Multiscale Synthetic Aperture Radar Research Articles

MSSD-Net: Multi-Scale SAR Ship Detection Network

In recent years, the development of neural networks has significantly advanced their application in Synthetic Aperture Radar (SAR) ship target detection for maritime traffic control and ship management. However, traditional neural network architectures are often complex and resource intensive, making them unsuitable for deployment on artificial satellites. To address this issue, this paper proposes a lightweight neural network: the Multi-Scale SAR Ship Detection Network (MSSD-Net). Initially, the MobileOne network module is employed to construct the backbone network for feature extraction from SAR images. Subsequently, a Multi-Scale Coordinate Attention (MSCA) module is designed to enhance the network’s capability to process contextual information. This is followed by the integration of features across different scales using an FPN + PAN structure. Lastly, an Anchor-Free approach is utilized for the rapid detection of ship targets. To evaluate the performance of MSSD-Net, we conducted extensive experiments on the Synthetic Aperture Radar Ship Detection Dataset (SSDD) and SAR-Ship-Dataset. Our experimental results demonstrate that MSSD-Net achieves a mean average precision (mAP) of 98.02% on the SSDD while maintaining a compact model size of only 1.635 million parameters. This indicates that MSSD-Net effectively reduces model complexity without compromising its ability to achieve high accuracy in object detection tasks.

Detecting Urban Floods with Small and Large Scale Analysis of ALOS-2/PALSAR-2 Data

When a large-scale flood disaster occurs, it is important to identify the flood areas in a short time in order to effectively support the affected areas afterwards. Synthetic Aperture Radar (SAR) is promising for flood detection. A number of change detection methods have been proposed to detect flooded areas with pre- and post-event SAR data. However, it remains difficult to detect flooded areas in built-up areas due to the complicated scattering of microwaves. To solve this issue, in this paper we propose the idea of analyzing the local changes in pre- and post-event SAR data as well as the larger-scale changes, which may improve accuracy for detecting floods in built-up areas. Therefore, we aimed at evaluating the effectiveness of multi-scale SAR analysis for flood detection in built-up areas using ALOS-2/PALSAR-2 data. First, several features were determined by calculating standard deviation images, difference images, and correlation coefficient images with several sizes of kernels. Then, segmentation on both small and large scales was applied to the correlation coefficient image and calculated explanatory variables with the features at each segment. Finally, machine learning models were tested for their flood detection performance in built-up areas by comparing a small-scale approach and multi-scale approach. Ten-fold cross-validation was used to validate the model, showing that highest accuracy was offered by the AdaBoost model, which improved the F1 Score from 0.89 in the small-scale analysis to 0.98 in the multi-scale analysis. The main contribution of this manuscript is that, from our results, it can be inferred that multi-scale analysis shows better performance in the quantitative detection of floods in built-up areas.

Multi-scale ship target detection using SAR images based on improved Yolov5

Synthetic aperture radar (SAR) imaging is used to identify ships, which is a vital task in the maritime industry for managing maritime fisheries, marine transit, and rescue operations. However, some problems, like complex background interferences, various size ship feature variations, and indistinct tiny ship characteristics, continue to be challenges that tend to defy accuracy improvements in SAR ship detection. This research study for multiscale SAR ships detection has developed an upgraded YOLOv5s technique to address these issues. Using the C3 and FPN + PAN structures and attention mechanism, the generic YOLOv5 model has been enhanced in the backbone and neck section to achieve high identification rates. The SAR ship detection datasets and AirSARship datasets, along with two SAR large scene images acquired from the Chinese GF-3 satellite, are utilized to determine the experimental results. This model’s applicability is assessed using a variety of validation metrics, including accuracy, different training and test sets, and TF values, as well as comparisons with other cutting-edge classification models (ARPN, DAPN, Quad-FPN, HR-SDNet, Grid R-CNN, Cascade R-CNN, Multi-Stage YOLOv4-LITE, EfficientDet, Free-Anchor, Lite-Yolov5). The performance values demonstrate that the suggested model performed superior to the benchmark model used in this study, with higher identification rates. Additionally, these excellent identification rates demonstrate the recommended model’s applicability for maritime surveillance.

CRTransSar: A Visual Transformer Based on Contextual Joint Representation Learning for SAR Ship Detection

Synthetic-aperture radar (SAR) image target detection is widely used in military, civilian and other fields. However, existing detection methods have low accuracy due to the limitations presented by the strong scattering of SAR image targets, unclear edge contour information, multiple scales, strong sparseness, background interference, and other characteristics. In response, for SAR target detection tasks, this paper combines the global contextual information perception of transformers and the local feature representation capabilities of convolutional neural networks (CNNs) to innovatively propose a visual transformer framework based on contextual joint-representation learning, referred to as CRTransSar. First, this paper introduces the latest Swin Transformer as the basic architecture. Next, it introduces the CNN’s local information capture and presents the design of a backbone, called CRbackbone, based on contextual joint representation learning, to extract richer contextual feature information while strengthening SAR target feature attributes. Furthermore, the design of a new cross-resolution attention-enhancement neck, called CAENeck, is presented to enhance the characterizability of multiscale SAR targets. The mAP of our method on the SSDD dataset attains 97.0% accuracy, reaching state-of-the-art levels. In addition, based on the HISEA-1 commercial SAR satellite, which has been launched into orbit and in whose development our research group participated, we released a larger-scale SAR multiclass target detection dataset, called SMCDD, which verifies the effectiveness of our method.

An Efficient Center-Based Method With Multilevel Auxiliary Supervision for Multiscale SAR Ship Detection

<b>The problem of multi-scale ship detection in synthetic aperture radar (SAR) images has received much attention with the development of deep convolutional neural networks (DCNNs). However, existing DCNN-based multi-scale SAR ship detection methods often lead to time-consuming detection process due to the massive parameters therein. To address this issue, a lightweight center-based detector with the multi-level auxiliary supervision (MLAS) structure is proposed in this paper. First, an extremely lightweight backbone network is designed to improve the computation efficiency and extract SAR image features in a bottom-up manner. Then, a feature fusion network (FFN) containing three multi-scale feature fusion modules is introduced to combine semantic features with different levels. Finally, a novel MLAS-based framework is proposed to train our DCNN with multi-level auxiliary detection subnets. MLAS improves the performance of multi-scale ship detection benefiting from the guidance of multi-level attention. Experimental results on the open SAR image dataset SSDD show that our proposed detector achieves a similar average precision (AP) for the problem of multi-scale SAR ship detection but significantly reduces the computation burden of state-of-the-art methods. The required number of floating points of operations (FLOPs) of our method is only 21.70&#x0025;, 19.30&#x0025;, and 4.81&#x0025; of those of CenterNet, YOLOv3, and RetinaNet, respectively, and the number of learnable weights in our method is only 0.68 million that is 5.63&#x0025;, 1.10&#x0025;, 2.98&#x0025; of those of the aforementioned three existing methods, respectively.</b>

A Fast and Lightweight Detection Network for Multi-Scale SAR Ship Detection under Complex Backgrounds

It is very difficult to detect multi-scale synthetic aperture radar (SAR) ships, especially under complex backgrounds. Traditional constant false alarm rate methods are cumbersome in manual design and weak in migration capabilities. Based on deep learning, researchers have introduced methods that have shown good performance in order to get better detection results. However, the majority of these methods have a huge network structure and many parameters which greatly restrict the application and promotion. In this paper, a fast and lightweight detection network, namely FASC-Net, is proposed for multi-scale SAR ship detection under complex backgrounds. The proposed FASC-Net is mainly composed of ASIR-Block, Focus-Block, SPP-Block, and CAPE-Block. Specifically, without losing information, Focus-Block is placed at the forefront of FASC-Net for the first down-sampling of input SAR images at first. Then, ASIR-Block continues to down-sample the feature maps and use a small number of parameters for feature extraction. After that, the receptive field of the feature maps is increased by SPP-Block, and then CAPE-Block is used to perform feature fusion and predict targets of different scales on different feature maps. Based on this, a novel loss function is designed in the present paper in order to train the FASC-Net. The detection performance and generalization ability of FASC-Net have been demonstrated by a series of comparative experiments on the SSDD dataset, SAR-Ship-Dataset, and HRSID dataset, from which it is obvious that FASC-Net has outstanding detection performance on the three datasets and is superior to the existing excellent ship detection methods.

MW-ACGAN: Generating Multiscale High-Resolution SAR Images for Ship Detection.

In high-resolution Synthetic Aperture Radar (SAR) ship detection, the number of SAR samples seriously affects the performance of the algorithms based on deep learning. In this paper, aiming at the application requirements of high-resolution ship detection in small samples, a high-resolution SAR ship detection method combining an improved sample generation network, Multiscale Wasserstein Auxiliary Classifier Generative Adversarial Networks (MW-ACGAN) and the Yolo v3 network is proposed. Firstly, the multi-scale Wasserstein distance and gradient penalty loss are used to improve the original Auxiliary Classifier Generative Adversarial Networks (ACGAN), so that the improved network can stably generate high-resolution SAR ship images. Secondly, the multi-scale loss term is added to the network, so the multi-scale image output layers are added, and multi-scale SAR ship images can be generated. Then, the original ship data set and the generated data are combined into a composite data set to train the Yolo v3 target detection network, so as to solve the problem of low detection accuracy under small sample data set. The experimental results of Gaofen-3 (GF-3) 3 m SAR data show that the MW-ACGAN network can generate multi-scale and multi-class ship slices, and the confidence level of ResNet18 is higher than that of ACGAN network, with an average score of 0.91. The detection results of Yolo v3 network model show that the detection accuracy trained by the composite data set is as high as 94%, which is far better than that trained only by the original SAR data set. These results show that our method can make the best use of the original data set, improve the accuracy of ship detection.

An Anchor-Free Method Based on Feature Balancing and Refinement Network for Multiscale Ship Detection in SAR Images

Recently, deep-learning methods have been successfully applied to the ship detection in the synthetic aperture radar (SAR) images. It is still a great challenge to detect multiscale SAR ships due to the broad diversity of the scales and the strong interference of the inshore background. Most prevalent approaches are based on the anchor mechanism that uses the predefined anchors to search the possible regions containing objects. However, the anchor settings have a great impact on their detection performance as well as the generalization ability. Furthermore, considering the sparsity of the ships, most anchors are redundant and will lead to the computation increase. In this article, a novel detection method named feature balancing and refinement network (FBR-Net) is proposed. First, our method eliminates the effect of anchors by adopting a general anchor-free strategy that directly learns the encoded bounding boxes. Second, we leverage the proposed attention-guided balanced pyramid to balance semantically the multiple features across different levels. It can help the detector learn more information about the small-scale ships in complex scenes. Third, considering the SAR imaging mechanism, the interference near the ship boundary with the similar scattering power probably affects the localization accuracy because of feature misalignment. To tackle the localization issue, a feature-refinement module is proposed to refine the object features and guide the semantic enhancement. Finally, extensive experiments are conducted to show the effectiveness of our FBR-Net compared with the general anchor-free baseline. The detection results on the SAR ship detection dataset (SSDD) and AIR-SARShip-1.0 dataset illustrate that our method achieves the state-of-the-art performance.

A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background

Convolution neural network (CNN)-based detectors have shown great performance on ship detections of synthetic aperture radar (SAR) images. However, the performance of current models has not been satisfactory enough for detecting multiscale ships and small-size ones in front of complex backgrounds. To address the problem, we propose a novel SAR ship detector based on CNN, which consist of three subnetworks: the Fusion Feature Extractor Network (FFEN), Region Proposal Network (RPN), and Refine Detection Network (RDN). Instead of using a single feature map, we fuse feature maps in bottom–up and top–down ways and generate proposals from each fused feature map in FFEN. Furthermore, we further merge features generated by the region-of-interest (RoI) pooling layer in RDN. Based on the feature representation strategy, the CNN framework constructed can significantly enhance the location and semantics information for the multiscale ships, in particular for the small ships. On the other hand, the residual block is introduced to increase the network depth, through which the detection precision could be further improved. The public SAR ship dataset (SSDD) and China Gaofen-3 satellite SAR image are used to validate the proposed method. Our method shows excellent performance for detecting the multiscale and small-size ships with respect to some competitive models and exhibits high potential in practical application.

A Multilayer Fusion Light-Head Detector for SAR Ship Detection.

Synthetic aperture radar (SAR) ship detection is a heated and challenging problem. Traditional methods are based on hand-crafted feature extraction or limited shallow-learning features representation. Recently, with the excellent ability of feature representation, deep neural networks such as faster region based convolution neural network (FRCN) have shown great performance in object detection tasks. However, several challenges limit the applications of FRCN in SAR ship detection: (1) FRCN with a fixed receptive field cannot match the scale variability of multiscale SAR ship objects, and the performance degrade when the objects are small; (2) as a two-stage detector, FRCN performs an intensive computation and leads to low-speed detection; (3) when the background is complex, the imbalance of easy and hard examples will lead to a high false detection. To tackle the above issues, we design a multilayer fusion light-head detector (MFLHD) for SAR ship detection. Instead of using a single feature map, shallow high-resolution and deep semantic feature are combined to produce region proposal. In detection subnetwork, we propose a light-head detector with large-kernel separable convolution and position sensitive pooling to improve the detection speed. In addition, we adapt focal loss to loss function and training more hard examples to reduce the false alarm. Extensive experiments on SAR ship detection dataset (SSDD) show that the proposed method achieves superior performance in SAR ship detection both in accuracy and speed.

A Densely Connected End-to-End Neural Network for Multiscale and Multiscene SAR Ship Detection

Synthetic aperture radar (SAR) images have been widely used for ship monitoring. The traditional methods of SAR ship detection are difficult to detect small scale ships and avoid the interference of inshore complex background. Deep learning detection methods have shown great performance on various object detection tasks recently but using deep learning methods for SAR ship detection does not show an excellent performance it should have. One of the important reasons is that there is no effective model to handle the detection of multiscale ships in multiresolution SAR images. Another important reason is it is difficult to handle multiscene SAR ship detection including offshore and inshore, especially it cannot effectively distinguish between inshore complex background and ships. In this paper, we propose a densely connected multiscale neural network based on faster-RCNN framework to solve multiscale and multiscene SAR ship detection. Instead of using a single feature map to generate proposals, we densely connect one feature map to every other feature maps from top to down and generate proposals from each fused feature map. In addition, we propose a training strategy to reduce the weight of easy examples in the loss function, so that the training process more focus on the hard examples to reduce false alarm. Experiments on expanded public SAR ship detection dataset, verify the proposed method can achieve an excellent performance on multiscale SAR ship detection in multiscene.

Mapping rice greenhouse gas emissions in the Red River Delta, Vietnam

ABSTRACTRice greenhouse gas (GHG) emissions in the Red River Delta, Vietnam, were mapped using multiscale satellite imagery and a processed-based biogeochemical model. Multiscale synthetic aperture radar (SAR) and optical imagery were fed into a random forest classifier using field observations and surveys as training data to map rice extent. Time series analysis then generated geospatial information on crop calendar, hydroperiod and cropping intensity to use as parameters for the denitrification–decomposition (DNDC) model to estimate emissions. Results show a 2015 rice extent of 583,470 ha with total harvested area of 1,078,783 ha and total methane emissions for the delta at 345.4 million kg CH4-C equivalent to 11.5 million tonnes CO2e (carbon dioxide equivalent). Satellite remote sensing was able to accurately map water management and improve model parameterization to understand the impacts of decisions such as irrigation practices, changes in GHG emissions, and mitigation initiatives. The approach described in this research provides a framework for using open-access SAR to derive maps of rice and landscape characteristics to drive process models like DNDC. These types of tools and approaches will support the next generation of monitoring, reporting, and verification (MRV) efforts to combat climate change and support robust and transparent policy decisions.

Multi-scale synthetic aperture radar remote sensing for archaeological prospection in Han Hangu Pass, Xin'an China

ABSTRACTIncreasing availability of multi-resolution synthetic aperture radar (SAR) data enabled us to demonstrate the benefits of the existing imaging solutions offered by radar satellites for purposes of archaeological prospection. In this study, mid-resolution L-band phased array type L-band synthetic aperture radar (PALSAR) to high-to-very-high-resolution X-band TerraSAR-X/TanDEM-X TerraSAR-X add-on for digital elevation measurements (TanDEM-X) (Stripmap/Staring Spotlight) images were synergistically applied for the archaeological prospection at the Han Hangu Pass, in Xin’an, China. First, the evidence and the stretching direction of the outer walls of the pass were identified from the temporal-averaged products of PALSAR and the terrain from TanDEM Co-registered Single-Look Data. Then, the spatial layout of archaeological monuments (previously documented as well as recently discovered) was observed in the visualization-enhanced Staring Spotlight TerraSAR-X imagery owing to its high spatial and radiometric resolution. The findings of this study highlight the effectiveness of using integrated multi-scale SAR remote sensing data from different platforms in archaeology.

A General Framework for Urban Area Extraction Exploiting Multiresolution SAR Data Fusion

This work is devoted to the presentation of a general framework for multiresolution synthetic aperture radar (SAR) data fusion for the purpose of urban area extraction. Within this framework, prerequisites for a reasonable analysis of SAR data from different sensors and spatial resolutions as well as the state of the art of fusion techniques are discussed. Furthermore, several fusion approaches on the pixel, feature, and decision level are applied on multiscale SAR data sets in a uniform experimental setup over four test sites: 1) Sao Paulo (Brazil); 2) Beijing; 3) Guangzhou; and 4) Shanghai (People’s Republic of China). The accuracy of the resulting urban maps is assessed quantitatively via comparison against manually generated reference data sets. Furthermore, advantages and drawbacks of the applied fusion methods are evaluated.