Multimodal land cover classification has become a research hotspot in remote sensing image interpretation, where optical and synthetic aperture radar (SAR) imagery are widely studied due to their complementarity. However, existing methods suffer from over-reliance on fused features and overlook single-modality representations. This limits their adaptability to varying observation conditions. To address this, CAFNet is proposed, which integrates channel complementary coordinate attention (C3A) and cross-spatial fusion (CSF) to enhance spatial-channel feature modeling and improve the ability to capture complementary information between modalities. Additionally, class-level feature alignment (CLFA) introduces auxiliary supervision to improve unimodal feature learning and model robustness. Experiments on WHU-OPT-SAR and PIE-RGB-SAR datasets validate the effectiveness of the proposed method, achieving the best overall performance compared with representative approaches.

High-resolution remote sensing (HRRS) scene classification is critical in various applications. HRRS data usually contain sensitive geographical and environmental information, such as the locations of critical assets, urban planning details, and military bases. To safeguard such private information, local governments have implemented regulations and policies that govern the sharing of HRRS data. However, existing scene classification methods typically rely on centralized training and assume that data are directly shared with a centralized server, posing significant privacy risks. To address these concerns, we propose federated remote sensing scene classification (Fed-RSSC), a novel framework enabling the collaborative training of a joint model while ensuring data remains localized. We further demonstrate that federated learning (FL) is an effective approach to tackling privacy issues in HRRS scene classification. Moreover, to reduce high communication overhead, Fed-RSSC, a semi-decentralized architecture, is designed with a local consensus aggregation (LCA) strategy based on device-to-device (D2D) communication. Consequently, Fed-RSSC significantly reduces reliance on direct communication between the server and clients, thereby enhancing both communication efficiency and scalability. Extensive experiments on the NWPU-RESISC45, AID, and UC-Merced datasets validate the effectiveness and scalability of Fed-RSSC, demonstrating its superiority in scene classification.

Synthetic aperture radar (SAR) altimeter is able to measure height with high precision, which has been extensively applied to airborne aircrafts for positioning. With the assumption of a flat surface following a Gaussian distribution, the height is obtained by retracking the waveform. However, this assumption often fails in a complex terrain, leading to unpredictable height bias. In this article, a slope-based height correction (SHC) toward robust height inversion in complex terrain is proposed using linear terrain decomposition. Based on the radar propagation equation, the impact of the topography on height inversion is investigated. Then, the response from complex topography can be divided into a determined part related to a set of primary slopes and a stochastic part with certain undulation. Additionally, the height bias induced by the slopes is given based on power constraints. The error bound of the height correction is also derived correspondingly. The main advantage of the proposed method is reliable height correction with the prior digital elevation model (DEM). Experimental results based on both simulated and real data demonstrate a significant decrease in height bias, which greatly extends the application of the altimeter.

Researchers in the fields of ecological environment and remote sensing pay considerable attention to the estimation of forest canopy height with synthetic aperture radar (SAR). The interest is due to the ability of SAR to penetrate the forest canopy and its sensitivity to forest properties through backscattered intensity. Recent advances in deep learning (DL) present the possibility to derive canopy height maps from single high-resolution (HR) SAR images using neural networks. SAR2Canopy, an innovative framework, is proposed in this paper for canopy height estimation based, which incorporates sensor and scattering knowledge into the estimation. The integration framework allows for the merging of reconstruction trunk scattering features by an equivalent dihedral corner reflector (DCR) scattering model into the supervised tree height estimation process. The proposed method attempts a new approach combining the physical characteristics of SAR data with the nonlinear feature learning ability of DL, potentially extending to different DL algorithms. Experiments are conducted with airborne fully polarimetric P-band SAR data from two areas. Compared to the baseline models, including UNet, DeepLabV3_ResNet50, and FCN_ResNet50, the proposed SAR2Canopy integrated with the DCR model achieves an increase of up to 13.66% in the coefficient of determination (R2), while reducing the root mean squared error (RMSE) and mean absolute error (MAE) by as much as 14.59% and 20.69%, respectively.

Synthetic aperture radar (SAR) altimetry has the capability of altimetry with a good accuracy, especially for the ocean scene. The model-based methods are widely used in the height inversion of the altimetry data due to the strong correlation with physical process. However, the bias of the model will significantly decrease performance of height inversion. In this work, we introduce a novel height inversion algorithm based on the closed-form expression, which is an effective model for measuring radar echoes. Effective initialization strategy expands the application scope, and two-step retracking algorithm is designed which could be used in an iterative least-squares algorithm. In essence, this method aims to remove the coupling between the parameters in closed-form expression. Experimental results using the simulated data indicate that this proposed method has wider application range under different signal-to-noise condition. In addition, precision of two-step method remains stable compared with traditional method, which has potential for actual altimetry system.

As more satellites are launched into space, space security has become an important issue, and the attitude estimation of space targets has been widely studied. Many recent works extract typical features of targets from ISAR images and utilize projection relationship to estimate the attitude. However, it is challenging to extract the features of typical components due to factors like occlusion. And some of these methods are based on conditions that are difficult to meet in reality. In this paper, we propose a two-stage attitude estimation approach for satellite with complex rotation conditions. The first step is to construct a 2D-3D correspondence relationship through convolutional neural network, and the second step is to obtain the satellite attitude according to the projection relationship and 2D-3D correspondence relationship. In order to verify the effectiveness of the proposed approach, a satellite with complex rotation conditions is simulated under different view angles. And the experimental results demonstrate the effectiveness of the proposed method.

This study explores the application of resampling techniques to address the data imbalance issue in LiDAR point cloud-based tree species classification. Considering the data imbalance problem in the point clouds, a simple yet efficient method, resampling is introduced in this paper. We compared two resampling strategies, undersampling the majority classes and oversampling the minority classes. The experimental results show that deep learning models, particularly when augmented with resampling strategies, can significantly improve the classification accuracy. Both strategies increased the overall accuracy (by 0.8% and 2% respectively) and classification of the minority class by 5.56%. And oversampling is superior to undersampling because it makes use of all the training samples.

Radar cross section (RCS) target recognition is an active part of radar target recognition (RTR). But the complex modulation and strong non-stationarity of radar echo signals pose extremely challenges for effective feature extraction and recognition. At the same time, traditional machine learning methods has limited ability to extract the deep features of the signal. To address above issues, this paper proposes an approach that transforms one-dimensional RCS data into joint two-dimensional image through Gramian Angular Field (GAF) transformation and Markov Transition Field (MTF) transformation. This approach fully leverages the static information encoded by the GAF and the dynamic information encoded by the MTF simultaneously. Residual network is utilized to achieve the task of RTR. The simulated experiment results demonstrate the effectiveness and high accuracy of the proposed method.

The inversion of forest structural parameters contributes to evaluation biodiversity and ecosystem functions, as well as enabling sustainable forest management. In this study, we propose a novel method for extracting forest parameters adopting P-band polarimetric synthetic aperture radar (SAR) data. Firstly, we utilize the Freeman-Durden decomposition to extract double-bounce scattering information, including ground-scatterer scattering, scatterer-ground scattering. Then, the scattering amplitude of tree trunks based on the principles of coherent scattering modeling is calculated. Additionally, we introduce the finite cylinder scattering amplitude function and utilize the constraints of the allometric growth model of vegetation to invert forest parameters. The reliability and effectiveness of the proposed method are verified through measurement data, with an RMSE of 3.35m for the inversion results. This research provides a new approach for inverting forest parameters and has potential applications in forest monitoring and ecological studies

Constant False Alarm Rate (CFAR) processing, a critical automated target detection method in radar systems, has been extensively studied for its capabilities. Nonetheless, complex backgrounds and the advancements in stealth technology pose considerable challenges for CFAR in detecting dim targets. To tackle this issue, an adaptive CFAR detection algorithm is proposed that employs two statistically robust models, the Fisher distribution and generalized gamma distribution (GΓD) for clutter modeling. Leveraging the strengths of neural networks in online model recognition, this method can achieve CFAR detection of low signal-to-clutter ratio (SCR) signals in diverse clutter scenarios. Experimental results using high-resolution range profiles (HRRP) demonstrate that, in comparison to traditional CFAR detection methods, this approach exhibits superior performance.

Space target recognition plays a crucial role in ballistic missile interception, especially in the vital task of distinguishing between warheads and decoys. This paper proposes a method to transform one-dimensional (1D) radar cross section (RCS) series into two-dimensional (2D) images by utilizing global information through Relative Position Matrix (RPM). Additionally, the ConvNeXt is enhanced by incorporating a random noise module and introducing a noise reduction self-coding layer to bolster the model's resistance to signal interference. The experimental results indicate that the proposed method achieves high accuracy in recognizing missiles.

Archaeology and Cultural Heritage play a crucial role in fostering the diversity and sustainable development of human culture. Remote sensing data provides valuable insights into underground sites. In this paper, an optical image is employed to classify land cover and extract the Region of Interest (ROI) mask for focused analysis. Moreover, the underground structures are calculated by combining Synthetic Aperture Radar (SAR) data with the Two-Scale Model (TSM). The TSM aids in extracting ground scattering factors while mitigating surface clutter interference. Validation of this method in the Lagash region of southern Iraq demonstrates alignment with known underground structures, as corroborated by published literature.

Synthetic aperture radar (SAR) images are highly sensitive to observation configurations and exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features. As a result, deep learning methods often generalize poorly across different view angles. Inspired by the concept of neural radiance field (NeRF), this study combines SAR imaging mechanisms with neural networks to propose a novel NeRF model for SAR image generation. Following the mapping and projection principles, a set of SAR images are modeled implicitly as a function of attenuation coefficients and scattering intensities in the 3-D imaging space through a differentiable rendering equation. SAR-NeRF is then constructed to learn the distribution of attenuation coefficients and scattering intensities of voxels, where the vectorized form of the 3-D voxel SAR rendering equation and the sampling relationship between the 3-D space voxels and the 2-D view ray grids are analytically derived. Through quantitative experiments on various datasets, we thoroughly assess the multiview representation and generalization capabilities of SAR-NeRF. In addition, this article includes few-shot classification performance improvement as a metric for generation performance. The study found that using 12 images per class resulted in an accuracy improvement of nearly 10% for the classification algorithm.

The space situational awareness (SSA) is a critical issue of space security. The SSA of three-dimensional (3-D) information on flying space targets has been operated by inverse-SAR (ISAR) and telescope observations. However, how good it is to fuse these two observations, i.e. microwave and optical, has not been well discussed. Especially, it would be difficult to determine the dynamic attitude and its projections of a spinning target, only based on ISAR. This paper presents a co-location fusion of ISAR-optical images to acquire a 3-D reconstruction. Making use of semantic segmentation and parallelogram fitting, the dynamic parameters of the target can be acquired, and their projections can be determined. Instead of adopting a scattering point-based method, this paper presents a uniform projection representation by fusing the joint ISAR-optical silhouette-based 3-D reconstruction. This approach enables structure-level voxel reconstruction, even for a spinning target. The simulated datasets of the orthogonal projection geometry of fused space target ISAR-optical images demonstrate that good accuracy and favorable 3-D reconstruction can be achieved.

Synthetic aperture radar (SAR) has become a state-of-the-art technology in many applications without being affected by changes in weather and daylight. Since the detection capability of the single-dimensional SAR is limited, the multidimensional (MD) SAR system, e.g., multibaseline and multipolarization, is used to improve its performance. The design of the MDSAR system should be directly related to the specified applications and a quantitatively analytical theory for bound analysis is required to achieve good efficiency. In this article, a mathematical framework for inversion bounds analysis of MDSAR is proposed. First, based on the attributed scattering center (ASC) model, the Fisher information matrix and its corresponding Cramer–Rao lower bound (CRLB) are used to get the error bound of the estimated parameters. Second, considering the discrete sampling (DS) of the parameters, a probability density function-based conversion is conducted to get the DS CRLB. Finally, the mathematical framework for MD acquisitions is established. The simulation-based experimental results show that the theoretical error bound is consistent with the output of the orthogonal matching pursuit (OMP). The error bound of the parameters obtained by the proposed general mathematical framework can be used to evaluate the performance of inversion algorithms under certain MDSAR configurations.

Rapidly evolving deep learning methods have yielded remarkable performance in Inverse Synthetic Aperture Radar (ISAR) target recognition. However, training deep neural networks often requires large-scale annotated datasets. Due to the scarcity of ISAR images, it is challenging to obtain sufficient well-labeled ISAR datasets. Therefore, this paper considers Few-Shot scenarios and investigates the fast learning and generalization of the model via a Meta-Learning framework. The simulated experimental results illustrate that the Meta-Learning model presented in this paper outperforms traditional Machine Learning method K-Nearest Neighbor (KNN) in terms of testing accuracy, achieving a 72.79% improvement in 5-way 6-shot tasks. In addition, we propose Learning Gain as a criterion to measure the learning ability of the model.

The situation awareness of non-cooperative satellites is essential, but the unknown parameters of the target spin motion makes the 3D (three-dimensional) reconstruction of the target from ISAR (inverse synthetic aperture radar) images difficult. We propose to adopt a joint optical-ISAR system to observe the satellites, and use the complementary information brought by the two different imaging geometries of the two sensors to accomplish the cross-range scaling of ISAR and obtain the target attitude information. Then, a differentiable voxel reconstruction network with updatable view angle parameters is introduced for 3D reconstruction. The experiments show that the proposed method can improve the robustness in the 3D reconstruction of a non-cooperative target.

Under the condition of large difference in imaging angle, Inverse Synthetic Aperture Radar (ISAR) images vary greatly and are difficult to identify. To solve this problem, a decision fusion framework based on scattering centers and Zernike Moment is proposed. In this framework, each feature corresponds to a classifier, then these classifiers are combined together by assigning different weights which reflect the ability of the classifiers. Experiments conducted on simulated ISAR images demonstrate that the proposed method can combine the outputs of the classifiers effectively and achieve better performance than single classifier.

Space target recognition is of great significance for ballistic missile interception, especially in distinguishing between real and decoy warheads. This paper proposes a recognition method that combines feature extraction and Bi-LSTM, surpassing existing algorithms in classification performance. To obtain more discriminative sequences, the method extracts 11-dimensional statistical features of the Radar Cross Section (RCS) sequence using a sliding window, and inputs the feature sequence into the Bi-LSTM network for classification. Even under low signal-to-noise ratio conditions, the proposed algorithm maintains strong performance, demonstrating its noise resistance and generalization ability.

This paper proposes an approach for time series classification of space target motion features with limited data, using reprogrammed time series classification model. Due to the extensive application of the acoustic model in time series classification, the proposed method involves modifying the input data to suit the acoustic model, extracting features using U-Net augmentation, and mapping the output labels of the acoustic models (AMs) to ballistic target recognition labels for accurate recognition. The efficiency and reliability of the method are verified through recognition experiments on simulated data under various conditions.

Above Ground Biomass (AGB) estimation is a basis for rational utilization of natural resources and ecological succession process. Recently, multiple sources of remote sensing data have been used to estimate AGB at high spatial resolution, overcoming the limitations of each type of data. In order to fully exploit the potential of deep learning models based on multi-source data in AGB estimation, an end-to-end Deep Neural Networks (DNN) model is developed using Sentinel-1/2 data, and a learnable weight matrix is designed to tune the contribution of different predictors in multi-source data, thus improving the performance of the model. The experimental results show that the designed DNN model can achieve accurate AGB estimation with a coefficient of determination of 0.7314. Compared with the widely employed XGBoost and Random Forest machine learning models, the proposed DNN model has improved by 6.29% and 5.07% for grassland biomass estimation, respectively.

The complicated distribution patterns of sea ice pose a challenging issue in terms of establishing effective monitoring and early warning systems. Convolutional neural network (CNN) is used by its powerful learning capabilities for accurate segmentation of sea ice areas. In this paper, the connections between large objects and their surrounding pixels are achieved through CNN. In order to enhance the detection of tiny objects, innovative methods including data augmentation, creative design of the loss function, and multiscale strategies are implemented. Knowledge distillation is conducted with the primary network to improve the effectiveness for real-time application. Comparison and ablation experiments demonstrate the effectiveness of the proposed methods on a large open dataset of sea-ice segmentation.

This paper proposes a method that transforms radar cross section (RCS) data into 2D image through Gramian Angular Field (GAF) transformation and utilizes attention mechanism to achieve recognition of four classical types of space targets. The effectiveness of the proposed method is validated on simulated data, demonstrating noteworthy advancements compared to conventional methods and widely employed deep learning methods.

Convolutional neural networks (CNNs) have been widely used in SAR (Synthetic Aperture Radar) target recognition, which can extract feature automatically. However, due to its own structural flaws, CNNs are easy to be fooled by adversarial examples, even if they have excellent performance. In this letter, a novel attack named scattering center model attack (SCMA) is designed, and its generation process does not rely on the prior knowledge of any neural network. Therefore, we can get a stable way which can be applied to any neural network. In addition, an improved scattering center model extraction method, which is the pre-part of SCMA, can filter out the useless noise to optimize the stability of attack. In the experiment, SCMA is compared with advanced attack algorithms. From the experimental results, it is clear to find that SCMA has excellent performance in terms of transfer attack success rate. Furthermore, visualization and interpretability analysis underpin the theoretical feasibility of SCMA.

To address the challenges in synthetic aperture radar (SAR) ship target detection, this paper proposes a SAR ship small target orientation detector named FADet based on semantic flow feature alignment and Gaussian label matching. First, to solve the feature misalignment problem caused by feature extraction downsampling and residual connections, we introduce the FAM module into FPN, which automatically aligns deep and shallow fine-grained semantics information through semantic flow alignment. Second, due to the scattering characteristics of SAR imaging, the boundary information of SAR targets is not obvious, we combining attention mechanisms design an adaptive boundary enhancement module to enhance the target boundary information. Finally, to solve the problem that small targets have difficulty matching positive samples under IOU rules, we design a label matching strategy based on Gaussian distribution. This matching strategy can still learn regression information when two boxes do not intersect. Based on the SSDD+ and RSDD-SAR datasets, the effectiveness of each module in FADet is verified by ablation experiments. Additionally, through comparison experiments with the latest orientation detection methods, FADet achieves a good compromise between accuracy and inference speed. The AP50 and AP75 on the SSDD+ and RSDD-SAR is 91.03, 59.94 and 90.78, 59.91 respectively, and the FPS is 19.83.

The extraction of high-frequency details is generally neglected in single image super-resolution (SISR) for remote sensing images. In this paper, we propose an attentional feature aggregation generative adversarial network (AFA-GAN) with the capability of strong feature extraction and attentional feature fusion to generate high-resolution remote sensing images. We adopt the residual feature aggregation framework for the feature extraction to make full use of the hierarchical features on the residual branches. To better fuse global and local features with inconsistent scales, an attentional feature fusion mechanism is utilized in residual feature aggregation modules. The comprehensive experiments with state-of-the-art SISR methods on the UC Merced dataset demonstrate the effectiveness and superiority of our AFA-GAN.

Array-InSAR system can acquire the multi-baseline images in a single flight, which significantly improves the capability of the practical application. However, the array-InSAR system with many channels has high complexity in both system and data processing due to the cross-channel calibration. Investigation of the 3D reconstruction suitable for sparse array-InSAR images enables the reduction of the number of channels. This work propose evaluates the possibility of the 3D reconstruction using three channel array-InSAR images. To improve the reliability, the proposed 3D phase unwrapping (PU) works on a framework combining short and long baseline interferograms. Additionally, Using a success unwrapping criteria, the bounds of th possible baseline combination is derived. Experimental results by real SAR data show that the proposed method is able to achieve 3D reconstruction in urban areas with high precision using only three channel array-InSAR images and optimize the baseline design of the array-InSAR system.

With the development of$5\mathrm{G}$, the location of base stations is related to the electromagnetic wave scattering with the surface of objects, especially the building walls in cities. In this study, the building wall is simply modeled as a two-dimensional plane surface. Since the roughness of the building wall is relatively small, the specular reflection is the main component of the scattering wave. The bidirectional reflectance distribution function (BRDF) of building walls is approximated as the Fresnel reflection coefficients. Then, a field measurement system, called FUSAR-Rail-S, is established to measure the scattering of the building wall. In the measurement, two different walls are used to analyze the roughness effect on the scattering coefficient. A comparison of the measurement result with the Fresnel reflection coefficients shows that they are in good agreement in most angles. Within a certain angle range, the reflection coefficients increase when the incident angle becomes larger. In addition, the reflection coefficients of the smaller roughness wall are larger.

Synthetic aperture radar (SAR) image classification with deep learning methods has achieved high accuracy on a variety of scenes. Despite the excellent performance of new methods, the phenomenon that small perturbations in data might lead to a sharp change in the result, raises attention to these black architectures. Increasing number of adversarial attacks on convolutional neural network (CNN) have been proposed, while these methods construct their adversarial examples with the aid of corresponding classifiers. Such condition cannot be realized in actual confrontation. Therefore, we introduce a universal adversarial attack on CNN-SAR image classification. In essence, this method focuses on distinguishing target distribution by feature dictionary modeling, excluding prior knowledge of any classifier. Experiments on simulated data of plane models indicate that this proposed method works well at various typical CNNs.

Multi-temporal synthetic aperture radar interferometry (MT-InSAR) is able to reconstruct a 3D surface model with high precision but requires a long waiting time to get the multi-baseline SAR images. Array-InSAR system can acquire multi-baseline images in a single flight, which significantly improves the practical capability of 3D reconstruction. However, the array-InSAR system with many channels has very high complexity in both system and processing because of cross-channel calibration and decoupling. Thus, reducing the number of channels requires the investigation of the 3D reconstruction algorithm to be suitable for sparse array-InSAR images. This work proposed an asymptotic 3D phase unwrapping (PU) algorithm for 3D reconstruction using sparse array-InSAR images, i.e., as few as three or four channels. A 2D (space) + 1D (baseline) PU framework is developed to improve the reliability of the 3D PU and a novel asymptotic strategy is proposed for the combination of the short-long baseline interferogram. Using a successful unwrapping (SU) criteria, the bounds of the possible baseline combination and the expected minimal coherence are derived, respectively. The main advantage of the proposed algorithm is the reliable phase unwrapping with very sparse channels and an analysis of the possible baseline combination. The experimental results by both simulated and real data show that the proposed method can achieve a 3D reconstruction using only three-pass array-InSAR images and optimize the baseline design for the array-InSAR system.

The ZY1-02D satellite, which was launched in 2019, is China’s first civil hyperspectral satellite. However, the laboratory calibration and vicarious calibration methods could not provide accurate radiometric calibration coefficients after the satellite had been launched. In this article, we describe how a cross-calibration method was utilized to calibrate the ZY1-02D hyperspectral imager using the well-calibrated Gaofen-5 Advanced Hyperspectral Imager (GF-5 AHSI). The 6S radiative transfer model was selected to simulate the apparent reflectance of the two hyperspectral sensors under corresponding imaging conditions, and the calibration coefficients were calculated by spectral channel matching. The reflectance-based vicarious calibration was carried out for comparison. Through the validation experiments, it is shown that the reflectance data obtained by cross-calibration and vicarious calibration are basically consistent, showing a stable radiation performance. At the Dunhuang calibration site, the ratio of measured surface reflectance to the cross-calibrated image reflectance is between 0.9 and 1.1, the$R^{2}$values are more than 0.96, and the spectral angles are less than 3°. The validation results for different ground features also show the applicability of the corrected coefficients. When compared with different sensors, the maximum difference between the ZY1-02D reflectance results after cross-calibration and Landsat-8/Sentinel-2 is less than 0.04 and the mean difference is less than 0.02, which further proves that the ZY1-02D hyperspectral imager has a high radiation accuracy after cross-calibration. The proposed cross-calibration method could be used as an effective supplement to the on-orbit calibration method and could also be extended to other satellite hyperspectral imagers.

Natural scene classification based on high resolution one-dimensional range profile (HRRP) has significant value in the field of target recognition and environmental monitoring. Statistical modeling of HRRP has been widely used to extract useful information from clutter-like signals. However, it is still difficult to distinguish manually based on the extracted parameters. This paper proposes an one-dimensional convolutional neural network (1D-CNN) to automatically recognize natural scenes based on the statistical parameters. generalized Gamma distribution ($\mathrm{G}\Gamma\mathrm{D}$) are used to model the HRRP data and the distribution parameters are estimated by the Method of estimating Log Cumulant (MoLC). Classification results on four scenes validates the proposed method with a 99% accuracy.

3-D reconstruction is a hot topic in remote sensing as well as computer vision. The particularity and complexity of the microwave scattering mechanism bring great challenges to the 3D reconstruction of SAR images, and the applicability of existing methods need to be improved. This study proposes an efficient and explainable point clouds framework for three-dimensional reconstruction of SAR images based on three-dimensional parametric electromagnetic part models. This 3-D SAR reconstruction framework consists of two parts: a feature extraction generative adversarial network and a 3-D reconstruction generative network. The feature extraction generative adversarial network has 5 convolutional layers to extract the features of single SAR image and save them in the form of graph, then input this graph to the 3-D reconstruction generative network and we can get the main shape of the target from a SAR image. This framework effectively reduces the numbers of observation for 3-D reconstruction and make the 3-D reconstruction from single SAR image possible.

One of the challenges faced by current intelligent target recognition tasks is the lack of samples, especially in the Inverse Synthetic Aperture Radar (ISAR) images understanding. In this paper, we proposed an ISAR objects generative network to generate multi-aspect ISAR images. A simulated ISAR dataset of six types of aircrafts is produced via, using bidirectional analytic ray tracing (BART) method. Then, the proposed generative network is trained with the simulated ISAR dataset. We evaluated the performance of the proposed network using structural similarity (SSIM). The experimental results show that the generated targets are very close to the real ISAR samples, and the SSIM between generated and real ISAR images of aircrafts is larger than 0.7.

The visible-shortwave infrared Advanced Hyperspectral Imager (AHSI) is a payload onboard the Gaofen-5 satellite, which is China’s first hyperspectral satellite and is part of the Chinese High-Resolution Earth Observation System. As a supplement to the onboard radiometric calibration of the AHSI instrument, vicarious calibration is also required, which is independent of the instrument-based calibration. In this article, a reflectance-based vicarious calibration approach is presented, which takes surface reflectance data, aerosol data, and atmospheric water vapor data into account. The Dunhuang test site, which is one of the China Radiometric Calibration Sites (CRCS) for the vicarious calibration of spaceborne sensors, possesses stable, uniform, and measurable surface objects, so it was chosen as the radiation source to replace the laboratory and onboard calibrators. A Spectra Vista Corporation (SVC) spectral radiometer and a CE318 sun photometer were utilized for the measurement of the surface reflectance and the condition of the aerosol, respectively. The radiance at the entrance pupil at the top of atmosphere was then obtained through the MODerate resolution atmospheric TRANsmission (MODTRAN) atmospheric transmission model. The surface reflectance was obtained using the Fast Line-of-sight Atmospheric Analysis of Hypercubes (FLAASH) atmospheric model for validation. The results show that, with regard to the calibration coefficients, the calibrated AHSI instrument presents a stable radiometric performance among different land-cover types. The ratios on all the bands are between 0.8 and 1.2 and are consistent with the reflectance data from the Dunhuang test site. The${R} ^{{2}}$values are all greater than 0.95 and the spectral angle is all less than 2°. The standard deviations of the ratios are less than 3% for each chosen band, which proves that the calibrated data have a high consistency with thein situmeasurements. When compared with Landsat 8 and Sentinel-2, the mean errors of the surface reflectance are all under 0.06, which further demonstrates that the calibrated reflectance has a high accuracy.

To monitor a space target, 3-D reconstruction from a multiview sequence of the inverse synthetic aperture radar (ISAR) imaging is developed. Scattering of a complex electric-large target, e.g., the ENVISAT satellite model, is numerically calculated, and multiview 2-D ISAR imaging can be simulated. Under the sparse sampling ISAR imaging via compressed sensing, the Kanade-Lucas–Tomasi feature tracker is applied to extraction of target feature points. Then, using the orthographic factorization method, 3-D reconstruction of those feature points is produced. A simple hexagonal frustum is first tested for the feasibility analysis. Two sequences of multiview ISAR imaging, one is the ENVISAT model and another real measurements of a space shuttle, are then presented for 3-D reconstruction. Furthermore, a complex multistructure model of the International Space Station is also studied from multiview ISAR imaging under different sparse sampling rates. All results demonstrate good feasibility of the 3-D reconstruction for those target components, e.g., solar panel and antenna.

Multi-station inverse synthetic aperture radar (MS-ISAR) imaging mode for on-orbit space target is presented. The MS-ISAR network produces bistatic ISAR images from different radar systems in different locations, and may retrieve more information of on-orbit space target, especially, for applications of target detection and recognition, as well as three dimensional (3-D) reconstruction. Numerical scattering/MS-ISAR imaging of a complex electrically-large target, which is different from simple point-scatterers, are simulated to demonstrate the facilities of multi-station networks, and an example of the Envisat on real orbits is presented.

Using numerical scattering simulation of the BART (bidirectional analytic ray tracing method), an angular sequence of high-resolution 2-D ISAR (inverse synthetic aperture radar) images of a space target is produced. The Kanade-Lucas-Tomasi (KLT) feature tracker is then adopted for extracting feature points and matching all angularly consecutive ISAR images. 3-D positions of those featured points can be retrieved by the orthographic factorization method (OFM). As a test, a simple hexagonal frustum is used for validation and analysis. Then, two ISAR imaging sequences, one is the simulation of the Envisat satellite model and another real measurements of the space shuttle, are presented to demonstrate 3-D shape information. It shows good feasibility for 3-D status evaluation and pointing control of solar array of a satellites in orbit.

Simulation of inverse synthetic aperture radar (ISAR) imaging of a space target and reconstruction under sparse sampling via compressed sensing (CS) are developed. The numerical bidirectional analytic ray tracing (BART) method is employed to compute the polarized scattering from an electrically large target. With multiorbit and multistation imaging modes, 2-D and 3-D ISAR images are acquired, leading to information retrieval of the space target, such as shape, structure, attitude, etc. CS is introduced into the reconstruction of ISAR images under sparse sampling. As an example, the models of the Aura satellite and the X-37B orbital test vehicle are presented for ISAR imaging and reconstruction.