High-resolution Synthetic Aperture Radar Images Research Articles

Monitoring of Water Level Change in a Dam from High-Resolution SAR Data

Accurate measurement of water levels and variations in lakes and reservoirs is crucial for water management. The retrieval of the accurate variations in water levels in lakes and reservoirs with small widths from high-resolution synthetic aperture radar (SAR) images such as the TerraSAR add-on for Digital Elevation Measurements (TanDEM-X) and COnstellation of small Satellites for the Mediterranean basin Observation (COSMO-SkyMed) are presented here. A detailed digital surface model (DSM) for the upstream face of the dam was constructed using SAR interferometry with TanDEM-X data to estimate the water level. The elevation of the waterline below that of the interferometric SAR (InSAR) DSM was estimated based on upstream face modeling. The waterline boundary detected using the SAR Edge Detection Hough Transform algorithm was applied to the restored DSM. The SAR-derived water level variations showed a high correlation coefficient of 0.99 and a gradient of 1.08 with the gauged data. The difference between the gauged data and SAR-derived data was within ±1 m, and the standard deviation of the residual was 0.60 m. These results suggest that water level estimation can be used as an operational supplement for traditional gauged data at remote sites.

Quad-FPN: A Novel Quad Feature Pyramid Network for SAR Ship Detection

Ship detection from synthetic aperture radar (SAR) imagery is a fundamental and significant marine mission. It plays an important role in marine traffic control, marine fishery management, and marine rescue. Nevertheless, there are still some challenges hindering accuracy improvements of SAR ship detection, e.g., complex background interferences, multi-scale ship feature differences, and indistinctive small ship features. Therefore, to address these problems, a novel quad feature pyramid network (Quad-FPN) is proposed for SAR ship detection in this paper. Quad-FPN consists of four unique FPNs, i.e., a DEformable COnvolutional FPN (DE-CO-FPN), a Content-Aware Feature Reassembly FPN (CA-FR-FPN), a Path Aggregation Space Attention FPN (PA-SA-FPN), and a Balance Scale Global Attention FPN (BS-GA-FPN). To confirm the effectiveness of each FPN, extensive ablation studies are conducted. We conduct experiments on five open SAR ship detection datasets, i.e., SAR ship detection dataset (SSDD), Gaofen-SSDD, Sentinel-SSDD, SAR-Ship-Dataset, and high-resolution SAR images dataset (HRSID). Qualitative and quantitative experimental results jointly reveal Quad-FPN’s optimal SAR ship detection performance compared with the other 12 competitive state-of-the-art convolutional neural network (CNN)-based SAR ship detectors. To confirm the excellent migration application capability of Quad-FPN, the actual ship detection in another two large-scene Sentinel-1 SAR images is conducted. Their satisfactory detection results indicate the practical application value of Quad-FPN in marine surveillance.

Multiple Statistics Contributing to Few-Sample Deep Learning for Subtle Trace Detection in High-Resolution SAR Images

With the ability to locate subtle trace objects in the large-scale region, coherent change detection (CCD) has been vital research for a synthetic aperture radar (SAR) system. Finding the difference between repeat-pass repeat-geometry SAR image pair and extracting impressive trace pixels from difference image, the SAR CCD methods consist of a difference generation module and a difference analysis module. The previous CCD methods mainly pay attention to devising a sophisticated working system or an appropriate statistic model to generalize a well difference image. In this article, we introduce the deep learning method into the CCD algorithm and propose a novel trace detection paradigm, which works by hierarchically fusing the unsupervised coherent statistics model and supervised deep learning model. To be specific, the complex reflectance change detection estimator is introduced to generate a difference image and reduce the false alarm in the low clutter-to-noise region. Since the low correlation in a difference image caused by the natural factors severely affects the detection performance, the multiple statistics based on intensity summation and intensity difference are, respectively, proposed to extract water region and vegetation region and suppress the corresponding false alarm. Then the construction of the coarse-to-fine image makes use of land cover information and trace features while the compressed Unet improves the utilization efficiency of trace samples. Meanwhile, the inductive transfer learning based on unsupervised pretraining and few labeled trace samples helps to train a well detection model. Experiments on measured SAR data demonstrate the effectiveness of proposed methods.

A Multiscale Method for Road Network Extraction from High-Resolution SAR Images Based on Directional Decomposition and Regional Quality Evaluation

Road network is an important part of modern transportation. For the demands of accurate road information in practical applications such as urban planning and disaster assessment, we propose a multiscale method to extract road network from high-resolution synthetic aperture radar (SAR) images, which consists of three stages: potential road area segmentation, preliminary network generation, and road network refinement. Multiscale analysis is implemented using an image pyramid framework together with a fixed-size filter. First, a directional road detector is designed to highlight road targets in feature response maps. Subsequently, adaptive fusion is performed independently at each image scale, followed by a threshold method to produce potential road maps. Then, binary maps are decomposed according to the obtained direction information. For each connected component (CC), quality evaluation is conducted to further distinguish road segments and polynomial curve fitting is adopted as a thinning method. Multiscale information fusion is realized through the weighted sum of road curves. Finally, tensor voting and spatial regularization are employed to generate the final road network. Experiments on three TerraSAR images demonstrate the effectiveness of the proposed algorithm to extract road network completely and correctly.

CVCMFF Net: Complex-Valued Convolutional and Multifeature Fusion Network for Building Semantic Segmentation of InSAR Images

Building segmentation of synthetic aperture radar (SAR) images is a challenging task that has not been solved well. High-resolution interferometric SAR (InSAR) images can provide delicate textures and interferometric phase images useful for building segmentation. However, current semantic segmentation networks in computer vision cannot be directly applied in InSAR building segmentation tasks to get good results because of the InSAR images’ particularity. In this article, we present a novel complex-valued convolutional and multifeature fusion network (CVCMFF Net) specifically for building semantic segmentation of InSAR images. This CVCMFF Net not only learns from the complex-valued SAR images but also considers multiscale and multichannel feature fusion. It can effectively segment the layover, shadow, and background on both the simulated InSAR building images and the real airborne InSAR images. The segmentation performance of CVCMFF Net is significantly improved compared with those of other state-of-the-art networks. By feature visualization, the feature extraction rule and feature fusion mechanism of the network are explored. We hope that the proposed network can be beneficial to InSAR phase filtering, phase unwrapping, and information extraction in urban areas.

Improved Fisher MAP Filter for Despeckling of High-Resolution SAR Images Based on Structural Information Detection

Fisher distribution is a popular model for high-resolution (HR) synthetic aperture radar (SAR) images due to its high-peaked and heavy-tailed characteristics as well as its theoretical justification and mathematical tractability. Based on the Fisher modeling of SAR images, the maximum a posteriori (MAP) filter is suggested. In the Fisher model, the parameter of image looks is thought to be fixed to correspond to the formation mechanism of multi-look intensity images, and the other two parameters are accur ately assessed from the SAR image based on second-kind statistics. To improve the Fisher MAP filter especially in the aspect of speckle suppression, the Fisher MAP filter based on recognition of structural information is created using point target detection, the adaptive windowing method, homogeneous region detection, and selection of most homogeneous sub-window. The experiments on despeckling of HR SAR images demonstrate that the improved Fisher MAP filter based on structural information detection can suppress speckle in homogenous and edge regions, and effectively preserve fine details, edges, and point targets.

Pixel Based Multitemporal Sentinel-1 SAR Despeckling PIMSAR

Despeckling of synthetic aperture radar (SAR) data is a challenge for high-resolution applications. This study presents a new pixel-based multitemporal nonlocal averaging (PIMSAR) approach to apply nonlocal mean filtering to ground range detected high (GRDH) resolution SAR images preserving the smallest details of the spatial resolution (10 m). The similarity of SAR pixels is based on the temporal evolution of nature using a two-step process. The mean and standard deviation of pixelwise intensity from spring to autumn are used as the basis of unsupervised classification of the area of interest. The nonlocal averaging is carried out within each class separately in magnitude order of the temporal averages. The filtered image shows the details that are indistinguishable in the original image. The kurtosis of the filtered image is close to that of a corresponding airborne image. PIMSAR preserves the mean intensity of the image with a relative accuracy better than 0.02%, and yet, the processing is rapid per image and the method is easy to use.

High-resolution synthetic aperture radar image classification using multi-scale anisotropic convolutional sparse coding

The classification of high-resolution (HR) synthetic aperture radar (SAR) image is of great significance to SAR scene interpretation and understanding. However, the HR SAR image contains rich ground information and complex spatial structural features. The extraction of effective distinguishing features under the influence of coherent speckle is still a challenging task. A multi-scale anisotropic convolution sparse coding (MACSC) algorithm is proposed for HR SAR image classification. First, the low-order statistical features are extracted to improve the richness of SAR image. Then an unsupervised MACSC model is utilized to learn a set of sparse feature maps and convolution filters for the above statistical features by solving the designed objective function. In MACSC, the multi-scale anisotropic Gaussian kernels are utilized to initialize the dictionary of MACSC. Compared with the isotropic Gaussian kernel of the original CSC, these kernels can more accurately describe the details of different directions and scales in the SAR scene. Meanwhile, the adaptive sparse control factor is introduced into the MACSC model, which can make the learned sparse feature maps suppress the speckle and capture the abundant edge and texture information of the SAR image. After that, the aggregation operation is conducted on multi-scale and multi-direction sparse feature maps to integrate the neighbor pixels and reduce the computing burden. Finally, the obtained feature vector is input into the support vector machine classifier to realize classification. Experiments on three challenging SAR data sets demonstrate that MACSC achieves better classification performance than related sparse representation methods.

Brain-Inspired Fast Saliency-Based Filtering Algorithm for Ship Detection in High-Resolution SAR Images

In this article, we aim to improve the performance of synthetic aperture radar (SAR) ship detection under complex conditions. The complex backgrounds are commonly encountered for high-resolution (HR) SAR ship detection data set, and they greatly influence the detection performance of ships. In recent years, deep neural networks (DNNs) have made substantial improvements on detection by adopting data augmentation. However, the improvement is limited since the models are sensitive to noise. To address this problem, a Fast Saliency-based Filtering algorithm (FSF) is proposed to filter out interference information. The FSF method is inspired by the filtering mechanisms of the human brain, which help people filter out target-irrelevant information fast to better extract target-relevant information. The FSF includes two parts of the bottom-up process and the top-down process. The bottom-up process is used to extract a saliency map of an input image, and the other one is used to filter out target-irrelevant information based on the saliency map. The FSF can be a front-end preprocessing module of DNNs to fast filter out target-irrelevant information and obtain a primary priority map of an input image. Experimental results demonstrate that our brain-inspired FSF method obtains obvious improvement of detection performance on AIR-SARShip-1.0.

Automatic Target Recognition for Low Resolution Foliage Penetrating SAR Images Using CNNs and GANs

In recent years, the technological advances leading to the production of high-resolution Synthetic Aperture Radar (SAR) images has enabled more and more effective target recognition capabilities. However, high spatial resolution is not always achievable, and, for some particular sensing modes, such as Foliage Penetrating Radars, low resolution imaging is often the only option. In this paper, the problem of automatic target recognition in Low Resolution Foliage Penetrating (FOPEN) SAR is addressed through the use of Convolutional Neural Networks (CNNs) able to extract both low and high level features of the imaged targets. Additionally, to address the issue of limited dataset size, Generative Adversarial Networks are used to enlarge the training set. Finally, a Receiver Operating Characteristic (ROC)-based post-classification decision approach is used to reduce classification errors and measure the capability of the classifier to provide a reliable output. The effectiveness of the proposed framework is demonstrated through the use of real SAR FOPEN data.

High-Resolution SAR Image Classification Using Multi-Scale Deep Feature Fusion and Covariance Pooling Manifold Network

The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms.

SAR Image Classification Using Fully Connected Conditional Random Fields Combined with Deep Learning and Superpixel Boundary Constraint

As one of the most important active remote sensing technologies, synthetic aperture radar (SAR) provides advanced advantages of all-day, all-weather, and strong penetration capabilities. Due to its unique electromagnetic spectrum and imaging mechanism, the dimensions of remote sensing data have been considerably expanded. Important for fundamental research in microwave remote sensing, SAR image classification has been proven to have great value in many remote sensing applications. Many widely used SAR image classification algorithms rely on the combination of hand-designed features and machine learning classifiers, which still experience many issues that remain to be resolved and overcome, including optimized feature representation, the fuzzy confusion of speckle noise, the widespread applicability, and so on. To mitigate some of the issues and to improve the pattern recognition of high-resolution SAR images, a ConvCRF model combined with superpixel boundary constraint is developed. The proposed algorithm can successfully combine the local and global advantages of fully connected conditional random fields and deep models. An optimizing strategy using a superpixel boundary constraint in the inference iterations more efficiently preserves structure details. The experimental results demonstrate that the proposed method provides competitive advantages over other widely used models. In the land cover classification experiments using the MSTAR, E-SAR and GF-3 datasets, the overall accuracy of our proposed method achieves 90.18 ± 0.37, 91.63 ± 0.27, and 90.91 ± 0.31, respectively. Regarding the issues of SAR image classification, a novel integrated learning containing local and global image features can bring practical implications.

Fine Building Segmentation in High-Resolution SAR Images Via Selective Pyramid Dilated Network

The building extraction from synthetic aperture radar (SAR) images has always been a challenging research topic. Recently, the deep convolution neural network brings excellent improvements in SAR segmentation. The fully convolutional network and other variants are widely transferred to the SAR studies because of their high precision in optical images. They are still limited by their processing in terms of the geometric distortion of buildings, the variability of building structures, and scattering interference between adjacent targets in the SAR images. In this article, a unified framework called selective spatial pyramid dilated (SSPD) network is proposed for the fine building segmentation in SAR images. First, we propose a novel encoder–decoder structure for the fine building feature reconstruction. The enhanced encoder and the dual-stage decoder, composed of the CBM and the SSPD module, extract and recover the crucial multiscale information better. Second, we design the multilayer SSPD module based on the selective spatial attention. The multiscale building information with different attention on multiple branches is combined, optimized, and adaptively selected for adaptive filtering and extracting features of complex multiscale building targets in SAR images. Third, according to the building features and SAR imaging mechanism, a new loss function called L-shape weighting loss (LWloss) is proposed to heighten the attention on the L-shape footprint characteristics of the buildings and reduce the missing detection of line buildings. Besides, LWloss can also alleviate the class imbalance problem in the optimization stage. Finally, the experiments on a large-scene SAR image dataset demonstrate the effectiveness of the proposed method and verify its superiority over other approaches, such as the region-based Markov random field, U-net, and DeepLabv3+.

Real-World DEM Super-Resolution Based on Generative Adversarial Networks for Improving InSAR Topographic Phase Simulation

Topographic phase simulation is important for deformation estimation in differential synthetic aperture radar (SAR) interferometry (DInSAR). The most commonly used 30-m resolution SRTM digital elevation model (DEM) is usually required to be resampled due to its relatively low resolution (LR) comparing to the high resolution (HR) SAR images. Although the WorldDEM^TM with a 12-m resolution achieves global coverage, it is not available freely. Consequently, it is useful to evaluate the practicability of the super-resolution (SR) from LR SRTM DEMs to HR WorldDEM^TM ones, which has not been investigated. Most existing DEM SR models are trained with synthetic datasets in which the LR DEMs are downsampled from their HR counterparts. However, these models become less effective when applied to real-world scenarios due to the domain gap between the synthetic and real LR DEMs. In this paper, we constructed a real-world DEM SR dataset where the LR and HR DEMs were collected from SRTM and WorldDEM^TM, respectively. An ESRGAN model was adapted to train on the dataset. Considering that the real LR-HR pairs may suffer from misalignment, we introduced the perceptual loss for better optimizing the model. Moreover, a logarithmic normalization was proposed to compress the wide elevation range and adjust the uneven distribution. We also pretrained the model using natural images since collecting sufficient HR DEMs is costly. Experiments demonstrate that the proposed method achieves near 0.69dB improvement of peak signal-to-noise ratio (PSNR). In addition, our method is also validated to improve the topographic phase simulation by 23.42% of MSE.

Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images

Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.

An Anchor-Free Detection Method for Ship Targets in High-Resolution SAR Images

With the rapid development of earth observation technology, high-resolution synthetic aperture radar (HR SAR) imaging satellites could provide more observational information for maritime surveillance. However, there are still some problems to detect ship targets in HR SAR images due to the complex surroundings, targets defocusing, and diversity of the scales. In this article, an anchor-free method is proposed for ship target detection in HR SAR images. First, fully convolutional one-stage object detection (FCOS) as the base network is applied to detect ship targets, achieving better detection performance through pixel-by-pixel prediction of the image. Second, the category-position (CP) module is proposed to optimize the position regression branch features in the FCOS network. This module can improve target positioning performance in complex scenes by generating guidance vector from the classification branch features. At the same time, target classification and boundary box regression methods are redesigned to shield the adverse effects of fuzzy areas in the network training. Finally, to evaluate the effectiveness of CP-FCOS, extensive experiments are conducted on High-Resolution SAR Images Dataset, SAR Ship Detection Dataset, IEEE 2020 Gaofen Challenge SAR dataset, and two complex large-scene HR SAR images. The experimental results show that our method can obtain encouraging detection performance compared with Faster-RCNN, RetinaNet, and FCOS. Remarkably, the proposed method was applied to SAR ship detection in the 2020 Gaofen Challenge. Our team ranked first among 292 teams in the preliminary contest and won seventh place in the final match.

Monitoring of Oil Tank Filling With Spaceborne SAR Using Coherent Scatterers

In this article a new method is introduced for the automatic estimation of all the relevant parameters of oil storage tanks using a single high-resolution synthetic aperture radar (SAR) image. For a given storage tank, this method will estimate its maximum capacity and determine whether it has a fixed or a floating roof. For tanks with a floating roof, the amount of oil stored will also be estimated. If a SAR time series is available all the images can be processed jointly, exploiting the available temporal information to provide more accurate and robust estimates than those obtained from each individual image. The dimensions of each storage tank are derived from its semicircular double reflections, which are detected using the coherent scatterers in the SAR image. The classification between tanks with fixed and floating roofs is performed with a simple machine learning classifier using just three features related to the detected semicircular double reflections. The performance of the proposed method using a single image and a time series is evaluated with three TerraSAR-X images of the port of Rotterdam, containing 167 oil storage tanks of different sizes, and with both fixed and floating roofs.

Multitask Learning for Ship Detection From Synthetic Aperture Radar Images

Ship detection from synthetic aperture radar (SAR) images is inherently subject to the special imaging mechanism of SAR. In recent years, deep-learning-based techniques for detecting objects from optical images have rapidly advanced and promoted the development of SAR image detection technology. However, the strong speckle noise in SAR images degrades low-level feature learning in shallow layers, hindering the higher level learning of semantic features for object detection. In view of the problems encountered in direct end-to-end feature learning for object detection and the close relationship between objects and auxiliary cues, a multitask learning-based object detector (MTL-Det) is proposed in this article to distinguish ships in SAR images. The proposed approach models the ship detection problem, not as a single object detection task, but as three cooperative tasks. The model involves two auxiliary subtasks that are focused on learning object-specific cues ( e.g ., texture and shape) for the ship detection task, which is constrained by the pseudoground truth generated by the main task. Assisted by auxiliary subtasks, the low-level features are robust to speckle noise and reliably support high-level feature learning. Compared with traditional single-task-based object detectors, more discriminative object-specific features are learned by multitask learning without the extra cost of manual labeling. The experiments conducted in this study help demonstrate the advantages of MTL-Det in improving the ship detection performance on two SAR datasets: high-resolution SAR images dataset and large-scale SAR ship detection dataset-v1.0.

Generalized Ambiguity Function for FDA Radar Joint Range, Angle and Doppler Resolution Evaluation

Differs from conventional phased-array, frequency diverse array (FDA) employs a frequency increment across the array elements and thus produces a range-angle-dependent beampattern. This additional range dependence finds applications in target detection/localization, high-resolution synthetic aperture radar (SAR) imaging, and SAR deceptive jamming. To capture the essence behind those applications, we analyze the range, angle, and Doppler resolution capabilities of FDA radar signal via ambiguity function. As conventional ambiguity function is defined for a single-input single-output (SISO) signal, we extend it to the generalized ambiguity function for FDA radar signal, parameterized with the range, angle, and Doppler shifts of a target. Both theoretical analysis and numerical results show that the FDA radar with a large frequency increment has potentials in high-resolution ranging but will suffer from additional range ambiguity within the range bin and Doppler ambiguity. Moreover, the use of frequency increment brings FDA radar a virtual transmit aperture but decreases the directional gain.

Urban Riverway Extraction from High-Resolution SAR Image Based on Blocking Segmentation and Discontinuity Connection

An urban riverway extraction method is proposed for high-resolution synthetic aperture radar (SAR) images. First, the original image is partitioned into overlapping sub-image blocks, in which the sub-image blocks that do not cover riverways are regarded as background. Sub-image blocks covering riverways are then filtered using the iterative adaptive speckle reduction anisotropic diffusion (SRAD) that introduces the relative signal-to-noise ratio (RSNR). The filtered images are segmented quickly by the Sauvola algorithm, and the false riverway fragments are removed by the area and aspect ratio of the connected component in the segmentation results. Using the minimum convex hull of each riverway segment as the connection object, the seeds are automatically determined by the difference between adjacent pyramid layers, and the sub-image block riverway extraction result is used as the bottom layer. The discontinuity connection between river segments is achieved by multi-layer region growth. Finally, the processed sub-image blocks are stitched to get the riverway extraction results for the entire image. To verify the applicability and usefulness of the proposed approach, high-resolution SAR imagery obtained by the Gaofen-3 (GF-3) satellite was used in the assessment. The qualitative and quantitative evaluations of the experimental results show that the proposed method can effectively and completely extract complex urban riverways from high-resolution SAR images.