Search Results (251)

Infrared small target (IRST) detection remains a challenging task due to extremely small target sizes, low signal-to-noise ratios (SNR), and complex background clutter. Existing methods often fail to balance reliable detection with low false alarm rates due to limited spatial–temporal modeling. To address this, we propose a multi-frame network that synergistically integrates spatial curvature and temporal motion consistency. Specifically, in the single-frame stage, a Gaussian Curvature Attention (GCA) module is introduced to exploit spatial curvature and geometric saliency, enhancing the discriminability of weak targets. In the multi-frame stage, a Motion-Aware Encoding Block (MAEB) utilizes MotionPool3D to capture temporal motion consistency and extract salient motion regions, while a Temporal Consistency Enhancement Module (TCEM) further refines cross-frame features to effectively suppress noise. Extensive experiments demonstrate that the proposed method achieves advanced overall performance. In particular, under low-SNR conditions, the method improves the detection rate by 0.29% while maintaining a low false alarm rate, providing an effective solution for the stable detection of weak and small targets. Full article

Direction of arrival (DOA) estimation is a fundamental problem in array signal processing, with extensive applications in radar, communications, sonar, and other fields. Traditional DOA estimation methods, such as MUSIC and ESPRIT, rely on eigenvalue decomposition or spectral peak search, which suffer from high computational complexity and performance degradation under conditions of low signal-to-noise ratio (SNR), coherent signals, and array imperfections. Cylindrical arrays offer unique advantages for omnidirectional sensing due to their circular structure and three-dimensional coverage capability; however, their nonlinear array manifold increases the difficulty of estimation. This paper proposes a circular-attention residual network (CA-ResNet) for DOA estimation using uniform cylindrical arrays. The proposed approach achieves high accuracy and robust angle estimation through phase difference feature extraction, a multi-scale residual network, an attention mechanism, and a joint output module. Simulation results demonstrate that the proposed CA-ResNet method delivers superior performance under challenging scenarios, including low SNR (−10 dB), a small number of snapshots (L = 5), and multiple sources (1 to 4 signal sources). The corresponding root mean square errors (RMSE) are 0.21°, 0.45°, and below 1.5°, respectively, significantly outperforming traditional methods like MUSIC and ESPRIT, as well as existing deep learning models (e.g., ResNet, CNN, MLP). Furthermore, the algorithm exhibits low computational complexity and a small parameter size, highlighting its strong potential for practical engineering applications and robustness. Full article

Direction-of-arrival (DOA) estimation is fundamental in array signal processing, yet classical algorithms suffer from significant performance degradation under low signal-to-noise ratio (SNR) conditions and require computationally intensive eigenvalue decomposition. This study presents a systematic comparative analysis of two backbone networks, a convolutional neural network (CNN) and long short-term memory (LSTM) for DOA estimation, addressing two critical research gaps: the lack of a mechanistic understanding of architecture-dependent performance under varying conditions and insufficient validation using real measured data. Both networks are trained using cross-spectral density matrices (CSDMs) from simulated uniform linear array (ULA) signals. Under baseline conditions (1° classification interval), both CNN and LSTM methods reach an accuracy (ACC) above 98%, in which the error is ±1° for CNN and ±2° for LSTM, only existing in the end-fire direction. Key findings reveal that LSTM maintains above 90% accuracy down to −20 dB SNR, demonstrating superior noise robustness, whereas CNN exhibits better angular resolution. Four performance boundaries are identified: optimal performance is achieved at half-wavelength element spacing; SNR crossover occurs at −20 dB below which accuracy drops sharply; the snapshot threshold of 32 marks the transition from snapshot-deficient to snapshot-sufficient conditions; the array size of 8 is the turning point for the performance variation rate. Comparative analysis against traditional methods demonstrates that deep learning approaches achieve superior resolution ability, batch processing efficiency, and noise robustness. Critically, models trained exclusively on single-target simulated data successfully generalize to multi-target experimental data from the Shallow Water Array Performance (SWAP) program, recovering primary target trajectories without domain adaptation. These results provide concrete engineering guidelines for architecture selection and validate the sim-to-real generalization capability of CSDM-based deep learning approaches in underwater acoustic environments. Full article

Fluorescence microscopy is a cornerstone technique in biological research, offering unparalleled insights into cellular and subcellular structures. However, inherent limitations such as photobleaching, phototoxicity, and low signal-to-noise ratios (SNR) often hinder its full potential. This paper introduces DeepFluoNet, a novel deep learning framework designed to significantly enhance the analysis of fluorescence microscopy data. DeepFluoNet leverages a sophisticated convolutional neural network architecture, meticulously optimized for denoising, segmentation, and classification tasks in fluorescence images. DeepFluoNet achieved a 98.5% accuracy in cell nucleus classification, a 95.2% F1-score in mitochondrial segmentation, and a 25% improvement in SNR for low-light images, surpassing state-of-the-art methods by an average of 7.3% in overall performance metrics. Furthermore, the inference time of DeepFluoNet is optimized to be 0.05 s per image, making it suitable for high-throughput analysis. This research bridges critical gaps in existing methodologies by providing a robust, efficient, and highly accurate solution for fluorescence microscopy data analysis, paving the way for more precise biological discoveries. Full article

This paper systematically reviews the key spectral information extraction methods in Brillouin microscopy, aiming to address the core challenge of accurately extracting material mechanical parameters from raw spectra. Based on technical principles, the methods are categorized into three types for elaboration: Spontaneous Brillouin Scattering (SpBS) is characterized by low signal-to-noise ratio (SNR) and strong background interference, and its processing relies on high-precision spectrometers and complex preprocessing procedures to mitigate noise and background effects; Stimulated Brillouin Scattering (SBS) operates on the mechanism of optical gain/loss, which achieves significantly improved data SNR and thereby enables more robust and accurate Lorentzian fitting for spectral analysis; Impulsive Stimulated Brillouin Scattering (ISBS) retrieves the frequency spectrum by inverting time-domain oscillating signals, and the core of its processing lies in super-resolution algorithms such as Fast Fourier Transform (FFT) and the Matrix Pencil Method, which are tailored to match its high-speed data acquisition capability. The paper further compares the advantages and disadvantages of various methods, outlines future development trends of intelligent processing technologies such as deep learning and multi-modal data fusion, and provides a clear guide for selecting the optimal data processing strategy in different application scenarios. Full article

Automatic modulation classification (AMC) under low signal-to-noise ratio (SNR) and complex channel conditions remains a significant challenge due to the trade-off between robustness and efficiency. This study proposes a lightweight temporal convolutional network (TCN) and Mamba fusion architecture designed to enhance modulation recognition performance. In the modulation signal denoising stage, a non-local adaptive thresholding denoising module (NATM) is introduced to explicitly improve the effective signal-to-noise ratio. In the parallel feature extraction stage, TCN captures local symbol-level dependencies, while Mamba models long-range temporal relationships. In the output stage, their outputs are integrated through additive layer-wise fusion, which prevents parameter explosion. Experiments were conducted on the RadioML 2016.10A, 2016.10B, and 2018.01A datasets with leakage-controlled partitioning strategies including GroupKFold and Leave-One-SNR-Out cross-validation. The proposed method achieves up to a 3.8 dB gain in the required signal-to-noise ratio at 90 percent accuracy compared with state-of-the-art baselines, while maintaining a substantially lower parameter count and reduced inference latency. The denoising module provides clear robustness improvements under low signal-to-noise ratio conditions, particularly below −8 dB. The results show that the proposed network strikes a balance between accuracy and efficiency, highlighting its application potential in real-time wireless receivers under resource constraints. Full article

Recent advances in deep learning have intensified the need for robust low-light image processing in critical applications like autonomous driving, where single-photon cameras (SPCs) offer high photon sensitivity but produce noisy outputs requiring specialized enhancement. This work addresses this challenge through a unified framework integrating three key components: an SNR-guided adaptive enhancement framework that dynamically processes regions with varying noise levels using spatial-adaptive operations and intelligent feature fusion; a specialized self-attention mechanism optimized for low-light conditions; and a conditional autoregressive generation approach applied to robust depth estimation from enhanced SPC images. Our comprehensive evaluation across multiple datasets demonstrates improved performance over state-of-the-art methods, achieving a PSNR of 24.61 dB on the LOL-v1 dataset and effectively recovering fine-grained textures in depth estimation, particularly in real-world SPC applications, while maintaining computational efficiency. The integrated solution effectively bridges the gap between single-photon sensing and practical computer vision tasks, facilitating more reliable operation in photon-starved environments through its novel combination of adaptive noise processing, attention-based feature enhancement, and generative depth reconstruction. Full article

Location-based services (LBSs) and positioning systems have spread worldwide due to the emergence of Internet of Things (IoT) and other application domains that require real-time estimation of the position of a person, tag, or asset in general in order to provide users with services and apps with added value. Whereas Global Navigation Satellite Systems (GNSSs) are well-established solutions outdoors, positioning is still an open challenge indoors, where different sensory technologies may be considered for that purpose, such as radio frequency, infrared, or ultrasounds, among others. With regard to ultrasonic systems, previous works have already developed indoor positioning systems capable of achieving accuracies in the range of centimeters but limited to a few square meters of coverage and severely affected by the Doppler effect coming from moving targets, which significantly degrades the overall positioning performance. Furthermore, the actual bandwidth available in commercial transducers often constrains the ultrasonic transmission, thus reducing the position accuracy as well. In this context, this work proposes a novel excitation and processing method for an ultrasonic positioning system, which significantly improves the transmission capabilities between an emitter and a receiver. The proposal employs a superheterodyne approach, enabling simultaneous transmission and reception of signals across multiple channels. It also adapts the bandwidths and central frequencies of the transmitted signals to the specific bandwidth characteristics of available transducers, thus optimizing the system performance. Binary spread spectrum sequences are utilized within a multicarrier modulation framework to ensure robust signal transmission. The ultrasonic signals received are then processed using filter banks and matched filtering techniques to determine the Time Differences of Arrival (TDoA) for every transmission, which are subsequently used to estimate the target position. The proposal has been modeled and successfully validated using a digital twin. Furthermore, experimental tests on the prototype have also been conducted to evaluate the system’s performance in real scenarios, comparing it against classical approaches in terms of ranging distance, signal-to-noise ratio (SNR), or multipath effects. Experimental validation demonstrates that the proposed narrowband scheme reliably operates at distances up to 40 m, compared to the 34 m limit of conventional wideband approaches. Ranging errors remain below 3 cm at 40 m, whereas the wideband scheme exhibits errors exceeding 8 cm. Furthermore, simulation results show that the narrowband scheme maintains stable operation at SNR as low as $-32$ dB, whereas the wideband one only achieves up to $-17$ dB, highlighting the significant performance advantages of the proposed approach in both experimental and simulated scenarios. Full article

The Global Navigation Satellite System (GNSS)/Inertial Measurement Unit (IMU) Loosely Coupled (LC) integration framework has been widely adopted due to its simple structure, but it relies on complete GNSS position and velocity solutions, and the rapid accumulation of IMU errors can easily lead to navigation failure when fewer than four satellites are visible. In this paper, GNSS Doppler observations are fused with IMU attitude information within an LC framework. An inter-satellite differential Doppler model is introduced, and the velocity obtained from the differential Doppler solution is transformed into the navigation frame using the IMU-derived attitude, enabling three-dimensional velocity estimation in the navigation frame even when only two satellites are available. Analysis of real vehicle data collected by the GREAT team at Wuhan University shows that the Signal-to-Noise Ratio (SNR) and the geometric relationship between the Satellite Difference Vector (SDV) and the Receiver Motion Direction (RMD) are the dominant factors affecting velocity accuracy. A multi-factor threshold screening strategy further indicates that when $\mathrm{S}\mathrm{NR}>$ 40 and $\mid \mathrm{SDV}·\mathrm{RMD}\mid >0.2$, the Root Mean Square (RMS) of the velocity error is approximately 0.3 m/s and the data retention rate exceeds 44%, achieving a good balance between accuracy and availability. The results indicate that, while maintaining a simple system structure, the proposed Doppler–IMU fusion method can significantly enhance velocity robustness and positioning continuity within an LC architecture under weak GNSS conditions (when more than two satellites are visible but standalone GNSS positioning is still unavailable), and is suitable for constructing low-cost, highly reliable integrated navigation systems. Full article

Non-contact heart rate estimation technology based on frequency-modulated continuous wave (FMCW) radar has garnered extensive attention in single-target scenarios, yet it remains underexplored in multi-target environments. Accurate discrimination of multiple targets and precise estimation of their heart rates constitute key challenges in the multi-target domain. To address these issues, we propose a novel scheme for multi-target heart rate estimation. First, a high-precision distance-bin selection (HDBS) method is proposed for target localization in the range domain. Next, multiple-input multiple-output (MIMO) array processing is combined with the Root-multiple signal classification (Root-MUSIC) algorithm for angular domain estimation, enabling accurate discrimination of multiple targets. Subsequently, we propose an efficient method for interference suppression and vital sign extraction that cascades variational mode decomposition (VMD), local mean decomposition (LMD), and wavelet thresholding (WT) termed as VLW, which enables high-quality heartbeat signal extraction. Finally, to achieve high-precision and super-resolution heart rate estimation with low computational burden, an improved fast iterative interpolated beamforming (FIIB) algorithm is proposed. Specifically, by leveraging the conjugate symmetry of real-valued signals, the improved FIIB algorithm reduces the execution time by approximately 60% compared to the standard version. In addition, the proposed scheme provides sufficient signal-to-noise ratio (SNR) gain through low-complexity accumulation in both distance and angle estimation. Six experimental scenarios are designed, incorporating densely arranged targets and front-back occlusion, and extensive experiments are conducted. Results show this scheme effectively discriminates multiple targets in all tested scenarios with a mean absolute error (MAE) below 2.6 beats per minute (bpm), demonstrating its viability as a robust multi-target heart rate estimation scheme in various engineering fields. Full article

Terahertz Synthetic Aperture Radar (THz-SAR) is highly sensitive to platform vibrations and trajectory deviations, which introduce severe phase errors and limited resolution. Typically, platform vibrations and trajectory deviations are investigated individually, and vibrations are modeled as a stationary sine term. In this work, a hybrid motion compensation (MOCO) scheme is proposed to address both platform vibrations and trajectory deviations simultaneously, achieving improved imaging quality. The scheme initiates with a parameter self-adaptive quadratic Kalman filter designed to resolve severe phase wrapping. Then, platform vibration is modeled as a non-stationary multi-sine term, whose components are accurately extracted using an improved signal decomposition algorithm enhanced by a dynamic noise adjustment mechanism. Subsequently, the trajectory deviation is parameterized following subaperture division, estimated using a hybrid optimizer that combines particle swarm optimization and gradient descent. Additionally, a composite modulated waveform application ensures low sidelobes and a low probability of intercept (LPI). Extensive simulations on point targets and complex scenes under various signal-to-noise-ratio (SNR) conditions are applied for SAR image reconstruction, demonstrating robust suppression of motion errors. Under identical simulated error conditions, the proposed method achieves an azimuth resolution of 4.28 cm, which demonstrates superior performance compared to the reported MOCO techniques. Full article

This article addresses anomaly detection in multichannel spatiotemporal data under strict low-false-alarm constraints (e.g., 1% False Positive Rate, FPR), a requirement essential for safety-critical applications such as signal interference monitoring in sensor networks. We introduce a lightweight, interpretable pipeline that deliberately avoids deep learning dependencies, implemented solely in NumPy and scikit-learn. The core innovation lies in fusing three complementary anomaly signals in an ensemble: (i) Principal Component Analysis (PCA) Reconstruction Error (MSE) to capture global structure deviations, (ii) Local Outlier Factor (LOF) on residual maps to detect local rarity, and (iii) Monte Carlo Variance as a measure of epistemic uncertainty in model predictions. These signals are combined via learned logistic regression (F*) and specialized Neyman–Pearson optimized fusion (F** and F***) to rigorously enforce bounded false alarms. Evaluated on synthetic benchmarks that simulate realistic anomalies and extensive SNR shifts (±12 dB), the fusion approach demonstrates exceptional robustness. While the best single baseline (MC-variance) achieves a True Positive Rate (TPR) of ≈0.60 at 1% FPR on the 0 dB hold-out, the fusion significantly raises this to ≈0.74 (F**), avoiding the performance collapse of baselines under degraded SNR (maintaining ≈ 0.62 TPR at −12 dB). This deployable solution provides a transparent, edge-ready anomaly detection capability that is highly effective at operating points critical for reliable monitoring in dynamic environments. Full article

Elevation Digital Beamforming (DBF) technology is key to achieving high-resolution wide-swath (HRWS) imaging in spaceborne Synthetic Aperture Radar (SAR) systems. However, multi-channel DBF-SAR systems face a prominent conflict between the need for real-time channel error calibration and the constraints of limited on-board hardware resources. To address this bottleneck, this paper proposes a real-time channel error calibration method based on Fast Fourier Transform (FFT) pulse compression and introduces a “calibration-operation” dual-mode control with a parameter-persistence architecture. This scheme decouples high-complexity computations by confining them to the system initialization phase, enabling on-board, real-time, closed-loop compensation for multi-channel signals with low resource overhead. Test results from a high-performance Field-Programmable Gate Array (FPGA) platform demonstrate that the system achieves high-precision compensation for inter-channel amplitude, phase, and time-delay errors. In the 4-channel system validation, the DBF synthesized signal-to-noise ratio (SNR) improved by 5.93 dB, reaching a final SNR of 44.26 dB. This performance approaches the theoretical ideal gain and significantly enhances the coherent integration gain of multi-channel signals. This research fully validates the feasibility of on-board, real-time calibration with low resource consumption, providing key technical support for the engineering robustness and efficient data processing of new-generation SAR systems. Full article

The exponential growth of candidate data from large-scale radio pulsar surveys has created a pressing need for efficient and accurate classification methods. This paper presents a novel hybrid pulsar candidate recognition algorithm that integrates diagnostic plot images and structured numerical features using a multi-scale DenseNet framework. The proposed model combines convolutional neural networks (CNNs) for extracting spatial patterns from pulsar diagnostic plots and feedforward neural networks (FNNs) for processing scalar features such as SNR, DM, and pulse width. By fusing these multimodal representations, the model achieves superior classification performance, particularly in class-imbalanced settings standard to pulsar survey data. Evaluated on a synthesized dataset constructed from FAST and HTRU survey characteristics, the model demonstrates robust performance, achieving an F1-score of 0.904 and AUC-ROC of 0.978. Extensive ablation and cross-validation analyses confirm the contribution of each data modality and the model’s generalizability. Furthermore, the system maintains low inference latency (4.2 ms per candidate) and a compact architecture (~2.3 million parameters), indicating potential for real-time deployment once validated on real observational datasets. The proposed approach offers a scalable and interpretable multimodal framework for automated pulsar classification and provides a foundation for future validation and potential integration into observatories such as FAST and the Square Kilometre Array (SKA). Full article

Electroencephalography (EEG)-based brain–computer interface (BCI) mimics the brain’s intrinsic information-processing mechanisms by translating neural oscillations into actionable commands. In motor imagery (MI) BCI, imagined movements evoke characteristic patterns over the sensorimotor cortex, forming a biomimetic channel through which internal motor intentions are decoded. However, this biomimetic interaction is highly vulnerable to signal degradation, particularly in mobile or low-resource environments where low sampling frequencies obscure these MI-related oscillations. To address this limitation, we propose a robust MI classification framework that integrates spatial, spectral, and temporal dynamics through a filter bank common spatial pattern with time segmentation (FBCSP-TS). This framework classifies motor imagery tasks into four classes (left hand, right hand, foot, and tongue), segments EEG signals into overlapping time domains, and extracts frequency-specific spatial features across multiple subbands. Segment-level predictions are combined via soft voting, reflecting the brain’s distributed integration of information and enhancing resilience to transient noise and localized artifacts. Experiments performed on BCI Competition IV datasets 2a (250 Hz) and 1 (100 Hz) demonstrate that FBCSP-TS outperforms CSP and FBCSP. A paired t-test confirms that accuracy at 110 Hz is not significantly different from that at 250 Hz (p < 0.05), supporting the robustness of the proposed framework. Optimal temporal parameters (window length = 3.5 s, moving length = 0.5 s) further stabilize transient-signal capture and improve SNR. External validation yielded a mean accuracy of 0.809 ± 0.092 and Cohen’s kappa of 0.619 ± 0.184, confirming strong generalizability. By preserving MI-relevant neural patterns under degraded conditions, this framework advances practical, biomimetic BCI suitable for wearable and real-world deployment. Full article