Remote Sensing

Research

Jump to: Other

21 pages, 5993 KiB

Open AccessArticle

Locality Preserving Property Constrained Contrastive Learning for Object Classification in SAR Imagery

by Jing Wang, Sirui Tian, Xiaolin Feng, Bo Zhang, Fan Wu, Hong Zhang and Chao Wang

Remote Sens. 2023, 15(14), 3697; https://doi.org/10.3390/rs15143697 - 24 Jul 2023

Cited by 1 | Viewed by 952

Abstract

Robust unsupervised feature learning is a critical yet tough task for synthetic aperture radar (SAR) automatic target recognition (ATR) with limited labeled data. The developing contrastive self-supervised learning (CSL) method, which learns informative representations by solving an instance discrimination task, provides a novel [...] Read more.

Robust unsupervised feature learning is a critical yet tough task for synthetic aperture radar (SAR) automatic target recognition (ATR) with limited labeled data. The developing contrastive self-supervised learning (CSL) method, which learns informative representations by solving an instance discrimination task, provides a novel method for learning discriminative features from unlabeled SAR images. However, the instance-level contrastive loss can magnify the differences between samples belonging to the same class in the latent feature space. Therefore, CSL can dispel these targets from the same class and affect the downstream classification tasks. In order to address this problem, this paper proposes a novel framework called locality preserving property constrained contrastive learning (LPPCL), which not only learns informative representations of data but also preserves the local similarity property in the latent feature space. In LPPCL, the traditional InfoNCE loss of the CSL models is reformulated in a cross-entropy form where the local similarity of the original data is embedded as pseudo labels. Furthermore, the traditional two-branch CSL architecture is extended to a multi-branch structure, improving the robustness of models trained with limited batch sizes and samples. Finally, the self-attentive pooling module is used to replace the global average pooling layer that is commonly used in most of the standard encoders, which provides an adaptive method for retaining information that benefits downstream tasks during the pooling procedure and significantly improves the performance of the model. Validation and ablation experiments using MSTAR datasets found that the proposed framework outperformed the classic CSL method and achieved state-of-the-art (SOTA) results. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

23 pages, 10579 KiB

Open AccessArticle

Anomaly-Based Ship Detection Using SP Feature-Space Learning with False-Alarm Control in Sea-Surface SAR Images

by Xueli Pan, Nana Li, Lixia Yang, Zhixiang Huang, Jie Chen, Zhenhua Wu and Guoqing Zheng

Remote Sens. 2023, 15(13), 3258; https://doi.org/10.3390/rs15133258 - 24 Jun 2023

Cited by 1 | Viewed by 1297

Abstract

Synthetic aperture radar (SAR) can provide high-resolution and large-scale maritime monitoring, which is beneficial to ship detection. However, ship-detection performance is significantly affected by the complexity of environments, such as uneven scattering of ship targets, the existence of speckle noise, ship side lobes, [...] Read more.

Synthetic aperture radar (SAR) can provide high-resolution and large-scale maritime monitoring, which is beneficial to ship detection. However, ship-detection performance is significantly affected by the complexity of environments, such as uneven scattering of ship targets, the existence of speckle noise, ship side lobes, etc. In this paper, we present a novel anomaly-based detection method for ships using feature learning for superpixel (SP) processing cells. First, the multi-feature extraction of the SP cell is carried out, and to improve the discriminating ability for ship targets and clutter, we use the boundary feature described by the Haar-like descriptor, the saliency texture feature described by the non-uniform local binary pattern (LBP), and the intensity attention contrast feature to construct a three-dimensional (3D) feature space. Besides the feature extraction, the target classifier or determination is another key step in ship-detection processing, and therefore, the improved clutter-only feature-learning (COFL) strategy with false-alarm control is designed. In detection performance analyses, the public datasets HRSID and LS-SSDD-v1.0 are used to verify the method’s effectiveness. Many experimental results show that the proposed method can significantly improve the detection performance of ship targets, and has a high detection rate and low false-alarm rate in complex background and multi-target marine environments. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

23 pages, 8850 KiB

Open AccessArticle

Refocusing Swing Ships in SAR Imagery Based on Spatial-Variant Defocusing Property

by Jin Wang, Xiangguang Leng, Zhongzhen Sun, Xi Zhang and Kefeng Ji

Remote Sens. 2023, 15(12), 3159; https://doi.org/10.3390/rs15123159 - 17 Jun 2023

Cited by 2 | Viewed by 1086

Abstract

Synthetic aperture radar (SAR) is an essential tool for maritime surveillance in all weather conditions and at night. Ships are often affected by sea breezes and waves, generating a three-dimensional (3D) swinging motion. The 3D swing ship can thereby become severely defocused in [...] Read more.

Synthetic aperture radar (SAR) is an essential tool for maritime surveillance in all weather conditions and at night. Ships are often affected by sea breezes and waves, generating a three-dimensional (3D) swinging motion. The 3D swing ship can thereby become severely defocused in SAR images, making it extremely difficult to recognize them. However, refocusing 3D swing ships in SAR imagery is challenging with traditional approaches due to different phase errors at each scattering point on the ship. In order to solve this problem, a novel method for refocusing swing ships in SAR imagery based on the spatial-variant defocusing property is proposed in this paper. Firstly, the spatial-variant defocusing property of a 3D swing ship is derived according to the SAR imaging mechanism. Secondly, considering the spatial-variant defocusing property, each azimuth line of the SAR 3D swing ship image is modeled as a multi-component linear frequency modulation (MC-LFM) signal. Thirdly, Fractional Autocorrelation (FrAc) is implemented in order to quickly calculate the optimal rotation order set for each azimuth line. Thereafter, Fractional Fourier Transform (FrFT) is performed on the azimuth lines to refocus their linear frequency modulation (LFM) components one by one. Finally, the original azimuth lines are replaced in the SAR image with their focused signals to generate the refocused SAR image. The experimental results from a large amount of simulated data and real Gaofen-3 data show that the proposed algorithm can overcome the spatial-variant defocusing of 3D swing ships. Compared with state-of-the-art algorithms, our approach reduces the image entropy by an order of magnitude, leading to a visible improvement in image quality, which makes it possible to recognize swing ships in SAR images. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 6954 KiB

Open AccessArticle

A SAR Image-Despeckling Method Based on HOSVD Using Tensor Patches

by Jing Fang, Taiyong Mao, Fuyu Bo, Bomeng Hao, Nan Zhang, Shaohai Hu, Wenfeng Lu and Xiaofeng Wang

Remote Sens. 2023, 15(12), 3118; https://doi.org/10.3390/rs15123118 - 14 Jun 2023

Cited by 1 | Viewed by 1190

Abstract

Coherent imaging systems, such as synthetic aperture radar (SAR), often suffer from granular speckle noise due to inherent defects, which can make interpretation challenging. Although numerous despeckling methods have been proposed in the past three decades, SAR image despeckling remains a challenging task. [...] Read more.

Coherent imaging systems, such as synthetic aperture radar (SAR), often suffer from granular speckle noise due to inherent defects, which can make interpretation challenging. Although numerous despeckling methods have been proposed in the past three decades, SAR image despeckling remains a challenging task. With the extensive use of non-local self-similarity, despeckling methods under the non-local framework have become increasingly mature. However, effectively utilizing patch similarities remains a key problem in SAR image despeckling. This paper proposes a three-dimensional (3D) SAR image despeckling method based on searching for similar patches and applying the high-order singular value decomposition (HOSVD) theory to better utilize the high-dimensional information of similar patches. Specifically, the proposed method extends two-dimensional (2D) to 3D for SAR image despeckling using tensor patches. A new, non-local similar patch-searching measure criterion is used to classify the patches, and similar patches are stacked into 3D tensors. Lastly, the iterative adaptive weighted tensor cyclic approximation is used for SAR image despeckling based on the HOSVD method. Experimental results demonstrate that the proposed method not only effectively reduces speckle noise but also preserves fine details. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

24 pages, 3779 KiB

Open AccessArticle

SCM: A Searched Convolutional Metaformer for SAR Ship Classification

by Hairui Zhu, Shanhong Guo, Weixing Sheng and Lei Xiao

Remote Sens. 2023, 15(11), 2904; https://doi.org/10.3390/rs15112904 - 02 Jun 2023

Cited by 1 | Viewed by 1033

Abstract

Ship classification technology using synthetic aperture radar (SAR) has become a research hotspot. Many deep-learning-based methods have been proposed with handcrafted models or using transplanted computer vision networks. However, most of these methods are designed for graphics processing unit (GPU) platforms, leading to [...] Read more.

Ship classification technology using synthetic aperture radar (SAR) has become a research hotspot. Many deep-learning-based methods have been proposed with handcrafted models or using transplanted computer vision networks. However, most of these methods are designed for graphics processing unit (GPU) platforms, leading to limited scope for application. This paper proposes a novel mini-size searched convolutional Metaformer (SCM) for classifying SAR ships. Firstly, a network architecture searching (NAS) algorithm with progressive data augmentation is proposed to find an efficient baseline convolutional network. Then, a transformer classifier is employed to improve the spatial awareness capability. Moreover, a ConvFormer cell is proposed by filling the searched normal convolutional cell into a Metaformer block. This novel cell architecture further improves the feature-extracting capability. Experimental results obtained show that the proposed SCM provides the best accuracy with only

0.46 \times 10^{6}

weights, achieving a good trade-off between performance and model size. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 14472 KiB

Open AccessArticle

Performance Analysis of Channel Imbalance Control and Azimuth Ambiguity Suppression in Azimuth Dual Receiving Antenna Mode of LT-1 Spaceborne SAR System

by Zongxiang Xu, Pingping Lu, Yonghua Cai, Yirong Wu and Robert Wang

Remote Sens. 2023, 15(11), 2765; https://doi.org/10.3390/rs15112765 - 26 May 2023

Cited by 1 | Viewed by 1161

Abstract

The LuTan-1(LT-1), known as the L-band differential interferometric synthetic aperture radar (SAR) satellite system, is an essential piece of civil infrastructure in China, providing extensive applications such as surface deformation monitoring and topographic mapping. To achieve high-resolution and wide-swath (HRWS) observation abilities, the [...] Read more.

The LuTan-1(LT-1), known as the L-band differential interferometric synthetic aperture radar (SAR) satellite system, is an essential piece of civil infrastructure in China, providing extensive applications such as surface deformation monitoring and topographic mapping. To achieve high-resolution and wide-swath (HRWS) observation abilities, the LT-1 takes the dual receiving antenna (DRA) imaging mode as its working mode. However, amplitude and phase errors between channels lead to a mismatch between the reconstruction filter and the multichannel echo signal, worsen the reconstructed azimuth spectrum, and introduce ambiguity targets in the final imaging results, seriously affecting the final imaging quality. In order to better evaluate the channel error and azimuth ambiguity performance of the LT-1 system, this paper proposed an advanced channel consistency correction method and conducted many measured data experiments. The experimental results show that the proposed method is effective, and the LT-1 system has excellent channel error control and azimuth ambiguity performance. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 8561 KiB

Open AccessArticle

Distillation Sparsity Training Algorithm for Accelerating Convolutional Neural Networks in Embedded Systems

by Penghao Xiao, Teng Xu, Xiayang Xiao, Weisong Li and Haipeng Wang

Remote Sens. 2023, 15(10), 2609; https://doi.org/10.3390/rs15102609 - 17 May 2023

Cited by 1 | Viewed by 1200

Abstract

The rapid development of neural networks has come at the cost of increased computational complexity. Neural networks are both computationally intensive and memory intensive; as such, the minimal energy and computing power of satellites pose a challenge for automatic target recognition (ATR). Knowledge [...] Read more.

The rapid development of neural networks has come at the cost of increased computational complexity. Neural networks are both computationally intensive and memory intensive; as such, the minimal energy and computing power of satellites pose a challenge for automatic target recognition (ATR). Knowledge distillation (KD) can distill knowledge from a cumbersome teacher network to a lightweight student network, transferring the essential information learned by the teacher network. Thus, the concept of KD can be used to improve the accuracy of student networks. Even when learning from a teacher network, there is still redundancy in the student network. Traditional networks fix the structure before training, such that training does not improve the situation. This paper proposes a distillation sparsity training (DST) algorithm based on KD and network pruning to address the above limitations. We first improve the accuracy of the student network through KD, and then through network pruning, allowing the student network to learn which connections are essential. DST allows the teacher network to teach the pruned student network directly. The proposed algorithm was tested on the CIFAR-100, MSTAR, and FUSAR-Ship data sets, with a 50% sparsity setting. First, a new loss function for the teacher-pruned student was proposed, and the pruned student network showed a performance close to that of the teacher network. Second, a new sparsity model (uniformity half-pruning UHP) was designed to solve the problem that unstructured pruning does not facilitate the implementation of general-purpose hardware acceleration and storage. Compared with traditional unstructured pruning, UHP can double the speed of neural networks. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

21 pages, 31189 KiB

Open AccessArticle

A Novel Multistage Back Projection Fast Imaging Algorithm for Terahertz Video Synthetic Aperture Radar

by Qibin Zheng, Shuangli Shang, Yinwei Li and Yiming Zhu

Remote Sens. 2023, 15(10), 2602; https://doi.org/10.3390/rs15102602 - 16 May 2023

Viewed by 1175

Abstract

Terahertz video synthetic aperture radar (THz-ViSAR) has tremendous research and application value due to its high resolution and high frame rate imaging benefits. However, it requires more efficient imaging algorithms. Thus, a novel multistage back projection fast imaging algorithm for the THz-ViSAR system [...] Read more.

Terahertz video synthetic aperture radar (THz-ViSAR) has tremendous research and application value due to its high resolution and high frame rate imaging benefits. However, it requires more efficient imaging algorithms. Thus, a novel multistage back projection fast imaging algorithm for the THz-ViSAR system is proposed in this paper to enable continuous playback of images like video. The radar echo data of the entire aperture is first divided into multiple sub-apertures, as with the fast-factorized back projection algorithm (FFBP). However, there are two improvements in sub-aperture imaging. On the one hand, the back projection algorithm (BPA) is replaced by the polar format algorithm (PFA) to improve the sub-aperture imaging efficiency. The imaging process, on the other hand, uses the global Cartesian coordinate system rather than the local polar coordinate system, and the wavenumber domain data of the full aperture are obtained step by step through simple splicing and fusion, avoiding the amount of two-dimensional (2D) interpolation operations required for local polar coordinate system transformation in FFBP. Finally, 2D interpolation for full-resolution images is carried out to image the ground object targets in the same coordinate system due to the geometric distortion caused by linear phase error (LPE) and the mismatch of coordinate systems in different imaging frames. The simulation experiments of point targets and surface targets both verify the effectiveness and superiority of the proposed algorithm. Under the same conditions, the running time of the proposed algorithm is only about 6% of FFBP, while the imaging quality is guaranteed. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

23 pages, 10962 KiB

Open AccessArticle

An Efficient Channel Imbalance Estimation Method Based on Subadditivity of Linear Normed Space of Sub-Band Spectrum for Azimuth Multichannel SAR

by Zongxiang Xu, Pingping Lu, Yonghua Cai, Junfeng Li, Tianyuan Yang, Yirong Wu and Robert Wang

Remote Sens. 2023, 15(6), 1561; https://doi.org/10.3390/rs15061561 - 13 Mar 2023

Cited by 4 | Viewed by 1481

Abstract

Azimuth multichannel (AMC) technology is one of the mainstream technical approaches to realize high-resolution wide-swath (HRWS) imaging. It has been successfully applied to several synthetic aperture radar (SAR) satellites in orbit. However, the inevitable imbalance between channels can seriously affect the azimuth reconstruction [...] Read more.

Azimuth multichannel (AMC) technology is one of the mainstream technical approaches to realize high-resolution wide-swath (HRWS) imaging. It has been successfully applied to several synthetic aperture radar (SAR) satellites in orbit. However, the inevitable imbalance between channels can seriously affect the azimuth reconstruction spectrum, introducing ghost targets into the final imaging results and degrading the SAR image quality. In order to address this issue, this paper proposes a channel imbalance estimation method based on minimizing the sum of the sub-band norm (MSSBN) for the reconstructed azimuth spectrum. First, the amplitude imbalance is calibrated in the range-Doppler domain. Then, the echo in each channel with phase imbalances is reconstructed by filters separately and converted to the range-Doppler domain. Finally, the global optimization algorithm is used to find the phase error of each channel so that the reconstructed postcompensation spectrum has the smallest sub-band spectrum norm sum. By two-dimensional blocking, this method can also estimate the space-varying phase imbalance in the range dimension and the time-varying phase imbalance in the azimuth dimension. Experimental results using simulated and actual AMC SAR data from the GF-3 system validate the proposed algorithm’s high estimation accuracy and excellent computational efficiency. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

15 pages, 3092 KiB

Open AccessCommunication

A Clutter Parameter Estimation Method Based on Origin Moment Derivation

by Liru Yang, Yongxiang Liu, Wei Yang, Xiaolong Su and Qinmu Shen

Remote Sens. 2023, 15(6), 1551; https://doi.org/10.3390/rs15061551 - 12 Mar 2023

Viewed by 1148

Abstract

Parameter estimation is significant to prediction and estimation in the field of radar clutter characteristics. Therefore, it is necessary to study the problem of parameter estimation. The K-distribution is a commonly used model in sea clutter, which is a two-parameter model with shape [...] Read more.

Parameter estimation is significant to prediction and estimation in the field of radar clutter characteristics. Therefore, it is necessary to study the problem of parameter estimation. The K-distribution is a commonly used model in sea clutter, which is a two-parameter model with shape parameters and scale parameters. The value of the shape parameters should be greater than 0. Moment estimation is usually used to estimate the parameters of the K-distribution. It overcomes the disadvantage of large computation compared with the maximum likelihood estimation method. However, the moment estimation usually uses two different order origin moments to solve the parameters. The joint solution of different order will cause large calculation errors, and sometimes the shape parameter is estimated to be less than 0. In the origin moment expression, the order k can be regarded as a continuous variable. By calculating the relationship between the k-order origin moment and its derivative, a parameter estimation method based on the origin moment derivative is proposed. The estimation efficiency and accuracy are compared with some moment estimation methods. Both simulation data and measured clutter data show that this method can achieve 100% estimation efficiency, can obtain higher estimation accuracy, and can also avoid the situation where the estimated value of the shape parameter is less than 0. Using the same idea to estimate the parameters in the two-parameter models, log–normal and Weibull distribution, we can also obtain the parameters with higher estimation accuracy. The experiments show that the higher-order origin moments are sensitive to the data, and the lower-order moments should be selected as far as possible. By selecting the appropriate order k, we can obtain ideal estimation parameters. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

24 pages, 9088 KiB

Open AccessArticle

A Modified 2-D Notch Filter Based on Image Segmentation for RFI Mitigation in Synthetic Aperture Radar

by Zewen Fu, Hengrui Zhang, Jianhui Zhao, Ning Li and Fengbin Zheng

Remote Sens. 2023, 15(3), 846; https://doi.org/10.3390/rs15030846 - 02 Feb 2023

Cited by 6 | Viewed by 2303

Abstract

Synthetic aperture radar (SAR), as an active microwave sensor, can inevitably receive radio frequency interference (RFI) generated by various electromagnetic equipment. When the SAR system receives RFI, it will affect SAR imaging and limit the application of SAR images. As a kind of [...] Read more.

Synthetic aperture radar (SAR), as an active microwave sensor, can inevitably receive radio frequency interference (RFI) generated by various electromagnetic equipment. When the SAR system receives RFI, it will affect SAR imaging and limit the application of SAR images. As a kind of RFI mitigation method, notch filtering method is a classical method with high efficiency and robust performance. However, the notch filtering methods pay no attention to the protection of useful signals. This paper proposed a modified 2-D notch filter based on image segmentation for RFI mitigation with signal-protected capability. (1) The adaptive gamma correction (AGC) approach was utilized to enhance the SAR image with RFI in the range-frequency and azimuth-time domain. (2) The modified selective binary and Gaussian filtering regularized level set (SBGFRLS) model was utilized to further process the image after AGC to accurately extract the contour of the useful signals with interference, which is more conducive to protecting the useful signals without interference. (3) The Generalized Singular Value Thresholding (GSVT) based low-rank sparse decomposition (LRSD) model was utilized to separate the RFI signals and the useful signals. Then, the useful signals were restored to the raw data. The simulation experiments and measured data experiments show that the proposed method can effectively mitigate RFI and protect the useful signals whether there are RFI with single source or multiple sources. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

20 pages, 54042 KiB

Open AccessArticle

Sparsity-Based Joint Array Calibration and Ambiguity Resolving for Forward-Looking Multi-Channel SAR Imagery

by Jingyue Lu, Xuhua Wang, Yunhe Cao and Lei Zhang

Remote Sens. 2023, 15(3), 647; https://doi.org/10.3390/rs15030647 - 21 Jan 2023

Viewed by 1198

Abstract

Forward-looking multi-channel synthetic aperture radar (FLMC-SAR) can realize two-dimension image formation in monostatic mode. This system must face the problem of left–right Doppler ambiguity. In the traditional methods, the spatial degrees of freedom of the FLMC-SAR system is expected to achieve Doppler ambiguity [...] Read more.

Forward-looking multi-channel synthetic aperture radar (FLMC-SAR) can realize two-dimension image formation in monostatic mode. This system must face the problem of left–right Doppler ambiguity. In the traditional methods, the spatial degrees of freedom of the FLMC-SAR system is expected to achieve Doppler ambiguity resolving by beamforming approaches. However, the influence of array error on beamforming cannot be ignored. In practice, the array error will lead to the mismatch of the space–time characteristic, which will reduce the performance of the Doppler ambiguity resolving method based on beamforming. This paper proposes a sparsity-based joint array calibration and ambiguity resolving method to enhance the robustness of FLMC-SAR imagery. For the FLMC-SAR system, the space–time characteristic of targets is first analyzed, based on which the observation model of FLMC-SAR Doppler ambiguity combined with array error is derived. Then, the Doppler ambiguity resolving and array error estimation are transformed into a sparse recovery problem. A modified quasi-Newton method is proposed to realize the array error estimation and Doppler ambiguity resolving of all targets in the local area. Finally, the results of the simulation and the real-data experiments verify that the proposed method can achieve FLMC-SAR Doppler ambiguity resolving and imaging. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

24 pages, 8413 KiB

Open AccessArticle

Mutual Interference Mitigation of Millimeter-Wave Radar Based on Variational Mode Decomposition and Signal Reconstruction

by Yanbing Li, Bo Feng and Weichuan Zhang

Remote Sens. 2023, 15(3), 557; https://doi.org/10.3390/rs15030557 - 17 Jan 2023

Cited by 5 | Viewed by 1704

Abstract

As an important remote sensing technology, millimeter-wave radar is used for environmental sensing in many fields due to its advantages of all-day, all-weather operation. With the increasing use of radars, inter-radar interference becomes increasingly critical. Severe mutual interference degrades radar signal quality and [...] Read more.

As an important remote sensing technology, millimeter-wave radar is used for environmental sensing in many fields due to its advantages of all-day, all-weather operation. With the increasing use of radars, inter-radar interference becomes increasingly critical. Severe mutual interference degrades radar signal quality and affects the performance of post-processing, e.g., synthetic aperture radar (SAR) imaging and target tracking. Aiming to deal with mutual interference, we propose an interference mitigation method based on variational mode decomposition (VMD). With the characteristics that the target is a single-frequency sine wave and the interference is a broadband signal, VMD is used for decomposing the radar received signal and separating the target from the interference. Interference mitigation is then implemented in each decomposed mode, and an interference-free signal is obtained through the reconstruction process. Simulation results of multi-target scenarios demonstrate that the proposed method outperforms existing decomposition-based methods. This conclusion is also confirmed by the experimental results on real data. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 18793 KiB

Open AccessArticle

Generation of Multiple Frames for High Resolution Video SAR Based on Time Frequency Sub-Aperture Technique

by Congrui Yang, Zhen Chen, Yunkai Deng, Wei Wang, Pei Wang and Fengjun Zhao

Remote Sens. 2023, 15(1), 264; https://doi.org/10.3390/rs15010264 - 02 Jan 2023

Cited by 4 | Viewed by 2022

Abstract

Video Synthetic Aperture Radar (ViSAR) operating in spotlight mode has received widespread attention in recent years because of its ability to form a sequence of SAR images for a region of interest (ROI). However, due to the heavy computational burden of data processing, [...] Read more.

Video Synthetic Aperture Radar (ViSAR) operating in spotlight mode has received widespread attention in recent years because of its ability to form a sequence of SAR images for a region of interest (ROI). However, due to the heavy computational burden of data processing, the application of ViSAR is limited in practice. Although back projection (BP) can avoid unnecessary repetitive processing of overlapping parts between consecutive video frames, it is still time-consuming for high-resolution video-SAR data processing. In this article, in order to achieve the same or a similar effect to BP and reduce the computational burden as much as possible, a novel time-frequency sub-aperture technology (TFST) is proposed. Firstly, based on azimuth resampling and full aperture azimuth scaling, a time domain sub-aperture (TDS) processing algorithm is proposed to process ViSAR data with large coherent integration angles to ensure the continuity of ViSAR monitoring. Furthermore, through frequency domain sub-aperture (FDS) processing, multiple high-resolution video frames can be generated efficiently without sub-aperture reconstruction. In addition, TFST is based on the range migration algorithm (RMA), which can take into account the accuracy while ensuring efficiency. The results of simulation and X-band airborne SAR experimental data verify the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 27137 KiB

Open AccessArticle

CLISAR-Net: A Deformation-Robust ISAR Image Classification Network Using Contrastive Learning

by Peishuang Ni, Yanyang Liu, Hao Pei, Haoze Du, Haolin Li and Gang Xu

Remote Sens. 2023, 15(1), 33; https://doi.org/10.3390/rs15010033 - 21 Dec 2022

Cited by 6 | Viewed by 1509

Abstract

The inherent unknown deformations of inverse synthetic aperture radar (ISAR) images, such as translation, scaling, and rotation, pose great challenges to space target classification. To achieve high-precision classification for ISAR images, a deformation-robust ISAR image classification network using contrastive learning (CL), i.e., CLISAR-Net, [...] Read more.

The inherent unknown deformations of inverse synthetic aperture radar (ISAR) images, such as translation, scaling, and rotation, pose great challenges to space target classification. To achieve high-precision classification for ISAR images, a deformation-robust ISAR image classification network using contrastive learning (CL), i.e., CLISAR-Net, is proposed for deformation ISAR image classification. Unlike traditional supervised learning methods, CLISAR-Net develops a new unsupervised pretraining phase, which means that the method uses a two-phase training strategy to achieve classification. In the unsupervised pretraining phase, combined with data augmentation, positive and negative sample pairs are constructed using unlabeled ISAR images, and then the encoder is trained to learn discriminative deep representations of deformation ISAR images by means of CL. In the fine-tuning phase, based on the deep representations obtained from pretraining, a classifier is fine-tuned using a small number of labeled ISAR images, and finally, the deformation ISAR image classification is realized. In the experimental analysis, CLISAR-Net achieves higher classification accuracy than supervised learning methods for unknown scaled, rotated, and combined deformations. It implies that CLISAR-Net learned more robust deep features of deformation ISAR images through CL, which ensures the performance of the subsequent classification. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

22 pages, 5682 KiB

Open AccessArticle

Aircraft Detection in SAR Images Based on Peak Feature Fusion and Adaptive Deformable Network

by Xiayang Xiao, Hecheng Jia, Penghao Xiao and Haipeng Wang

Remote Sens. 2022, 14(23), 6077; https://doi.org/10.3390/rs14236077 - 30 Nov 2022

Cited by 3 | Viewed by 1919

Abstract

Due to the unique imaging mechanism of synthetic aperture radar (SAR), targets in SAR images often shows complex scattering characteristics, including unclear contours, incomplete scattering spots, attitude sensitivity, etc. Automatic aircraft detection is still a great challenge in SAR images. To cope with [...] Read more.

Due to the unique imaging mechanism of synthetic aperture radar (SAR), targets in SAR images often shows complex scattering characteristics, including unclear contours, incomplete scattering spots, attitude sensitivity, etc. Automatic aircraft detection is still a great challenge in SAR images. To cope with these problems, a novel approach called adaptive deformable network (ADN) combined with peak feature fusion (PFF) is proposed for aircraft detection. The PFF is designed for taking full advantage of the strong scattering features of aircraft, which consists of peak feature extraction and fusion. To fully exploit the strong scattering features of the aircraft in SAR images, peak features are extracted via the Harris detector and the eight-domain pixel detection of local maxima. Then, the saliency of aircraft under multiple imaging conditions is enhanced by multi-channel blending. All the PFF-preprocessed images are fed into the ADN for training and testing. The core components of ADN contain an adaptive spatial feature fusion (ASFF) module and a deformable convolution module (DCM). ASFF is utilized to reconcile the inconsistency across different feature scales, raising the characterization capabilities of the feature pyramid and improving the detection performance of multi-scale aircraft further. DCM is introduced to determine the 2-D offsets of feature maps adaptively, improving the geometric modeling abilities of aircraft in various shapes. The well-designed ADN is established by combining the two modules to alleviate the problems of the multi-scale targets and attitude sensitivity. Extensive experiments are conducted on the GaoFen-3 (GF3) dataset to demonstrate the effectiveness of the PFF-ADN with an average precision of 89.34%, as well as an F1-score of 91.11%. Compared with other mainstream algorithms, the proposed approach achieves state-of-the-art performance. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

19 pages, 23977 KiB

Open AccessArticle

A Novel Echo Separation Scheme for Space-Time Waveform-Encoding SAR Based on the Second-Order Cone Programming (SOCP) Beamformer

by Shuo Han, Yunkai Deng, Wei Wang, Qingchao Zhao, Jinsong Qiu, Yongwei Zhang and Zhen Chen

Remote Sens. 2022, 14(22), 5888; https://doi.org/10.3390/rs14225888 - 20 Nov 2022

Viewed by 1501

Abstract

Space-time waveform-encoding (STWE)-synthetic aperture radar (SAR) is an effective way to accomplish high-resolution and wide-swath (HRWS) imaging. By designing the specific signal transmit mode, the echoes from several subswaths are received within a single receiving window and overlap each other in STWE-SAR. In [...] Read more.

Space-time waveform-encoding (STWE)-synthetic aperture radar (SAR) is an effective way to accomplish high-resolution and wide-swath (HRWS) imaging. By designing the specific signal transmit mode, the echoes from several subswaths are received within a single receiving window and overlap each other in STWE-SAR. In order to separate the overlapped echoes, the linear-constrained minimum variance (LCMV) beamformer, a single-null beamformer, is typically used. However, the LCMV beamformer has a very narrow and unstable notch depth, which is not sufficient to accurately separate the overlapped echoes with large signal energy differences between subswaths. The issue of signal energy differences in STWE-SAR is first raised in this paper. Moreover, a novel echo separation scheme based on a second-order cone programming (SOCP) beamformer is proposed. The beam pattern generated by the SOCP beamformer allows flexible adjustment of the notch width and depth, which effectively improves the quality of separation results compared to the LCMV beamformer. The simulation results illustrate that the scheme can greatly enhance the performance of echo separation. Furthermore, the experimental results based on the X-band STWE-SAR airborne system not only demonstrate the scheme’s effectiveness but also indicate that it holds great promise for future STWE-SAR missions. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

16 pages, 2085 KiB

Open AccessArticle

Retrieval of Farmland Surface Soil Moisture Based on Feature Optimization and Machine Learning

by Jianhui Zhao, Chenyang Zhang, Lin Min, Zhengwei Guo and Ning Li

Remote Sens. 2022, 14(20), 5102; https://doi.org/10.3390/rs14205102 - 12 Oct 2022

Cited by 14 | Viewed by 2338

Abstract

Soil moisture is an important parameter affecting environmental processes such as hydrology, ecology, and climate. Synthetic aperture radar (SAR) microwave remote sensing is an important means of farmland surface soil moisture (SSM) measurement. The inversion of farmland SSM by microwave remote sensing is [...] Read more.

Soil moisture is an important parameter affecting environmental processes such as hydrology, ecology, and climate. Synthetic aperture radar (SAR) microwave remote sensing is an important means of farmland surface soil moisture (SSM) measurement. The inversion of farmland SSM by microwave remote sensing is greatly affected by vegetation cover. To address this problem, a multisource remote sensing inversion method of farmland SSM based on feature optimization and machine learning is proposed in this paper. Six typical machine learning algorithms suitable for small sample training, including random forest, radial basis function neural network, generalized regression neural network, support vector regression, genetic algorithm–back propagation neural network, and extreme learning machine, were selected in this paper. The features extracted from Sentinel-1/2 and Radarsat-2 remote sensing data were analyzed by Pearson correlation, and those with high correlation coefficients were selected to form the optimal feature subset as the input for the subsequent machine learning models. Then, the SSM collaborative inversion models under different machine learning algorithms were constructed, and comparative experiments were set up to select the optimal prediction model. The models’ accuracy under different feature parameters were studied, and the difference in the performance between the dual-polarization SAR data and the quad-polarization SAR data in SSM inversion was explored. The experimental results showed that among the six models, the random forest model had a higher inversion accuracy, with a coefficient of determination of 0.6395 and a root mean square error of 0.0264 cm³/cm³. Meanwhile, the inversion accuracy could be greatly improved after feature optimization, and the inversion accuracy of the quad-polarization SAR data combined with optical remote sensing data, was better than that of the dual-polarization SAR data combined with optical remote sensing data. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

26 pages, 9669 KiB

Open AccessArticle

by Elisa Giusti, Selenia Ghio, Amir Hosein Oveis and Marco Martorella

Remote Sens. 2022, 14(18), 4665; https://doi.org/10.3390/rs14184665 - 19 Sep 2022

Cited by 11 | Viewed by 2419

Abstract

Most of the existing Non-Cooperative Target Recognition (NCTR) systems follow the “closed world” assumption, i.e., they only work with what was previously observed. Nevertheless, the real world is relatively “open” in the sense that the knowledge of the environment is incomplete. Therefore, unknown [...] Read more.

Most of the existing Non-Cooperative Target Recognition (NCTR) systems follow the “closed world” assumption, i.e., they only work with what was previously observed. Nevertheless, the real world is relatively “open” in the sense that the knowledge of the environment is incomplete. Therefore, unknown targets can feed the recognition system at any time while it is operational. Addressing this issue, the Openmax classifier has been recently proposed in the optical domain to make convolutional neural networks (CNN) able to reject unknown targets. There are some fundamental limitations in the Openmax classifier that can end up with two potential errors: (1) rejecting a known target and (2) classifying an unknown target. In this paper, we propose a new classifier to increase the robustness and accuracy. The proposed classifier, which is inspired by the limitations of the Openmax classifier, is based on proportional similarity between the test image and different training classes. We evaluate our method by radar images of man-made targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. Moreover, a more in-depth discussion on the Openmax hyper-parameters and a detailed description of the Openmax functioning are given. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

23 pages, 6581 KiB

Open AccessArticle

A Repeater-Type SAR Deceptive Jamming Method Based on Joint Encoding of Amplitude and Phase in the Intra-Pulse and Inter-Pulse

by Dongyang Cheng, Zhenchang Liu, Zhengwei Guo, Gaofeng Shu and Ning Li

Remote Sens. 2022, 14(18), 4597; https://doi.org/10.3390/rs14184597 - 14 Sep 2022

Cited by 3 | Viewed by 1496

Abstract

Due to advantages such as low power consumption and high concealment, deceptive jamming against synthetic aperture radar (SAR) has received extensive attention in electronic countermeasures. However, the false targets generated by most of the deceptive jamming methods still have limitations, such as poor [...] Read more.

Due to advantages such as low power consumption and high concealment, deceptive jamming against synthetic aperture radar (SAR) has received extensive attention in electronic countermeasures. However, the false targets generated by most of the deceptive jamming methods still have limitations, such as poor controllability and strong regularity. Inspired by the idea of waveform coding, this paper proposed a repeater-type SAR deceptive jamming method through the joint encoding of amplitude and phase in intra-pulse and inter-pulse, which can generate a two-dimensional controllable deceptive jamming effect. Specifically, the proposed method mainly includes two parts, i.e., grouping and encoding. The number of groups determines the number of false targets, and the presence of the phase encoding produces false targets. The amplitude encoding affects the amplitude of the false targets. For the intra-pulse cases, the proposed method first samples the intercepted SAR signal. Meanwhile, the sampling points are grouped in turn. For the inter-pulse cases, the grouped objects are the pulses. Subsequently, the joint encoding of amplitude and phase is performed on each group, which generates jamming signals with deceptive effects. In this paper, the imaging effect of the generated jamming signals is analyzed in detail, and the characteristics of false targets, including numbers, position, and amplitude, are derived. The simulation and experimental results verify the correctness of the theoretical analysis. In addition, the superiority of the proposed method is verified by comparing it with other methods. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

19 pages, 3459 KiB

Open AccessArticle

Crop Classification Based on GDSSM-CNN Using Multi-Temporal RADARSAT-2 SAR with Limited Labeled Data

by Heping Li, Jing Lu, Guixiang Tian, Huijin Yang, Jianhui Zhao and Ning Li

Remote Sens. 2022, 14(16), 3889; https://doi.org/10.3390/rs14163889 - 11 Aug 2022

Cited by 7 | Viewed by 1802

Abstract

Crop classification is an important part of crop management and yield estimation. In recent years, neural networks have made great progress in synthetic aperture radar (SAR) crop classification. However, the insufficient number of labeled samples limits the classification performance of neural networks. In [...] Read more.

Crop classification is an important part of crop management and yield estimation. In recent years, neural networks have made great progress in synthetic aperture radar (SAR) crop classification. However, the insufficient number of labeled samples limits the classification performance of neural networks. In order to solve this problem, a new crop classification method combining geodesic distance spectral similarity measurement and a one-dimensional convolutional neural network (GDSSM-CNN) is proposed in this study. The method consisted of: (1) the geodesic distance spectral similarity method (GDSSM) for obtaining similarity and (2) the one-dimensional convolutional neural network model for crop classification. Thereinto, a large number of training data are extracted by GDSSM and the generalized volume scattering model which is based on radar vegetation index (GRVI), and then classified by 1D-CNN. In order to prove the effectiveness of the GDSSM-CNN method, the GDSSM method and 1D-CNN method are compared in the case of a limited sample. In terms of evaluation and verification of methods, the GDSSM-CNN method has the highest accuracy, with an accuracy rate of 91.2%, which is 19.94% and 23.91% higher than the GDSSM method and the 1D-CNN method, respectively. In general, the GDSSM-CNN method uses a small number of ground measurement samples, and it uses the rich polarity information in multi-temporal fully polarized SAR data to obtain a large number of training samples, which can quickly improve the accuracy of classification in a short time, which has more new inspiration for crop classification. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

22 pages, 22443 KiB

Open AccessArticle

An Improved RFI Mitigation Approach for SAR Based on Low-Rank Sparse Decomposition: From the Perspective of Useful Signal Protection

by Hengrui Zhang, Lin Min, Jing Lu, Jike Chang, Zhengwei Guo and Ning Li

Remote Sens. 2022, 14(14), 3278; https://doi.org/10.3390/rs14143278 - 07 Jul 2022

Cited by 4 | Viewed by 1762

Abstract

As an open system, synthetic aperture radar (SAR) inevitably receives radio frequency interference (RFI) generated by electromagnetic equipment in the same band. The existence of RFI seriously affects SAR signal processing and image interpretation. In recent years, many algorithms and models related to [...] Read more.

As an open system, synthetic aperture radar (SAR) inevitably receives radio frequency interference (RFI) generated by electromagnetic equipment in the same band. The existence of RFI seriously affects SAR signal processing and image interpretation. In recent years, many algorithms and models related to RFI mitigation have been proposed. However, most of that focus on effectively mitigating the RFI is insufficient to protect the useful signals. This article proposes a mitigation method of RFI with a signal-protected capability. (1) The kurtosis coefficient is used to detect RFI pulse-by-pulse, and the echoes containing RFI are stored in matrix form. (2) The preliminary extraction of RFI is complete by low-rank sparse decomposition of the echo matrix containing RFI. (3) For the secondary separation of RFI, the accurate position of RFI in the preliminary extraction results is located by the fuzzy C-means clustering; then, we separate the RFI and the remaining useful signals again and reconstruct the useful signals to complete the mitigation work. The proposed method can further protect useful signals while effectively removing interference through the secondary separation of RFI. Experimental results based on simulated and measured data verify the performance and potential of the proposed method. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

21 pages, 3770 KiB

Open AccessArticle

A Novel Topography Retrieval Algorithm Based on Single-Pass Polarimetric SAR Data and Terrain Dependent Error Analysis

by Congrui Yang, Fengjun Zhao, Chunle Wang, Mengmeng Wang, Xiuqing Liu and Robert Wang

Remote Sens. 2022, 14(13), 3176; https://doi.org/10.3390/rs14133176 - 01 Jul 2022

Viewed by 1383

Abstract

Polarimetric synthetic aperture radar (PolSAR) data provide an alternative way for topography retrieval, especially when limited PolSAR data are available. This article proposes a novel topography retrieval algorithm based on the Lambertian backscatter model that further improves the vertical precision of digital elevation [...] Read more.

Polarimetric synthetic aperture radar (PolSAR) data provide an alternative way for topography retrieval, especially when limited PolSAR data are available. This article proposes a novel topography retrieval algorithm based on the Lambertian backscatter model that further improves the vertical precision of digital elevation model (DEM) generation and requires only one flight. The key idea of the proposed algorithm is to avoid data fluctuations caused by the ratio of the azimuth slope angle to the polarimetric orientation angle (POA). The previous research has confirmed the feasibility of generating a DEM based on single-pass PolSAR data, but its effect on the quality of reference DEM has not been well-explained. To analyze this effect, a large number of experiments on DEM with different resolutions are conducted. In addition, an in-depth analysis of non-linear and terrain-dependent errors is performed. The L-band PolSAR data of NASA/JPL TOPSAR and ALOS-2 PALSAR-2 and interferometric SAR (InSAR) DEM data are used to verify the proposed algorithm. The experimental results show that PolSAR data can be used as an additional reliable information source for DEM fusion under certain conditions to improve the quality of public DEM. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Figure 1

11 pages, 3612 KiB

Open AccessCommunication

Vehicle Target Detection Network in SAR Images Based on Rectangle-Invariant Rotatable Convolution

by Lu Li, Yuang Du and Lan Du

Remote Sens. 2022, 14(13), 3086; https://doi.org/10.3390/rs14133086 - 27 Jun 2022

Cited by 2 | Viewed by 1619

Abstract

In recent years, convolutional neural network (CNN)-based methods have been extensively explored for synthetic aperture radar (SAR) target detection. Nevertheless, the convolutional sampling locations of CNNs cannot accurately fit vehicle targets due to the fixed sampling mechanism in the convolutional kernel. In this [...] Read more.

In recent years, convolutional neural network (CNN)-based methods have been extensively explored for synthetic aperture radar (SAR) target detection. Nevertheless, the convolutional sampling locations of CNNs cannot accurately fit vehicle targets due to the fixed sampling mechanism in the convolutional kernel. In this paper, we focus on the vehicle target detection task in SAR images and propose a novel rectangle-invariant rotatable convolution (RIRConv) to determine more accurately the convolutional sampling locations for vehicle targets. Specifically, this paper considers the shape characteristic of vehicle targets in SAR images, which always retain a rectangular shape despite having varying sizes, aspect ratios, and rotation angles. The proposed RIRConv equips three additional learnable attribute parameters, namely, width, height, and angle attributes, to adaptively adjust the sampling locations in the convolutional kernel according to the targets. In addition, the RIRConv applies a modulation mechanism to focus on the sampling locations that significantly affect the output. Finally, the RIRConv is introduced into the single-shot multibox detector (SSD) to realize SAR vehicle target detection. In this way, the feature representation capability of SSD for vehicle targets can be enhanced, thus leading to higher detection performance. Notably, the proposed RIRConv is “plug-and-play” and can also be used with other existing advanced technologies to achieve higher detection performance. The experiments based on the measured miniSAR data validate the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

Other

Jump to: Research

15 pages, 5635 KiB

Open AccessTechnical Note

Recognizing the Shape and Size of Tundra Lakes in Synthetic Aperture Radar (SAR) Images Using Deep Learning Segmentation

by Denis Demchev, Ivan Sudakow, Alexander Khodos, Irina Abramova, Dmitry Lyakhov and Dominik Michels

Remote Sens. 2023, 15(5), 1298; https://doi.org/10.3390/rs15051298 - 26 Feb 2023

Cited by 1 | Viewed by 2088

Abstract

Permafrost tundra contains more than twice as much carbon as is currently in the atmosphere, and it is warming six times as fast as the global mean. Tundra lakes dynamics is a robust indicator of global climate processes, and is still not well [...] Read more.

Permafrost tundra contains more than twice as much carbon as is currently in the atmosphere, and it is warming six times as fast as the global mean. Tundra lakes dynamics is a robust indicator of global climate processes, and is still not well understood. Satellite data, particularly, from synthetic aperture radar (SAR) is a suitable tool for tundra lakes recognition and monitoring of their changes. However, manual analysis of lake boundaries can be slow and inefficient; therefore, reliable automated algorithms are required. To address this issue, we propose a two-stage approach, comprising instance deep-learning-based segmentation by U-Net, followed by semantic segmentation based on a watershed algorithm for separating touching and overlapping lakes. Implementation of this concept is essential for accurate sizes and shapes estimation of an individual lake. Here, we evaluated the performance of the proposed approach on lakes, manually extracted from tens of C-band SAR images from Sentinel-1, which were collected in the Yamal Peninsula and Alaska areas in the summer months of 2015–2022. An accuracy of 0.73, in terms of the Jaccard similarity index, was achieved. The lake’s perimeter, area and fractal sizes were estimated, based on the algorithm framework output from hundreds of SAR images. It was recognized as lognormal distributed. The evaluation of the results indicated the efficiency of the proposed approach for accurate automatic estimation of tundra lake shapes and sizes, and its potential to be used for further studies on tundra lake dynamics, in the context of global climate change, aimed at revealing new factors that could cause the planet to warm or cool. Full article

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

SAR-Based Signal Processing and Target Recognition

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Related Special Issue

Published Papers (25 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI