Distributed array radar(DAR)has the benefits including flexible deployment and excellent spatial resolution.However,the independent clock and oscillator configurations of each radar unit,along with the instability introduced by trigger signals transmitted over the feeder link,introduce errors in time and phase synchronization,thereby reducing the accuracy of coherent synthesis in a DAR.This paper proposes a time and phase synchronization error estimation method based on space-time spectral entropy.The distance-angle space-time two-dimensional spectrum is first constructed by establishing a space-time covariance matrix with time and phase synchronization faults.Then,based on entropy theory,the correspondence between synchronization errors and space-time spectral shape uncertainty is established.The time and phase synchronization errors are estimated by optimizing the space-time spectral entropy to minimize its value.Simulation experiments validate the accuracy of the proposed method,particularly exhibiting good estimation performance under low signal-to-noise ratio.

In the field of synthetic aperture radar (SAR) target recognition, leveraging computer-generated labeled simulated SAR data to aid in the recognition of unlabeled real SAR data has garnered significant attention. However, the domain shift between the simulated and real domain contravenes the assumption of independent and identically distributed in deep learning (DL). Moreover, the categories of real SAR data may not align precisely with those of the simulated SAR data, and the prior knowledge of the label shift typically remains unavailable. To align the common category samples and identify target-private unknown category samples in the presence of both domain shift and potential label shift, we introduce a two-stage universal domain adaptation method for simulation-assisted SAR target recognition based on adversarial uncertainty and neighbor relation (AUNR). The proposed AUNR introduces Dirichlet distribution-based evidential DL, which not only performs classification tasks but also characterizes decision uncertainty, enabling the model to express the concept of "Unknow." In the first stage, alongside supervised learning, we leverage data augmentation-based contrastive learning to achieve robust feature representation. In the second stage, adversarial learning based on model and data uncertainty is employed to separate common and unknown class samples, and contrastive learning based on neighbor relation aligns samples in two domains according to their geometric relationships. To the best of our knowledge, this is the first study on UniDA for SAR target recognition. Experimental results demonstrate that our method outperforms previous State-of-the-Art methods in various label shift scenarios, which indicates the effectiveness of the proposed method.

Distributed array radar (DAR) achieves large-aperture performance by combining small subarrays at different locations, which reducing system burden and manufacturing complexity while meeting low-cost and highresolution requirements in modern sensing. This paper proposes a 2-dimensional (2D) subarray optimization method for regular DARs with identical subarrays, aiming to minimize beamwidth (BW) and maximum sidelobe level (MSLL) under physical layout constraints. A directional expanded beam pattern (DiEBP) is introduced to reformulate non-analytic optimization objectives into a differentiable form, which enables gradient-descent updates within an alternating direction method of multipliers (ADMM) framework for this non-convex problem, with exponential smoothing and Monte Carlo tree search (MCTS) used for stabilization and initialization. Numerical experiments show that, compared with existing algorithms, the proposed method achieves about 10-15% narrower BW and 2 dB lower MSLL on average, along with a reduced Cramer-Rao Bound (CRB). Its effectiveness is further validated through DOA estimation and near-field imaging experiments.

This letter presents an efficient algorithm for designing Doppler-tolerant radar waveforms with superior computational efficiency. The proposed method jointly minimizes the peak sidelobe level (PSL) and mainlobe loss level (MLL) under Doppler shifts by introducing a dynamic weighting strategy that adaptively balances these competing objectives. To address the resulting non-convex optimization problem, log-sumexp smoothing combined with automatic differentiation is employed, enabling efficient gradient-based optimization. Experimental results demonstrate that the proposed algorithm achieves 1 dB lower PSL than the state-of-the-art maximum block improvement (MBI) method with comparable MLL, while being up to 8 times faster computationally. Moreover, the algorithm scales efficiently to longer code lengths, making it particularly suitable for practical radar applications requiring adaptive waveform design.

With the ongoing miniaturization of smart devices, fine-grained hand gesture recognition using millimeter-wave radar has attracted increasing attention, yet practical deployment remains challenging in continuous-gesture segmentation, robust feature extraction, and reliable classification. This paper presents an end-to-end fine-grained gesture recognition framework based on frequency modulated continuous wave(FMCW) millimeter-wave radar, including gesture design, data acquisition, feature construction, and neural network-based classification. Ten gesture types are recorded (eight valid gestures and two return-to-neutral gestures); for classification, the two return-to-neutral gesture types are merged into a single invalid class, yielding a nine-class task. A sliding-window segmentation method is developed using short-time Fourier transformation(STFT)-based Doppler-time representations, and a dataset of 4050 labeled samples is collected. Multiple signal classification(MUSIC)-based super-resolution estimation is adopted to construct range-time and angle-time representations, and instance-wise normalization is applied to Doppler and range features to mitigate inter-individual variability without test leakage. For recognition, a variable-channel deep residual shrinkage network (DRSN) is employed to improve robustness to noise, supporting single-, dual-, and triple-channel feature inputs. Results under both subject-dependent evaluation with repeated random splits and subject-independent leave one subject out(LOSO) cross-validation show that DRSN architecture consistently outperforms the RefineNet-based baseline, and the triple-channel configuration achieves the best performance (98.88% accuracy). Overall, the variable-channel design enables flexible feature selection to meet diverse application requirements.

Distributed aperture radar (DAR) emulates an equivalent large-aperture performance by synthesizing multiple subarrays placed at different locations, offering a cost-effective solution for high-resolution radar systems. However, subarray spacing leads to spatially sparse sampling, resulting in grating lobes that degrade subsequent image interpretation. In this study, a near-field grating lobe suppression method based on subarray migration and spatial multiapodization (MA) is proposed for nonuniform 2-D sparse DAR imaging. In our method, an optimized subarray response with sharp main lobe and low sidelobe level is achieved via parallel subarray migration and MA processing, which is further utilized to mitigate the prominent grating lobes arising from sparse intersubarray placement. To address the spatial variation of array radiation characteristics under near-field effects, the proposed method is integrated into the back-projection algorithm (BPA) framework using an adaptive weighting strategy. Numerical experiments on extended targets demonstrate the superiority of the proposed method in grating lobe suppression, enabling high-fidelity, ambiguity-free near-field imaging with 2-D sparse DAR systems.

Deep-learning-based few-shot synthetic aperture radar (SAR) ship detection has demonstrated considerable potential in scenarios with limited annotated samples and dynamically emerging ship categories, closely matching the practical requirements of maritime surveillance and intelligent SAR image interpretation. However, existing methods often overlook challenging negative proposals and the incomplete annotation problem inherent in few-shot learning. In complex offshore and inshore scenes, negative proposals contain either difficult background regions caused by sea clutter, port facilities, and strong scattering interference, or unlabeled ship targets resulting from missing annotations. Existing methods struggle to distinguish between these two types of proposals. Ignoring challenging negatives prevents the detector from learning precise decision boundaries between ships and complex backgrounds, whereas treating unlabeled ships as background introduces erroneous gradients during backpropagation and degrades detection performance. To address these issues, we introduce uncertainty as a measure of proposal reliability and propose two complementary components: uncertainty-guided proposal separation (UGPS) and uncertainty-aware discriminative gradient refocusing (UADGR). UGPS jointly exploits proposal uncertainty and intersection-over-union (IoU) to separate challenging negatives and confusing negatives from the negative proposal set, thereby preserving informative hard backgrounds while identifying potential unlabeled ships. Subsequently, UADGR combines proposal uncertainty with feature dissimilarity to a background prototype to adaptively regulate their training gradients. Specifically, higher weights are assigned to challenging negatives to improve discrimination between ships and complex background interference, whereas lower weights are assigned to confusing negatives to suppress erroneous supervision introduced by missing ship annotations. Extensive experiments on SRSDD-v1.0 demonstrate consistent improvements over existing few-shot detection approaches across different data splits and shot settings, while additional results on SAR-AIRcraft-1.0 further confirm the generalization of the proposed method.

Deep learning-based Synthetic Aperture Radar (SAR) ship detection has achieved remarkable progress in recent years. However, the high cost of annotating SAR images severely limits the practical deployment of fully-supervised detection methods. Pseudo-label-based semi-supervised learning is a mainstream approach for alleviating the reliance on large-scale annotations, and it has achieved superior performance in general object detection. Nevertheless, when directly transferred to SAR ship detection, these methods face two critical challenges due to the unique imaging characteristics of SAR data: first, they struggle to balance pseudo-label precision and recall, as ship diversity and speckle noise make confidence scores unreliable; second, they cannot effectively filter out low-quality pseudo-labels during student training, which limits further performance improvement. To address the issues above, this paper proposes a novel semi-supervised object detection framework, named SPG-IAD, specifically for SAR ship detection. The framework consists of two core components: the Scattering-Point-Guided Dual-Criterion Coarse Filtering (SPG-DC) strategy and the Intersection over Union (IoU)-Aware Teacher-Student Dynamic Fine Selection (IA-TSD) strategy. Specifically, SPG-DC combines classification scores with the physical prior of ship scattering points to collaboratively filter detection outputs, effectively recalling low-confidence yet well-localized candidate predictions. IA-TSD introduces an IoU prediction branch to quantify localization quality and compares teacher-student localization quality using a scale-adaptive threshold. This strategy enables dynamic pseudo-label selection and suppresses the misleading effects of low-quality pseudo-labels. Experiments on the HRSID and SSDD datasets demonstrate that under the semi-supervised setting with 10% labeled data, the proposed method achieves a significant improvement in Average Precision (AP) over the fully-supervised baseline, and outperforms existing state-of-the-art methods.

In recent years, lossy compression algorithms such as H.264/AVC, H.265/HEVC, and H.266/VVC have been proposed and widely applied in image and video encoding. However, these compression algorithms inevitably introduce various complex types of compression artifacts, which severely degrade image quality. Although existing methods have attempted to remove artifacts through filter design or probabilistic prior modeling, they are often effective only for specific types of artifacts, lacking generalization and adaptability. To address this, we propose a novel image compression artifacts removal model: ARMoE, which combines multiple frequency domain transformations with the Mixture of Experts (MoE). Considering the frequency distribution and energy distribution differences of images, we introduce various frequency domain transformations as expert branches and use the Sparse Activation Strategy to adaptively select the optimal frequency domain expert to suppress compression artifacts, achieving an efficient artifacts removal method. Furthermore, we reencode and decode multiple original uncompressed high-quality datasets, including DF2K and Kodak24, using the VTM-20.0 codec under the H.266/VVC standard, constructing a more challenging artifacts dataset. We conducted rigorous comparative experiments with current state-of-the-art image restoration methods and the results demonstrate that ARMoE exhibits outstanding image restoration capability.

Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for 3D human pose estimation in ubiquitous Internet of Things (IoT) applications, owing to its privacy-preserving nature and robustness under challenging illumination conditions. However, accurate skeletal reconstruction remains difficult due to the inherent sparsity, non-uniform distribution, and instability of radar point clouds. To address these challenges, this paper proposes MS-STPoseNet, a unified multi-scale spatio-temporal learning framework for robust mmWavebased human pose estimation. For spatial representation, MS-STPoseNet employs a hierarchical multi-scale spatial encoder built upon PointNet++, which leverages multi-scale grouping to effectively capture body structures across different spatial resolutions, from fine-grained joint regions to limb- and torso-level configurations, under irregular radar observations. For temporal modeling, a multi-branch Temporal Convolutional Network (TCN) with different dilation rates is introduced to model multi-rate motion dynamics, enabling effective representation of both rapid limb movements and smoother torso motions. An attention mechanism is further incorporated to enhance informative temporal features while suppressing noise. The entire framework is trained end-to-end to estimate per-frame 3D poses by exploiting short-term temporal context, thereby improving robustness under noisy sensing conditions. Extensive experiments conducted on a self-collected dataset and two public benchmarks demonstrate that MS-STPoseNet consistently outperforms state-of-the-art methods in terms of pose estimation accuracy and cross-subject generalization, achieving an MPJPE of 3.08 cm on the self-collected dataset. In addition, the proposed framework exhibits favorable computational efficiency and a compact model size, highlighting its potential applicability to practical IoT sensing systems.

Quasi-coherent radar imaging systems have gained attention for their low hardware complexity, design flexibility, and potential aperture scalability. However, the use of independent phase-locked loop (PLL) to generate local oscillator (LO) signals for each subarray introduces intersubarray phase deviations, which limit the effectiveness of multistatic range migration algorithm (RMA) reliant on intersubarray signal coherence. To address this issue, we propose an imaging algorithm based on multilevel fast Fourier transform (FFT) decomposition that relies solely on intrasubarray data, and provide two specific implementation forms. The one divides the entire array into subarrays, applies zero padding and FFT to align their wavenumber domains for summation, and finally reconstructs images through dimension reduction and inverse fast Fourier transform (IFFT). To improve generality, an alternative implementation uses nonuniform fast Fourier transform (NUFFT) for domain alignment, extending the algorithm to MIMO arrays with arbitrary topologies. Simulations and experiments are carried out for verification, and the proposed algorithm is compared with the back projection algorithm (BPA) and monostatic RMA based on range compensation. The results demonstrate the effectiveness of the proposed algorithm for imaging and its superiority in imaging quality and computational efficiency.

Rotorcraft unmanned aerial vehicle (UAV) recognition is an crucial task in radar-based low-altitude UAV surveillance. Micro-Doppler signatures offer promising capabilities for UAV recognition. However, the diversity and unpredictability of other low-altitude targets pose significant challenges to conventional closed-set recognition methods. To address this issue, we propose an open-set recognition approach for identifying rotorcraft UAVs and other targets. First, a boundary point identification method based on the minimum description length (MDL) code length is introduced. Then, based on the MDL-induced code length, it is theoretically demonstrated that the extreme boundary samples conform to a generalized extreme value distribution, which enables the establishment of statistically sound decision thresholds. Finally, experiments conducted on real-world radar datasets demonstrate the superiority of our work over existing methods.

Unmanned aerial vehicle (UAV) classification using radar micro-Doppler signatures remains challenging due to the diversity, variability, and heterogeneity of the observed features. Most existing feature selection methods adopt a global strategy, which overlooks sample-specific differences arising from diverse UAV categories, flight dynamics, and observation conditions. To address this limitation, we propose an instance-wise feature selection framework based on the Information Bottleneck (IB)principle. The method jointly optimizes a differentiable feature selector and a classifier via variational inference and Gumbel–Softmax reparameterization, enabling adaptive identification of discriminative features for each sample. Experimental evaluations on real radar data validate the effectiveness and interpretability of the proposed approach.

Instance segmentation of ships in synthetic aperture radar (SAR) imagery is critical for applications such as maritime monitoring, environmental analysis, and national security. SAR ship images present challenges including scale variation, object density, and fuzzy target boundary, which are often overlooked in existing methods, leading to suboptimal performance. In this work, we propose O2Former, a tailored instance segmentation framework that extends Mask2Former by fully leveraging the structural characteristics of SAR imagery. We introduce two key components. The first is the Optimized Query Generator (OQG). It enables multiscale feature interaction by jointly encoding shallow positional cues and high-level semantic information. This improves query quality and convergence efficiency. The second component is the Orientation-Aware Embedding Module. It enhances directional sensitivity through direction-aware convolution and polar-coordinate encoding. This effectively addresses the challenge of uneven target orientations in SAR scenes. Together, these modules facilitate precise feature alignment from backbone to decoder and strengthen the model's capacity to capture fine-grained structural details. Extensive experiments demonstrate that O2Former outperforms state-of-the-art instance segmentation baselines, validating its effectiveness and generalization on SAR ship datasets.

Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for 3-D human pose estimation in ubiquitous Internet of Things (IoT) applications, owing to its privacy-preserving nature and robustness under challenging illumination conditions. However, accurate skeletal reconstruction remains difficult due to the inherent sparsity, nonuniform distribution, and instability of radar point clouds. To address these challenges, this article proposes MS-STPoseNet, a unified multiscale spatio-temporal learning framework for robust mmWave-based human pose estimation. For spatial representation, MS-STPoseNet employs a hierarchical multiscale spatial encoder built upon PointNet++, which leverages multiscale grouping (MSG) to effectively capture body structures across different spatial resolutions, from fine-grained joint regions to limb- and torso-level configurations, under irregular radar observations. For temporal modeling, a multibranch temporal convolutional network (TCN) with different dilation rates is introduced to model multirate motion dynamics, enabling effective representation of both rapid limb movements and smoother torso motions. An attention mechanism is further incorporated to enhance informative temporal features while suppressing noise. The entire framework is trained end-to-end to estimate per-frame 3-D poses by exploiting short-term temporal context, thereby improving robustness under noisy sensing conditions. Extensive experiments conducted on a self-collected dataset and two public benchmarks demonstrate that MS-STPoseNet consistently outperforms state-of-the-art methods in terms of pose estimation accuracy and cross-subject generalization, achieving an MPJPE of 3.08 cm on the self-collected dataset. In addition, the proposed framework exhibits favorable computational efficiency and a compact model size, highlighting its potential applicability to practical IoT sensing systems.

In practical observations, multiple micro-motion targets with different translational characteristics may be detected within the same radar beam. The resulting mixed modulation causes overlap among the echo signals, making translational compensation, micro-Doppler (m-D) feature extraction, and multi-target signal separation challenging. This paper proposes a multi-target translational compensation and m-D feature extraction algorithm framework based on the ambiguity domain and dual-domain (i.e., signal domain and image domain) to handle mixed signals, achieving motion parameter extraction and signal separation. Firstly, a narrowband signal model for multiple targets with micro-motion is established. Secondly, HMPPS-HAF, a translational parameter estimation algorithm is proposed based on the high-order ambiguity function (HAF) for hybrid modulated polynomial phase signals (HMPPS). HMPPS-HAF identifies the number of targets in the ambiguity domain, followed by accurate estimation of each target’s m-D period, jerk, and acceleration. Then, DD-IDBO, an m-D feature extraction algorithm based on dual-domain (DD) processing and the improved dung beetle optimizer (IDBO), is proposed to estimate translational velocity, m-D amplitude, and m-D initial phase. Specifically, IDBO performs signal-domain spectral-peak searching for parameter estimation, while image-domain masks suppress cross-interference among scattering center signals. Finally, the extended intrinsic chirp component decomposition (EICCD) algorithm is applied to separate each target’s signal. Experiments on simulated data and semi-measured data both validate the effectiveness of the proposed framework.

Ground vehicles pose significant challenges for low-altitude surveillance radar to classify low-flying multirotor Uncrewed aerial vehicles (UAVs). Radar micro-Doppler signatures could provide a variety of kinematic and structural features to potentially distinguish between them. However, the integration usage of such diverse features always exerts a strong impact on the classification performance, suffering redundancy and sensitivity to outliers. To address this issue, we propose a micro-Doppler feature selection and classification framework to distinguish between low-altitude multirotor UAVs and ground vehicles. A sparse learning model with joint l(1)-norm regularization and outlier compensation is employed to simultaneously select discriminative features and suppress outlier samples. In addition, a kernel density-based thresholding strategy is introduced to optimize classification under class imbalance by modeling the prediction score distribution. Finally, experimental results on real radar dataset demonstrate the proposed framework outperforms conventional feature selection ones with stronger outlier robustness, better class imbalance adaptability, and higher classification accuracy.

This letter presents an efficient algorithm for designing binary phase-coded sequences with low peak sidelobe level (PSL) for multiple-input multiple-output (MIMO) radar applications. The algorithm features a log-sum-exp function (LSEF)-based fitness function and a vectorized recursive computation method, substantially reducing computational complexity compared to conventional approaches. A two-stage search strategy effectively balances between local exploitation and global exploration. Numerical results demonstrate that the proposed algorithm achieves comparable PSL performance to state-of-the-art algorithms with enhanced computational efficiency in monostatic cases, while exhibiting superior PSL performance in MIMO scenarios.