestrians on the road, is crucial for advanced driver assistance systems. However, pedestrian detection using the radar system remains an ongoing challenge due to the radar cross section (RCS) of pedestrians being much smaller than that of the clutter. Existing radar systems and pedestrian detection methods predominantly rely on the single-polarization radar, while research on the fully polarized radar for pedestrian detection is relatively limited. In this paper, the L-band fully polarimetric radar system is developed for pedestrian detection, and based on the full polarized radar echo HH, HV, VH, and VV, a novel clutter suppression method is proposed, which integrates the optimal polarization states of antennas and optimal scattering characteristics of pedestrians. Moreover, the field experiment has been conducted, and the results demonstrate that the signal-to-clutter-plus-noise ratio (SCNR) of the total power signal of full-polarization echoes is higher than that of single-polarization echoes, and the proposed clutter suppression method is able to reduce the non-stationary clutter and the interference signal generated by the multipath effect, thereby improving the SCNR. Furthermore, the OTSU algorithm is employed to detect pedestrian targets using radar data before and after clutter suppression, and the results demonstrate that the proposed method yields superior detection performance. These findings justify the potential of fully polarimetric radar in enhancing pedestrian detection. Full article

In order to achieve 0.1 m resolution and fully polarimetric observation capabilities for airborne SAR systems, the adoption of stepped-frequency modulation waveform combined with the polarization time-division transmit/receive (T/R) technique proves to be an effective technical approach. Considering the issue of range resolution degradation and paired echoes caused by multichannel amplitude–phase mismatch in fully polarimetric airborne SAR with 0.1 m resolution, an amplitude–phase error estimation algorithm based on echo data is proposed in this paper. Firstly, the subband amplitude spectrum correction curve is obtained by the statistical average of the subband amplitude spectrum. Secondly, the paired-echo broadening function is obtained by selecting high-quality sample points after single-band imaging and the nonlinear phase error within the subbands is estimated via Sinusoidal Frequency Modulation Fourier Transform (SMFT). Thirdly, based on the minimum entropy criterion of the synthesized compressed pulse image, residual linear phase errors between subbands are quickly acquired. Finally, two-dimensional cross-correlation of the image slice is utilized to estimate the positional deviation between polarization channels. This method only requires high-quality data samples from the echo data, then rapidly estimates both intra-band and inter-band amplitude/phase errors by using SMFT and the minimum entropy criterion, respectively, with the characteristics of low computational complexity and fast convergence speed. The effectiveness of this method is verified by the imaging results of the experimental data. Full article

Dual polarimetric SAR is capable of reflecting the biophysical and geometrical information of terrain with open access data availability. When it is combined with time-series observations, it can effectively capture the dynamic evolution of scattering characteristics of crops in different growth cycles. However, the actual planting of crops often shows spatial dispersion, and the same crop may be dispersed in different plots, which fails to adequately consider the correlation information between dispersed plots of the same crop in spatial distribution. This study proposed a crop classification method based on multi-temporal dual polarimetric data, which considered the utilization of information between near and far spatial plots, by employing superpixel segmentation and a HyperGraph neural network, respectively. Firstly, the method utilized the dual polarimetric covariance matrix of multi-temporal data to perform superpixel segmentation on neighboring pixels, so that the segmented superpixel blocks were highly compatible with the actual plot shapes from a long-term period perspective. Then, a HyperGraph adjacency matrix was constructed, and a HyperGraph neural network (HGNN) was utilized to better learn the features of plots of the same crop that are distributed far from each other. The method fully utilizes the three dimensions of time, polarization and space information, which complement each other so as to effectively realize high-precision crop classification. The Sentinel-1 experimental results show that, under the optimal parameter settings, the classified accuracy of combined temporal superpixel scattering features using the HGNN was obviously improved, considering the near and far distance spatial correlations of crop types. 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

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

Soil salinization is a critical factor affecting land desertification and limiting agricultural development in arid regions, and the rapid acquisition of salinized soil information is crucial for prevention and mitigation efforts. In this study, we selected the Yutian Oasis in Xinjiang, China as the study area and utilized Gaofen-3 synthetic aperture radar (SAR) remote sensing data and field measurements to analyze the correlations between the salinized soil properties and 36 polarimetric radar feature components. Based on the analysis results, two components with the highest correlation, namely, Yamaguchi4_vol (p < 0.01) and Freeman3_vol (p < 0.01), were selected to construct a two-dimensional feature space, named Yamaguchi4_vol-Freeman3_vol. Based on this feature space, a radar salinization monitoring index (RSMI) model was developed. The results indicate that the RSMI exhibited a strong correlation with the surface soil salinity, with a correlation coefficient of 0.85. The simulated values obtained using the RSMI model were well-fitted to the measured soil electrical conductivity (EC) values, achieving an R² value of 0.72 and a root mean square error (RMSE) of 7.28 dS/m. To assess the model’s generalizability, we applied the RSMI to RADARSAT-2 SAR data from the environmentally similar Weiku Oasis. The validation results showed comparable accuracy (R² = 0.70, RMSE = 9.29 dS/m), demonstrating the model’s robustness for soil salinity retrieval across different arid regions. This model offers a rapid and reliable approach for quantitative monitoring and assessment of soil salinization in arid regions using fully polarimetric radar remote sensing. Furthermore, it lays the groundwork for further exploring the application potential of Gaofen-3 satellite data and expanding its utility in soil salinization monitoring. Full article

Spaceborne Synthetic Aperture Radar (SAR) is extensively used in maritime surveillance due to its ability to monitor vast oceanic regions regardless of weather conditions and sun illumination. Over the years, numerous automatic ship detection algorithms have been developed, utilizing either single-polarimetric data (i.e., intensity) or leveraging additional information provided by polarimetric sensors. One of the main challenges in automatic ship detection using SAR is that sea clutter, influenced primarily by sea conditions and image acquisition angles, can exhibit strong backscatter, reducing the signal-to-clutter ratio (that is, the contrast) between ships and their surroundings. This leads inevitably to detection errors, which can be either false alarms or miss-detections. A potential solution to this issue is to develop methodologies that suppress backscattered signals from the sea while preserving the radar returns from ships. In this work, we analyse a contrast enhancement method which is designed to suppress unwanted sea clutter while preserving signals from potential ships. A key advantage of this method is that it is fully analytical, eliminating the need for numerical optimization and enabling the rapid generation of an enhanced image better suited for automatic detection. This technique, based on polarimetric orthogonality, was originally formulated for quad-polarimetric data, and here the adaptation for dual-polarimetric SAR images is also detailed. To demonstrate its effectiveness, a comprehensive set of results using both quad- and dual-polarimetric images acquired by various sensors operating at L-, C-, and X-band is presented. 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

China’s first L-band fully polarimetric Synthetic Aperture Radar (SAR) constellation, LuTan-1 (LT-1), was designed for terrain mapping and geohazard monitoring. This study evaluates LT-1’s capability in identifying landslides in the southern hilly regions of China, focusing on Longshan County, Hunan Province. Using both ascending and descending orbit data from LT-1, we conducted landslide identification experiments. First, deformation was obtained using Differential Interferometric SAR (D-InSAR) technology, and the deformation rates were derived through the Stacking technique. A landslide identification method that integrates C-index, slope, and ascending/descending orbit deformation information was then applied. The identified landslides were validated against existing geohazard points and medium-to-high-risk slope and gully unit data. The experimental results indicate that LT-1-ascending orbit data identified 88 landslide areas, with 39.8% corresponding to geohazard points and 65.9% within known slope units. Descending orbit data identified 90 landslide areas, with 37.8% matching geohazard points and 61.1% within known slope units. The identification results demonstrated good consistency with existing data. Comparative analysis with Sentinel-1 data revealed that LT-1’s combined ascending and descending orbit data outperformed Sentinel-1’s single ascending orbit data. LT-1’s L-band characteristics, comprehensive ascending and descending orbit coverage, and high-precision deformation detection make it highly promising for landslide identification in the southern hilly regions. This study underscores LT-1’s robust technical support for early landslide identification, highlighting its potential to enhance geohazard monitoring and mitigate risks in challenging terrains. Full article

Due to the limited accuracy of experimental data, Mueller polarimetry can produce real 4×4 matrices that fail to meet required covariance or passivity conditions. A general and simple procedure to convert any real 4×4 matrix into a valid Mueller matrix by adding a portion of polarimetric white noise is presented. This approach provides deeper insight into the structure of Mueller matrices and has a subtle relation to the effective component of the Mueller matrix, which is defined through the subtraction of the fully random component of the characteristic decomposition. Up to a scale coefficient determined by the third index of polarimetric purity of the original Mueller matrix, the effective component retains complete information on the polarimetric anisotropies. Full article