Change detection (CD) is a crucial application in the field of remote sensing. Most current CD methods are based on deep learning and revolve around multispectral data. However, a common issue arising from these methods is the large number of model parameters due to the high dimensionality of the data channels. In this paper, we propose a lightweight Siamese network structure that minimally incorporates conventional convolutional layers. Additionally, in terms of data preprocessing, we select the R, G, and B channels of multispectral data for dehazing processing, and employ the processed data as inputs to the network. Experimental results illustrate the outstanding effectiveness and efficiency of the proposed method.

In recent years, the complex-valued convolutional neural network (CV-CNN) for processing complex data has made great use in the field of SAR data processing. In this paper, a complex-valued activation enhancement method named CRIA is constructed based on the cross-fusion of real and imaginary activation in the activation layer of CV-CNN, the core of which is to cross-combine the real and imaginary parts of the activation output of the two activation functions to enhance the overall processing of complex data, to enhance the ability of the network to parse complex value information. By conducting classification experiments on ship slices in SAR images of complex data, the experimental results show that the CRIA method in the activation layer can accelerate the network convergence speed and enhance the network classification performance.

Flood disasters are a major factor threatening agriculture, human life, and property safety. Suppose the areas affected by flood disasters can be effectively delineated and reasonably predicted. In that case, it will not only be beneficial for agricultural production but also provide convenience for disaster prevention and relief. The Segment Anything Model (SAM) emerged, providing innovative ideas for many visual tasks. SAM has excellent feature extraction ability in network models, allowing it to adapt to different scenes and effectively segment various objects, so it also has great application prospects in remote sensing images. Therefore, this article utilizes the excellent feature extraction ability of the SAM to enable the model to adapt to downstream tasks of remote sensing image segmentation. This article will use the decoder structure of CycleGAN as the decoder. Due to the large proportion of background in remote sensing images, this article also enhances the loss function to suit remote sensing image tasks better. The MMFlood dataset in this article consists of Synthetic Aperture Radar (SAR) images combined with a digital elevation model (DEM). The experimental results demonstrate improved performance with the assistance of SAM compared to Unet++.

Change detection (CD) methods for remote sensing images based on deep learning have garnered increasing research attention. However, existing deep learning approaches are often tailored for specific types of sensors. Extending these methods to dual-sensor scenarios presents challenges, including difficulties in data fusion and an increase in parameter numbers. To address these challenges, we propose a novel dual-stream encoder–decoder CD network architecture. In the encoder, the architecture comprises a shared-weight Siamese Unet stream for each sensor, with unique weights for different sensors. Before the decoder, a 3-D attention module (3-D AM) is incorporated, processing encoder outputs and fusing features from different streams. In addition, to mitigate the increased model parameter numbers due to the use of dual sensors, we propose a lightweight Unet architecture along with a time-difference structure in each stream. The proposed model is evaluated across multiple scenarios on a dual-sensor CD dataset, yielding an F1 score of 0.572 and the parameter number of 0.91 M. These results showcase high performance on a cost-effective level. Our code is available athttps://github.com/CodeofHuang/SmaDS_SiamUnet.

Since synthetic aperture radar (SAR) can observe all-weather, it is widely used in ship target detection and segmentation tasks. However, SAR images have complex backgrounds and clutter interference, which affect the segmentation accuracy. This paper proposes a saliency-combined complex-valued U-Net. The network consists of two parts, namely complex-valued U-Net(CV-UNet) and original U-Net. The CV-UNet is used to process the measured data of SAR images which contains amplitude and phase information. The original U-Net is used to process the saliency map generated by the SAR image, and the results of two parts of the network output are connected. The experiment uses the measured data of HISEA-1 to make a target segmentation dataset, and uses the trained network for testing. The results show that the performance of the proposed method is better than that of the original U-Net and CV-UNet.

Synthetic aperture radar (SAR) system is susceptible to electromagnetic jamming during imaging, which seriously affects the subsequent interpretation of SAR images. Aiming at the problem of active suppressive jamming, this paper proposes a suppression method of SAR suppressive jamming based on self-supervised complex-valued deep learning, which consists of a novel complex-valued jamming suppression network CV-MUNet++ and a self-supervised training strategy. CV-MUNet++ could fully use the amplitude and phase information of complex-valued SAR images. The network’s weights, activation functions, and convolution operations are designed for complex domain processing. The different information representations of target and jamming in amplitude and phase in SAR images are mined to achieve jamming suppression. The self-supervised training strategy is proposed to solve the problem of relying heavily on manually labeled samples in the traditional network training process and is suitable for application scenarios where ground truth is difficult to obtain under complex jamming. The experimental results show that the proposed method could effectively suppress the active jamming of complex backgrounds and has the ability to self-supervised intelligent jamming suppression.

In Synthetic Aperture Radar (SAR) images, ship targets suffer from blurring due to pitch, yaw, and sway, resulting in poor recognition accuracy. This paper proposes a complex-valued convolutional neural network (CV-CNN) architecture called CV-RotNet. This neural network could realize the recognition of SAR defocused ship targets without three-dimensional rotation refocusing. CV-RotNet makes full use of the amplitude and phase information of SAR images. Based on the classic deep learning architecture, RotNet and CV-RotNet were designed from the real domain and the complex domain. CV-RotNet and RotNet are tested on the five types of SAR three-dimensional rotating target simulation samples and the three types of GF-3 real ship target samples. Experimental results show that the average accuracy of CV-RotNet is higher than RotNet with the same degree of freedom, which reflects the advantages of CV-RotNet over RotNet.

Heterogeneous images imaged by different types of sensors have different imaging mechanisms, reflecting the characteristics of different sides of the target scene; while multi-source images formed by different working platforms or at different times have different imaging perspectives, and provide different target scene information. The use of multi-source heterogeneous images for fusion to obtain target and scene information more accurately and comprehensively has potential important applications in many fields such as military, medicine, and meteorology, and has become an important branch of image processing research. To this end, a PCGP algorithm is proposed in this paper to realize the fusion of optical images from different sources and SAR images. It first applies PCA transformation to the multi-source data images to obtain the principal component variables, then performs histogram matching on the first principal components of the transformed data sources, and finally uses the gradient pyramid decomposition algorithm to fuse the matched images to obtain a fused image. Then, the proposed fusion algorithm is tested in the fusion task of remote sensing images from different sources of GF2, GF6 and GF3. The experimental results show that the proposed fusion algorithm has better results.

With the rapid development of GNSS(Global Navigation Satellite System), reflected signal processing is applied in various fields. In this paper, the GNSS-R system is used to detect the moving target by compensation. Corresponding algorithms are proposed for medium RCS target and low RCS target respectively to improve the detection performance of the whole system. It lays the foundation for the follow-up target detection. Simulation results can prove the detection performance of the algorithm, and also demonstrate the feasibility of the GNSS-R system to detect moving targets from the perspective of simulation.

The echo of maneuvering targets are analyzed in this paper, which combined with Polynomial phase signals (PPSs), and compared the parameter estimation performance of PPSs based on the fractional Fourier transform(FRFT), the cubic phase function and the product cubic phase function(PCPF) for the echo characteristics. In the third section of the paper, sparse aperture imaging is performed on the aircraft, which flies smoothly and the echo is randomly missing, and the RD algorithm of the maneuvering target is compared with FRFT and PCPF algorithm.

With the cross of Global Navigation Satellite Systems (GNSS) technology and other subject, the application of GNSS has been expanded. This paper focus on the research on the feasibility investigation of target detection with GNSS and a stationary receiver. The system is discussed as a whole and performs link calculation to verify the experimental scene. The experimental results obtained from the GNSS and stationary receiver experiments are presented and analyzed to demonstrate the performance of the algorithm.

Nowadays, deep learning has got a major success in computer vision, especially in image recognition. In this paper, a new architecture based on DenseNets which is referred to as Multi-Scale Input Spatial Pyramid Pooling Fusion Networks (MSPPF-nets) is proposed for the work of classification of local climate zones (LCZs). Multi-scale remote sensing images can be inputs of the networks by the benefit of Spatial Pyramid Pooling (SPP) layer, multi-scale features from different channels were extracted and fused by our multi-branch-input framework. The final classification results have illustrated the feasibility of this presented classification method.

Extraction of ocean surface wind field from data collected by shipborne high-frequency surface wave radar (HFSWR) is an ongoing challenge because of the inherent directional ambiguity and the effect of complicated platform motion on radar Doppler spectra. Here, a method for extracting the wind direction and speed from the spreading first-order radar Doppler spectra is first presented. First, the mathematical model of the wind direction versus a variable spreading parameter is developed. Moreover, based on the spreading characteristic of the first-order spectra, an approach for simultaneously determining the unambiguous wind direction and the unique spreading parameter with a single receiving antenna is presented. Furthermore, the relationship between the wind speed and the spreading parameter is derived on the basis of the relationship between the drag coefficient and the spreading parameter, and the wind speed can be determined. Therefore, the wind field of ocean area covered by shipborne HFSWR can be measured by sequentially exploiting the presented method, which is more beneficial for shipborne HFSWR because of smaller installation space and less cost. Simulation results and discussions of basic applications show the feasibility of wind field measurement in shipborne HFSWR. Experimental results validate the presented method and evaluate the detection accuracy and distance limit. The range for wind field measurement is up to 120 km, which is the range for which the signal-to-noise ratio typically exceeds about 11 dB in the relevant first-order portions of the backscatter spectra. Comparisons between the radar-measured and forecasting or buoy-measured results show good agreement.

Shipborne high-frequency surface wave radar (SHFSWR) has exhibited great advantages over onshore HFSWR (OHFSWR) in ocean remote sensing. Unlike OHFSWR, SHFSWR suffers the problem of Doppler spectrum spread owing to platform movement, which is a great challenge preventing the extraction of ocean surface parameters for SHFSWR. To address this challenge, in this letter, the mathematical model of ocean surface wind direction is first investigated based on the first-order SHFSWR cross section. Furthermore, a method for the wind direction inversion without ambiguity from the spread Doppler spectrum is proposed using a single receiving antenna. Meanwhile, the wind directions of the sea area covered by radar can be obtained by sequentially utilizing the proposed method, which is more appropriate for the application of SHFSWR with limited deck space and less cost. Experimental results of the real data collected in Taiwan Strait preliminarily verify the detection accuracy and the distance limit of the wind direction inversion, as the root-mean-square error and the detection range are 9.85° and 120 km, respectively.

Sea clutter has a major impact on the detection performance of a shipborne high-frequency surface wave radar (HFSWR) system. Due to the platform motion of shipborne HFSWR, the Doppler spectrum of the first-order sea clutter suffers from some broadening so that the targets submerged in this broadening Doppler spectrum can be hardly detected. In this letter, an improved oblique projection (IOP) method, combining the oblique projection (OP) algorithm and the method of sea clutter suppression in the Doppler domain, is proposed to suppress sea clutter in both Doppler domain and spatial domain for shipborne HFSWR. Compared with the OP and the orthogonal weighting algorithms, the proposed IOP algorithm is shown to give far superior suppression results in the Doppler domain and can achieve better azimuth estimation results based on real data.