Interference suppression is crucial for the proper operation of Synthetic Aperture Radar (SAR). In complex electromagnetic environments, when SAR systems are affected by Coherent Modulation and Forwarding (CMF) signals, Artificial Modulation Targets (AMT) may manifest in the imaging results. To solve this problem, this paper proposes an AMT reconstruction method for C/X-band SAR based on complex signal codec network, which aims to separate and cancel the AMT signals from the raw echoes. The method achieves precise AMT signal reconstruction and cancellation by three aspects. Firstly, a multi-scenario echo dataset with storage size of 65.3 GB is constructed by the authors through modeling and analyzing. Secondly, the network introduces a Large-interlayer Signal Reconstruction Link (LSRL) module to mitigate significant errors caused by size adjustments in traditional codec architectures, while dual-channel processing of amplitude and phase information significantly improves reconstruction accuracy. Thirdly, a Composite Signal Reconstruction Precision (CSRP) loss function, combining global loss and micro-cumulative-error loss, is designed to optimize the training process. The effectiveness of this method is verified by Hardware-In-Loop (HIL) experiments. Results demonstrate that the Structure Similarity Index Measure (SSIM) between reconstructed AMT signals and ground-truth injected signals reaches 0.81054, while the SSIM of interference-canceled scene imagery attains 0.85508. The comparison test proves that the CSRP loss function is superior to the traditional method in convergence and reconstruction effect, and the ablation test verifies the key role of LSRL module in improving performance. Furthermore, discussions on optimizer selection and the abrupt drops phenomenon in training loss curve provide theoretical insights for future research.

Despite significant advancements in salient object detection (SOD) in optical remote sensing images (ORSIs), challenges persist due to the intricate edge structures of ORSIs and the complexity of their contextual relationships. Current deep learning (DL) approaches encounter difficulties in accurately identifying boundary features and lack efficiency in collaboratively modeling the foreground and background by leveraging contextual features. To address these challenges, we propose a stronger multifaceted collaborative salient object detector in ORSIs, termed LBA-MCNet, which incorporates aspects of localization, balance, and affinity. The network focuses on accurately locating targets, balancing detailed features, and modeling image-level global context information. Specifically, we design the edge feature adaptive balancing and adjusting (EFABA) module for precise edge localization, using edge features to guide attention to boundaries and preserve spatial details. Moreover, we design the global distributed affinity learning (GDAL) module to model global context. It captures global context by generating an affinity map from the encoder’s final layer, ensuring effective modeling of global patterns. In addition, deep supervision during deconvolution further enhances feature representation. Finally, we compared with 28 state-of-the-art approaches on three publicly available datasets. The results clearly demonstrate the superiority of our method. The codes of our method are available athttps://github.com/little1bold/LBA-MCNet.

Existing false moving target generation methods face challenges such as uncontrollable position and velocity when against multichannel synthetic aperture radar ground moving target indication (SAR-GMTI) system, as well as significant computational burden in generating dense false targets. Meanwhile, current false blocking image generation methods struggle to create blocking images with controllable position and coverage shape, and the generated images will be partially cancelled against multichannel SAR-GMTI. To tackle these issues, we propose a smart multi-transmitter cooperative false images generation method against multichannel SAR-GMTI and present an accurate and a fast implementation scheme of the method in this paper. The accurate implementation scheme is referred to as the multi-transmitter cooperative frequency-shifting modulation jamming (MTC-FSMJ) method, which can generate false moving targets with controllable radial velocities and initial positions by utilizing multiple transmitters. However, due to the need for iteration calculations in generating a single false target, the computation load of the MTC-FSMJ method becomes substantial when generating dense false moving targets. When we want to generate dense false moving targets, a fast implementation scheme known as the multi-transmitter cooperative template-modulated jamming (MTC-TMJ) method provides an excellent alternative. This approach can quickly generate dense false moving targets within the template without iteration calculations. Moreover, by reasonably designing the template, the MTC-TMJ method can also generate false blocking images with controllable positions, while avoiding partial cancellation. Theoretical analysis and simulation experiments have verified the effectiveness of both implementation structures.

Existing frequency-diverse array (FDA)-based jamming methods against synthetic aperture radar (SAR) still require complex modulation calculations to generate false area targets as the traditional SAR jamming method does, and cannot generate them solely without the regular distribution or repetition in range in SAR images. However, such regular distribution or repetition tends to make false area targets easily identifiable. Therefore, in order to create flexible jamming both in range and azimuth, this letter first proposes a method to obtain Doppler-modulation phase using the Fast Fourier transform (FFT) of a template along the azimuthal direction, which can help the jammer generate template-based jamming in the azimuth domain. Then, by leveraging the distinctive features of FDA’s multifrequency transmission structure, which allows for accurate determination of range positions of false targets within the template, and incorporating the utilization of Doppler-modulation phase, a template-modulation jamming method based on the FDA is proposed. This method can produce solely two-dimensional template-based deceptive or controllable suppression jamming in SAR images without complex modulation calculation requirements. As the final jamming result is determined by the template constructed, the regular jamming distribution can be avoided. The effectiveness of the proposed method is validated through theoretical analysis and simulation experiments.

With the increasing application of deep learning in various domains, salient object detection in optical remote sensing images (ORSI-SOD) has attracted significant attention. However, most existing ORSI-SOD methods predominantly rely on local information from low-level features to infer salient boundary cues and supervise them using boundary ground truth, but fail to sufficiently optimize and protect the local information, and almost all approaches ignore the potential advantages offered by the last layer of the decoder to maintain the integrity of saliency maps. To address these issues, we propose a novel method named boundary-semantic collaborative guidance network (BSCGNet) with dual-stream feedback mechanism. First, we propose a boundary protection calibration (BPC) module, which effectively reduces the loss of edge position information during forward propagation and suppresses noise in low-level features without relying on boundary ground truth. Second, based on the BPC module, a dual feature feedback complementary (DFFC) module is proposed, which aggregates boundary-semantic dual features and provides effective feedback to coordinate features across different layers, thereby enhancing cross-scale knowledge communication. Finally, to obtain more complete saliency maps, we consider the uniqueness of the last layer of the decoder for the first time and propose the adaptive feedback refinement (AFR) module, which further refines feature representation and eliminates differences between features through a unique feedback mechanism. Extensive experiments on three benchmark datasets demonstrate that BSCGNet exhibits distinct advantages in challenging scenarios and outperforms the 17 state-of-the-art (SOTA) approaches proposed in recent years. Codes and results have been released on GitHub: https://github.com/YUHsss/BSCGNet.

For the special azimuth multichannel reconstruction processing of high-resolution wide-swath single-input multiple-output synthetic aperture radar (HRWS-SIMO-SAR) to resolve the Doppler ambiguities, this letter studies the imaging characteristics of conventional SAR Doppler-modulation jamming (DMJAM) in HRWS-SIMO-SAR to provide the theoretical basis for the development of HRWS-SIMO-SAR anti-jamming technology. The theoretical analysis points out that the DMJAM signal will generate equally spaced false targets along the azimuth direction after imaging, and the amplitude of the false targets is decided by the combined sinusoidal function and matched filter loss associated with the Doppler-modulation frequency. The simulation experiments verify the accuracy of the theoretical analysis.

In polarimetric synthetic aperture radar (PolSAR) images, strong scattering centers on man-made targets contaminate their adjacent weak scattering points. We can use the target null theory to mitigate this effect, so that we can acquire the adequate scattering mechanism of these weak points. Since the efficiency of the theory depends on the system biases of the transmitting/receiving polarimetric channels, we analyze the relationship between suppression efficiency and the system bias requirement when the PolSAR system works in two modes: the alternate transmit and simultaneous receive (ATSR) mode and the simultaneous transmit and simultaneous receive (STSR) mode. The theoretical model proposed in this letter is verified by electromagnetic simulations and GF-3 data.

Damaged building detection from remote sensing imagery helps to quickly and rapidly assess losses after an earthquake. In recent years, deep learning technology has become a favorable tool for remote sensing image information detection. Based on the characteristics of damaged buildings in remote sensing images, in this paper, a framework for damaged building detection that considers heterogeneity characteristics is proposed. First, a local-global context attention module is proposed to improve the feature detection ability of the network, which can extract the features of damaged buildings from different directions and effectively aggregate global and local features. In addition, the module takes the correlation between feature maps at different scales into account while extracting information. Second, a feature fusion module with self-attention is established to replace the simple connection between the encoding and decoding processes, which improves the detail feature recovery ability of the network during the upsampling process. Finally, to fully aggregate semantic and detail features at different scales, a multibranch auxiliary classifier is established by adding two separate branches in the prediction stage. The effectiveness of the proposed approach is verified based on data from the 2010 Haiti earthquake, and comparisons with 3 object-oriented methods and 16 existing excellent deep learning models are performed. The IOU increase of 0.03%-7.39% is achieved using the proposed approach compared with excellent deep learning models.

Shadow extraction is an important and challenging task in remote sensing image analysis because the presence of shadows not only reduces radiation information but also affects the interpretation of remote sensing images. In this article, a clustering feature constraint multiscale attention network for shadow extraction from remote sensing images is proposed. First, in addition to the pixel-level description of the traditional neural network, our method focuses on the clustering relationships between pixel pairs to obtain the pixel group features of shadows. The feature extraction capability of the network is improved with a reweighting mechanism at the pixel level and pixel group features. Second, we employ a feature fusion algorithm by considering contextual information to improve the network’s attention toward shadow areas and enhance the nonlinear expression ability during the encoding and decoding layers. Furthermore, considering the most prominent multiscale features of shadows in remote sensing images, a deep multiscale feature aggregation structure is established to better fit the multiscale feature expression of shadows. Finally, we construct a shadow extraction dataset to verify the proposed approach. We compare our method with the results of state-of-the-art deep learning models. The results show that the intersection over union (IOU) of our method is improved by 0.85%–9.51% and that the$F1$-score is improved by 0.73–6.48. In addition, the test results for images with different resolutions prove that the proposed approach is more robust than the other methods.

Feature extraction and recognition of wobbling targets are very important in spatial target surveillance. It has been shown that the scattering centers are slipping on the edge of the rotational symmetry target with the target micro-motion according to the electromagnetic scattering theory and electromagnetic computation analysis. Based on the slippery scattering center model, the micro-motion model and high-range resolution profile (HRRP) model of a wobbling rotational symmetry cone-shaped target are introduced, and the observed HRRP sequence is used to construct a time-range distribution matrix, then a estimation method of the wobbling period is proposed based on time-range distribution matrix correlation, which is validated by electromagnetic computation data and dynamic simulation.

The various applications of polarimetric SAR data have brought to the fore questions of polarimetric calibration. Most polarimetric calibration methods based on distributed targets employed reflection symmetry assumption, which might be inconsistent with the truth due to a possible orientation angle shift, and therefore would skew the polarimetric signatures of targets. In this paper, a model incorporating orientation angle shift effect is introduced to characterize the POL SAR data, and a numeric algorithm is presented. The proposed calibration method can preserve the orientation angle information precisely. Simulations and real SAR data experiments are performed to test the proposed method.