Search Results (86)

To improve the unmanned aerial vehicle (UAV) detection and recognition rate based on radar detection technology, this paper proposes to take the radar range-Doppler planar graph that characterizes the echo information of the UAV as the input of the improved YOLOv8 network, uses the YOLOv8n-RFL network to detect and identify the UAV target. In the detection method of the UAV target, first, we detect the echo signal of the UAV through radar, and take the received echo model as the foundation, utilize the principle of generating range-Doppler planar data to convert the received UAV echo signals into range-Doppler planar graphs, and then, use the improved YOLOv8 network to train and detect the UAV target. In the detection algorithm, the range-Doppler planar graph is taken as the input of the YOLOv8n backbone network, the UAV target is extracted from the complex background through the C2f-RVB and C2f-RVBE modules to obtain more feature maps containing multi-scale UAV feature information; the shallow features from the backbone network and deep features from the neck network are integrated through the feature semantic fusion module (FSFM) to generate high-quality fused UAV feature maps with rich details and deep semantic information, and then, the lightweight sharing detection head (LWSD) is utilized to conduct unmanned aerial vehicle (UAV) feature recognition based on the generated fused feature map. By detecting the collected echo data of the unmanned aerial vehicle (UAV), it was found that the proposed improved algorithm can effectively detect the UAV. Full article

Localizing ground-penetrating radar (LGPR) benefits from deep subsurface coupling, ensuring robustness against surface variations and adverse weather. While LGPR is widely recognized as the complement of existing vehicle localization methods, its reliance on prior maps introduces significant challenges. Channel misalignment during traversal positioning and time-dimension distortion caused by non-uniform platform motion degrade matching accuracy. Furthermore, rain and snow conditions induce subsurface water-content variations that distort ground-penetrating radar (GPR) echoes, further complicating the localization process. To address these issues, we propose a weather-resilient adaptive spatio-temporal mask alignment algorithm for LGPR. The method employs adaptive alignment and dynamic time warping (DTW) strategies to sequentially resolve channel and time-dimension misalignments in GPR sequences, followed by calibration of GPR query sequences. Moreover, a multi-level discrete wavelet transform (MDWT) module enhances low-frequency GPR features while adaptive alignment along the channel dimension refines the signals and significantly improves localization accuracy under rain or snow. Additionally, a local matching DTW algorithm is introduced to perform robust temporal image-sequence alignment. Extensive experiments were conducted on both public LGPR datasets: GROUNDED and self-collected data covering five challenging scenarios. The results demonstrate superior localization accuracy and robustness compared to existing methods. Full article

Weather radar, as a crucial component of remote sensing data, plays a vital role in convective weather forecasting through radar echo extrapolation techniques. To address the limitations of existing deep learning methods in radar echo extrapolation, this paper proposes a radar echo extrapolation model based on video vision transformer and spatiotemporal sparse attention (ViViT-Prob). The model takes historical sequences as input and initially maps them into a fixed-dimensional vector space through 3D convolutional patch encoding. Subsequently, a multi-head spatiotemporal fusion module with sparse attention encodes these vectors, effectively capturing spatiotemporal relationships between different regions in the sequences. The sparse constraint enables better utilization of data structural information, enhanced focus on critical regions, and reduced computational complexity. Finally, a parallel output decoder generates all time step predictions simultaneously, then maps back to the prediction space through a deconvolution module to reconstruct high-resolution images. Our experimental results on the Moving MNIST and real radar echo dataset demonstrate that the proposed model achieves superior performance in spatiotemporal sequence prediction and improves the prediction accuracy while maintaining structural consistency in radar echo extrapolation tasks, providing an effective solution for short-term precipitation forecasting. Full article

The non-Gaussian nature of radar-observed clutter echoes induces performance degradation in the context of remote sensing target detection when using conventional Gaussian detectors. To enhance target detection performance, this study addresses the issue of adaptive detection in nonzero-mean non-Gaussian sea clutter environments. The nonzero-mean compound Gaussian model, composed of the texture and complex Gaussian speckle, is utilized to capture the sea clutter. Further, we adopt the inverse Gamma, Gamma, and inverse Gaussian distributions to characterize the texture component. Novel adaptive detectors based on the two-step Rao and Wald tests, taking advantage of the maximum a posteriori (MAP) method to estimate textures, are designed. More specifically, test statistics of the proposed Rao- and Wald-based detectors are derived by assuming the speckle covariance matrix (CM), mean vector (MV), and clutter texture in the first step. Then, the sea clutter parameters assumed to be known are replaced with their estimations, and fully adaptive detectors are obtained. The Monte Carlo performance evaluation experiments using both simulated and measured sea clutter data are conducted, and numerical results validate the constant false alarm rate (CFAR) properties and detection performance of the proposed nonzero-mean detectors. Additionally, the proposed Rao and Wald detectors, respectively, show strong robustness and good selectivity for mismatch signals. Full article

Due to the rebars layer’s shielding effect on Ground Penetrating Radar (GPR) waves, the hyperbolic clutter generated by the rebars interferes with the echoes from void beneath them. The overlapping waveforms of both signals result in attenuation and distortion of the void signals, making it difficult to identify void defects under the rebar. This study proposes an unsupervised generative network model based on Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Through a shared latent space, mapping is achieved between two image domains, effectively eliminating the multiple reflection interference signals caused by the rebar while accurately reconstructing the void defects, generating GPR B-Scan images without rebar clutter. Additionally, the channel and spatial attention module (CSA) is implemented into the model to help the network to better focus on the essential information in GPR images. The proposed model was validated through ablation and comparative experiments using synthetic data. Finally, real GPR data from the Husa Tunnel were used to verify the model’s effectiveness in practical engineering applications. The results showed that this model is highly effective; it improves the visibility of void defects signals, thereby enhancing the interpretability of GPR data for tunnel lining inspections. Full article

Artificial metasurfaces can rapidly modulate their electromagnetic scattering properties and the characteristics of echo signals, which can lead to different imaging features in synthetic aperture radar (SAR) imaging results. Based on this, for the first time, this paper proposes an approach for SAR feature reconfiguring based on periodic phase modulation with inter-pulse time bias. Considering the position and energy requirements of the expected reconfigured imaging target, this approach optimizes the metasurface modulation parameters via a dual algorithm collaborative optimization system, i.e., a modulation parameter generation algorithm (MPGA) and a parameter mapping matching algorithm (PMMA). Time-modulated metasurface targets can reconfigure imaging features of different targets at SAR reconnaissance moments under the guidance of optimized modulation parameters obtained using this approach. Compared with the previous single-point target research on the combination of SAR and metasurfaces, this method is expanded to include the combined analysis of multi-point targets and the reconfigurability of SAR features. Experiments have proved that the programmable reconfigurability of different target features (such as passenger plane targets and truck targets) can be achieved in SAR imaging results through dynamic adjustment of the modulation parameter set. The reconfigured imaging features maintain geometric consistency within the resolution error range, and the size and position of the target can be set as required. Full article

Human activity recognition (HAR) is an important field in the application of millimeter-wave radar. Radar-based HARs typically use Doppler signatures as primary data. However, some common similar human activities exhibit similar features that are difficult to distinguish. Therefore, the identification of similar activities is a great challenge. Given this problem, a recognition method based on convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and class activation mapping (CAM) is proposed in this paper. The spectrogram is formed by processing the radar echo signal. The high-dimensional features are extracted by CNN, and then the corresponding feature vectors are fed into the BiLSTM to obtain the recognition results. Finally, the class activation mapping is used to visualize the decision recognition process of the model. Based on the data of four similar activities of different people collected by mm-wave radar, the experimental results show that the recognition accuracy of the proposed model reached 94.63%. Additionally, the output results of this model have strong robustness and generalization ability. It provides a new way to improve the accuracy of human similar posture recognition. Full article

In this paper, the idea of a radar based on orthogonal frequency division multiplexing (OFDM) is applied to 5G NR Positioning Reference Signals (PRS). This study demonstrates how the estimation of the communication channel using the PRS can be applied for the identification of objects moving near the 5G NR receiver. In this context, this refers to a 5G NR base station capable of detecting a high-speed train (HST). The anatomy of a 5G NR frame as a sequence of OFDM symbols is presented, and different PRS configurations are described. It is shown that spectral analysis of time-varying channel impulse response weights, estimated with the help of PRS pilots, can be used for the detection of transmitted signal reflections from moving vehicles and the calculation of their time and frequency/Doppler shifts. Different PRS configurations with varying time and frequency reference signal densities are tested in simulations. The peak-to-noise-floor ratio (PNFR) of the calculated radar range–velocity maps (RVM) is used for quantitative comparison of PRS-based radar scenarios. Additionally, different echo signal strengths are simulated while also checking various observation window lengths (FFT lengths). This study proves the practicality of using PRS pilots in remote sensing; however, it shows that the most dense configurations do not provide notable improvements, while also demanding considerably more resources. Full article

Deep neural network-based synthetic aperture radar (SAR) automatic target recognition (ATR) systems are susceptible to attack by adversarial examples, which leads to misclassification by the SAR ATR system, resulting in theoretical model robustness problems and security problems in practice. Inspired by optical images, current SAR ATR adversarial example generation is performed in the image domain. However, the imaging principle of SAR images is based on the imaging of the echo signals interacting between the SAR and objects. Generating adversarial examples only in the image domain cannot change the physical world to achieve adversarial attacks. To solve these problems, this article proposes a framework for generating SAR adversarial examples in a 3D physical scene. First, adversarial attacks are implemented in the 2D image space, and the perturbation in the image space is converted into simulated rays that constitute SAR images through backpropagation optimization methods. The mapping between the simulated rays constituting SAR images and the 3D model is established through coordinate transformation, and point correspondence to triangular faces and intensity values to texture parameters are established. Thus, the simulated rays constituting SAR images are mapped to the 3D model, and the perturbation in the 2D image space is converted back to the 3D physical space to obtain the position and intensity of the perturbation in the 3D physical space, thereby achieving physical adversarial attacks. The experimental results show that our attack method can effectively perform SAR adversarial attacks in the physical world. In the digital world, we achieved an average fooling rate of up to 99.02% for three objects in six classification networks. In the physical world, we achieved an average fooling rate of up to 97.87% for these objects, with a certain degree of transferability across the six different network architectures. To the best of our knowledge, this is the first work to implement physical attacks in a full physical simulation condition. Our research establishes a theoretical foundation for the future concealment of SAR targets in practical settings and offers valuable insights for enhancing the attack and defense capabilities of subsequent DNNs in SAR ATR systems. Full article

An intelligent approach is proposed and investigated in this paper for the detection of ultra-low-altitude sea-skimming moving targets for airborne pulse Doppler radar. Without suppressing interferences, the proposed method uses both target and multipath information for detection based on their distinguishable image features and deep learning (DL) techniques. First, the image features of the target, multipath, and sea clutter in the real-measured range-Doppler (RD) map are analyzed, based on which the target and multipath are defined together as the generalized target. Then, based on the composite electromagnetic scattering mechanism of the target and the ocean surface, a scattering-based echo generation model is established and validated to generate sufficient data for DL network training. Finally, the RD features of the generalized target are learned by training the DL-based target detector, such as you-only-look-once version 7 (YOLOv7) and Faster R-CNN. The detection results show the high performance of the proposed method on both simulated and real-measured data without suppressing interferences (e.g., clutter, jamming, and noise). In particular, even if the target is submerged in clutter, the target can still be detected by the proposed method based on the multipath feature. Full article

A new method is proposed for identifying ground clutter in single-polarization radar data based on the gated recurrent unit (GRU) neural network. This method needs five independent input variables related to radar reflectivity structure, which are the reflectivity at current tilt, the reflectivity at the upper tilt, the reflectivity at 3.5 km, the echo top height, and the texture of reflectivity at current tilt, respectively. The performance of the new method is compared with that of the traditional method used in the Weather Surveillance Radar 1988-Doppler system in four cases with different scenarios. The results show that the GRU method is more effective than the traditional method in capturing ground clutter, particularly in situations where ground clutter exists at two adjacent elevation angles. Furthermore, in order to assess the new method more comprehensively, 709 radar scans from Nanchang radar in July 2019 and 708 scans from Jingdezhen radar in June 2019 were collected and processed by the two methods, and the frequency map of radar reflectivity exceeding 20 dBZ was analyzed. The results indicate that the GRU method has a stronger ability than the traditional method to identify and remove ground clutter. Meanwhile, the GRU method can also preserve meteorological echoes well. Full article

Automotive millimeter-wave (MMW) synthetic aperture radar (SAR) systems can achieve high-resolution images of detection areas, providing environmental perceptions that facilitate intelligent driving. However, curved path is inevitable in complex urban road environments. Non-uniform spatial sampling, brought about by curved path, leads to cross-coupling and spatial variation deteriorates greatly, significantly impacting the imaging results. To deal with these issues, we developed an Extended Omega-K Algorithm (EOKA) for an automotive SAR with a curved path. First, an equivalent range model was constructed based on the relationship between the range history and Doppler frequency. Then, using azimuth time mapping, the echo data was reconstructed with a form similar to that of a uniform linear case. As a result, an analytical two-dimensional (2D) spectrum was easily derived without using of the method of series reversion (MSR) that could be exploited for EOKA. The results from the parking lot, open road, and obstacle experimental scenes demonstrate the performance and feasibility of an MMW SAR for environmental perception. Full article

Synthetic aperture radar (SAR) is often affected by other high-power electromagnetic devices during ground observation, which causes unintentional radio frequency interference (RFI) with the acquired echo, bringing adverse effects into data processing and image interpretation. When faced with the task of screening massive SAR data, there is an urgent need for the global perception and detection of interference. The existing RFI detection method usually only uses a single type of data for detection, ignoring the information association between the data at all levels of the real SAR product, resulting in some computational redundancy. Meanwhile, current deep learning-based algorithms are often unable to locate the range of RFI coverage in the azimuth direction. Therefore, a novel RFI processing framework from quick-looks to single-look complex (SLC) data and then to raw echo is proposed. We take the data of Sentinel-1 terrain observation with progressive scan (TOPS) mode as an example. By combining the statistics-assisted network with the sliding-window algorithm and the error-tolerant training strategy, it is possible to accurately detect and locate RFI in the quick looks of an SLC product. Then, through the analysis of the TOPSAR imaging principle, the position of the RFI in the SLC image is preliminarily confirmed. The possible distribution of the RFI in the corresponding raw echo is further inferred, which is one of the first attempts to use spaceborne SAR data to elucidate the RFI location mapping relationship between image data and raw echo. Compared with directly detecting all of the SLC data, the time for the proposed framework to determine the RFI distribution in the SLC data can be shortened by 53.526%. All the research in this paper is conducted on Sentinel-1 real data, which verify the feasibility and effectiveness of the proposed framework for radio frequency signals monitoring in advanced spaceborne SAR systems. Full article

Sparse synthetic aperture radar (SAR) imaging has demonstrated excellent potential in image quality improvement and data compression. However, conventional observation matrix-based methods suffer from high computational overhead, which is hard to use for real data processing. The approximated observation sparse SAR imaging method relieves the computation pressure, but it needs to manually set the parameters to solve the optimization problem. Thus, several deep learning (DL) SAR imaging methods have been used for scene recovery, but many of them employ dual-path networks. To better leverage the complex-valued characteristics of echo data, in this paper, we present a novel complex-valued convolutional neural network (CNN)-based approximated observation sparse SAR imaging method, which is a single-path DL network. Firstly, we present the approximated observation-based model via the chirp-scaling algorithm (CSA). Next, we map the process of the iterative soft thresholding (IST) algorithm into the deep network form, and design the symmetric complex-valued CNN block to achieve the sparse recovery of large-scale scenes. In comparison to matched filtering (MF), the approximated observation sparse imaging method, and the existing DL SAR imaging methods, our complex-valued network model shows excellent performance in image quality improvement especially when the used data are down-sampled. Full article

Precipitation nowcasting, which involves the short-term, high-resolution prediction of rainfall, plays a crucial role in various real-world applications. In recent years, researchers have increasingly utilized deep learning-based methods in precipitation nowcasting. The exponential growth of spatiotemporal observation data has heightened interest in recent advancements such as denoising diffusion models, which offer appealing prospects due to their inherent probabilistic nature that aligns well with the complexities of weather forecasting. Successful application of diffusion models in rainfall prediction tasks requires relevant conditions and effective utilization to direct the forecasting process of the diffusion model. In this paper, we propose a probabilistic spatiotemporal model for precipitation nowcasting, named LLMDiff. The architecture of LLMDiff includes two networks: a conditional encoder–decoder network and a denoising network. The conditional network provides conditional information to guide the denoising network for high-quality predictions related to real-world earth systems. Additionally, we utilize a frozen transformer block from pre-trained large language models (LLMs) in the denoising network as a universal visual encoder layer, which enables the accurate estimation of motion trend by considering long-term temporal context information and capturing temporal dependencies within the frame sequence. Our experimental results demonstrate that LLMDiff outperforms state-of-the-art models on the SEVIR dataset. Full article