Search Results (2,663)

Unmanned Aerial Vehicle (UAV)-based small object detection is a challenging computer vision task. It is constrained by two primary factors: UAV platforms have limited onboard computational resources, and high-altitude objects often have weak features that are easily overwhelmed by complex backgrounds. To address these challenges, we propose LUIM-YOLO. First, a Lightweight Multi-Scale Feature Enhancement (LMSFE) module integrates parallel multi-scale convolutions with attention to strengthen small and low-contrast object feature extraction. Second, an Adaptive Multi-Scale Bottleneck (AMSB) module enhances key semantic features of small objects and spatial correlation of medium-scale objects. Third, an Enhanced Cross-layer Compensation Feature Pyramid Network (ECC-FPN) constructs cross-level interaction pathways to improve small object position and scale perception. Experimental results on VisDrone2019 show that compared with YOLOv8n, LUIM-YOLO reduces parameters by 57% and improves mAP@50 by 12.9%. Additional full-validation-set PyTorch inference tests on NVIDIA Jetson Orin show that LUIM-YOLO achieves 88.19 ms/image in FP32, indicating a parameter-efficient accuracy-oriented design with edge deployment potential. Full article

Accurate and robust localization is essential for intelligent vessels operating in complex marine and port environments. However, single-sensor localization is often affected by limited observation range, environmental occlusion, local interference, and sensor degradation. Although multi-sensor fusion can improve localization reliability, unknown cross-correlated measurement noise arising from shared disturbances, time synchronization errors, communication delays, and inconsistent fusion rates may degrade traditional information-filter-based fusion methods. To address this problem, this paper proposes an Adaptive Correlation Information Filter Network (ACIFNet) for multi-sensor fusion localization of intelligent vessels. ACIFNet preserves the recursive structure of the extended information filter and uses a Transformer-based network to learn adaptive information-domain fusion weights, thereby compensating for unknown inter-sensor correlations without explicitly estimating the full correlation covariance matrix. Experiments on constant-velocity, coordinated-turn (CV), and three-degree-of-freedom vessel motion models, together with a real-world restricted-waterway dataset, demonstrate that ACIFNet achieves higher localization accuracy and stability than Edge Incorporative Fusion (EIF)-inexact fusion, measurement fusion, and KalmanNet. In the CV and three-degree-of-freedom experiments, ACIFNet reduces the mean RMSE by 48.7%, 23.2%, and 26.1%, respectively, compared with KalmanNet. On the real-world dataset, ACIFNet achieves a mean position error of 9.90 m, an RMSE of 11.24 m, and a cross-track error of 8.72 m. These results show that ACIFNet effectively combines the interpretability of information filtering with the adaptive representation capability of neural networks for robust multi-sensor fusion localization under unknown cross-correlated measurement noises. Full article

Detecting small targets in Unmanned Aerial Vehicle (UAV) imagery is challenging due to low pixel coverage, complex backgrounds, and information loss during downsampling. Existing detectors lack explicit mechanisms for enhancing weak target signals. We propose GHF-DETR, a Transformer-based detector featuring three collaboratively designed modules. First, a Heterogeneous Multi-Path Convolutional Network (HMC) backbone uses partial convolution and gated linear units to reduce computational redundancy while maintaining discrimination of small-object features. Second, a Dynamic Multi-Scale Focusing (DMSF) module integrates learned offset alignment with multi-kernel depthwise convolutions for cross-scale feature fusion. Third, a High-Frequency Selective Preservation (HSP) downsampling module combines space-to-depth convolution with 2D Discrete Wavelet Transform (DWT) to compensate for information loss in both spatial and frequency domains. On VisDrone2019, GHF-DETR achieves 33.1% mAP@0.5 and 18.6% mAP@0.5:0.95 with 15.4 GFLOPs and 7.59 M parameters, improving over the DFINE-n baseline by 5.4% and 3.1%, respectively, with AP_S reaching 10.1%. Generalization is validated on NWPU VHR-10. These results demonstrate that GHF-DETR achieves a favorable accuracy–efficiency balance for efficient UAV small-object detection. Full article

With the rapid development of networked cyber-physical systems, the coordinated control of heterogeneous multi-agent systems has attracted increasing attention in applications such as autonomous vehicles, robotic arms, and distributed sensor networks. This paper investigates the leader-following cluster consensus problem for heterogeneous multi-agent systems over weighted cooperative–competitive networks with matched disturbances generated by linear exosystems. Unlike purely cooperative or binary signed networks, the considered network allows interaction weights to take arbitrary positive or negative values, thereby describing both the type and intensity of cooperative or competitive interactions. To handle heterogeneous agent dynamics and matched disturbances, a disturbance-observer-based distributed control protocol is developed for both first-order and second-order followers. Based on path-product-based coordinate transformations and Lyapunov stability analysis, sufficient conditions are derived to guarantee topology-dependent scaled leader-following cluster consensus under interactively balanced and interactively sub-balanced topologies. For interactively unbalanced topologies, a structurally selected pinning control strategy is introduced to compensate for sign conflicts caused by unbalanced directed cycles and ensure global asymptotic convergence. Numerical simulations verify the effectiveness of the proposed protocol under heterogeneous dynamics, weighted cooperative–competitive interactions, and matched disturbances. Full article

Background: The Physical Internet (PI) promotes resource sharing among independent firms. This can improve logistics efficiency, but shared route capacity and limited compensation may also create unequal outcomes among firms. Methods: This study develops a framework for coordinated logistics planning under shared route capacity constraints. The framework includes two coordination rules. Model 3.3 is an efficiency-oriented participation-guaranteeing rule with individual rationality constraints. Model 3.4 is a fairness-oriented rule that minimizes the maximum firm-level disadvantage under a limited compensation budget. Numerical experiments are conducted using a stylized Japanese domestic consumer goods distribution network. Results: Coordinated planning reduces total logistics cost compared with decentralized sequential allocation. Model 3.3 achieves the lowest system cost but gives benefits unevenly. Model 3.4 gives more balanced firm-level outcomes and improves the worst-off firm in the tested scenarios. The results also show that substantial fairness improvements can be obtained through small route-allocation changes. Conclusions: The study shows how two coordination rules can be used in PI-oriented logistics coordination. Model 3.3 is useful when firms need a no-loss guarantee, especially in an early stage. Model 3.4 is useful in a mature or repeated coordination stage, where the platform needs to avoid excessive disadvantage. Full article

Structural Health Monitoring (SHM) of large-span bridges requires dense sensor networks to accurately capture dynamic and kinematic behaviors. Traditional commercial systems rely on complex wiring or wireless protocols that frequently suffer from data loss, high power consumption, and synchronization phase errors, which are detrimental to Operational Modal Analysis (OMA). To address these limitations, this study presents the design, development, and field validation of a custom, offline-synchronized multi-sensor Data Acquisition (DAQ) system. Two specialized sensor nodes were developed: (i) an inertial node integrating a low-noise triaxial MEMS accelerometer (ADXL355); and (ii) a displacement node featuring a 24-bit Analog-to-Digital Converter (ADS1220) for displacement sensors. Both nodes share an ultra-low-power microcontroller (STM32L431) and utilize a local microSD storage strategy with an intermediate pseudo-SRAM buffer. To ensure precise temporal alignment without wireless communication overhead, each node incorporates a temperature-compensated Real-Time Clock (DS3231) for offline timestamp synchronization. The system was validated during a field campaign on the Spyckstraße bridge (Germany), deploying a hardware pool of 53 physical DAQ nodes to monitor 118 distinct geometric measurement points (106 inertial, 12 displacement) through a hybrid strategy of fixed and roving setups. The proposed system achieved reliable, low-noise measurements and enabled accurate extraction of operational mode shapes, demonstrating its viability as a robust, cost-effective solution for large-scale infrastructure monitoring. Full article

Cloud contamination obscures ground objects, interferes with surface reflectance, and disrupts spatial continuity. In thick-cloud regions, surface structures and spectral information are often extensively missing. CNN-based cloud removal methods can recover local textures, but they are less effective at modeling global structures and color consistency over large cloud-covered areas. Transformer-based methods capture long-range dependencies; however, standard self-attention introduces high computational and memory costs for high-resolution remote sensing images. Efficient attention reduces this cost but may weaken edge and texture discriminability. SAR imagery can penetrate clouds and provide surface structural information, yet repeated SAR injections may propagate speckle noise, cross-modal misalignment, and imaging discrepancies through deep restoration layers. To address these issues, this paper proposes DST-SARNet, a dual-stage SAR structural guidance network for optical remote sensing image cloud removal. In this framework, dual-stage refers to two explicit SAR-guidance positions: early structural skeleton guidance at the input side and late high-frequency modulation near the output. The Texture-Aware Asymmetric Retrieval module is placed between these two stages as a bottleneck memory retrieval operation rather than as a third dense SAR injection stage. With this design, SAR provides structural skeletons, readable texture memory, and terminal detail compensation, while the optical branch remains responsible for color, semantics, and spectral appearance recovery. Experiments on the SMILE-CR and SEN12MS-CR datasets show that DST-SARNet effectively restores cloud-contaminated imagery with a compact model scale, demonstrating its potential for efficient SAR-assisted optical cloud removal. Full article

This paper presents an adaptive neural-network-based algorithm for chattering mitigation in sliding mode control (SMC) of parallel multicellular DC/AC power converters. Although conventional SMC provides strong robustness against parameter uncertainties, external disturbances, and load variations, its discontinuous control action often generates chattering, resulting in excessive switching activity and reduced converter performance. To address this limitation, a computationally efficient adaptive neural network is integrated into the SMC framework to approximate the discontinuous switching term and generate a smooth control signal. The proposed algorithm updates neural network parameters online through an adaptive learning mechanism, enabling real-time compensation of modeling uncertainties while preserving the inherent robustness of SMC. The resulting adaptive neural network sliding mode control (ANN-SMC) algorithm is formulated to ensure accurate output voltage tracking, balanced operation of converter cells, and reduced switching oscillations. Extensive simulation studies are conducted under different operating scenarios, including load variations and system disturbances. The performance of the proposed method is evaluated against classical SMC using quantitative indicators related to tracking accuracy, dynamic response, robustness, and chattering suppression. The results demonstrate that the ANN-SMC algorithm significantly reduces high-frequency oscillations while improving transient behavior and maintaining robust operation. These findings indicate that the proposed adaptive learning-based control algorithm constitutes an effective and scalable solution for advanced power conversion systems operating under uncertain conditions. Full article

Tracking highly maneuverable UAVs in complex maritime environments faces multiple challenges: dynamic sea surface interference and low-altitude occlusion make UAV motion trajectories difficult to predict; the strong maneuvering behavior of UAVs imposes high demands on tracking real-time performance and accuracy; and marine environmental noise and unstable shipborne sensor data lead to measurement incompleteness. These factors collectively limit the adaptability and robustness of existing maneuvering UAV tracking methods in complex maritime scenarios. In this context, accurate model recognition for UAVs becomes a key factor in improving tracking performance. Traditional interactive multiple model (IMM) methods rely on probabilistic weighting for model selection, suffering from response delays during UAV maneuvers, and fixed model sets cannot adapt to diverse maneuvering scenarios, resulting in degraded UAV velocity estimation accuracy. To address the above issues, this study proposes a dual long short-term memory (LSTM) cooperative network architecture, targeting the two key problems of incomplete measurements in shipborne radar measurements and inaccurate model probability estimation, and presents corresponding solutions. First, an online-trained LSTM-based incomplete-measurement compensation method is proposed, which achieves real-time fitting and restoration of historical measurement data, providing continuous and stable measurement inputs for shipborne platform UAV tracking in maritime environments. Second, building on this, an LSTM-based UAV model recognition method is developed to directly identify the UAV’s current motion model from multi-frame historical measurement information, effectively reducing maneuvering delays. Furthermore, GPS data is used to generate optimal model probabilities as training labels, thereby improving model reliability. Simulation results show that, under incomplete-measurement conditions, the proposed method can effectively reconstruct missing measurements and ensure measurement continuity. Under complete-measurement conditions, the proposed LSTM-based model recognition method significantly improves UAV model recognition accuracy and three-dimensional velocity estimation performance, demonstrating the effectiveness of deep learning for maneuvering UAV tracking from shipborne platforms in maritime environments. Full article

Deep learning methods that integrate convolutional neural networks (CNNs) and Transformers have achieved remarkable progress in hyperspectral image (HSI) classification. However, existing methods still suffer from insufficient multi-scale spatial–spectral feature modeling, a lack of efficient interaction mechanisms between local and global features, and the inherent high computational complexity and redundant information of Transformers, which limit model performance. To address these issues, a Multi-Scale Spatial–Spectral Convolutional Hybrid Transformer model (MS³CHFormer) is proposed in this article. Specifically, a Multi-Scale Spatial–Spectral Convolution Module (MS³ConvM) is first constructed. Through a multi-branch and multi-receptive-field design, it jointly models spatial and spectral features at different scales, thereby enhancing the representation capability of complex ground objects. Then, a Token-Selective Sparse Transformer Encoder (TSSTE) is designed, which adaptively selects tokens and performs sparse modeling via a Dynamic Correlation-Aware Attention (DCAA) mechanism, effectively reducing computational complexity while suppressing redundant information and further reinforcing key feature representations. Furthermore, a Local–Global Feature Fusion Module (LGFFM) is designed to achieve deep complementary fusion of CNN and Transformer features by mapping them into different representation spaces. Finally, a Detail-Preserving Enhancement Module (DPEM) introduces original detail information through residual connections to compensate for detail loss in high-level semantic representations, thereby enhancing the representation capability of boundaries and fine-grained structures. Experiments and comparative analyses on four public HSI datasets demonstrate that the proposed MS³CHFormer outperforms state-of-the-art methods and achieves superior classification accuracy under limited training samples, exhibiting excellent robustness and generalization ability. Full article

This paper investigates an observer-based secure control method for networked non-Lipschitz nonlinear systems subject to unknown nonlinearities, external disturbances, sensor noises, and intermittent denial-of-service (DoS) attacks. Multi-layer neural networks (MNNs) are adopted to compensate for non-smooth, non-Lipschitz terms, guaranteeing bounded approximation errors. A resilient high-gain observer fused with the MNN is developed to continuously reconstruct system states. When DoS attacks block sensor channels, the observer acts as a virtual dynamic engine to substitute for lost real-time measurements, providing uninterrupted feedback to the controller. Furthermore, to optimize communication efficiency, an observer-based static event-triggered mechanism (SETM) coupled with a hold-input strategy is integrated. Employing the Lyapunov–Krasovskii functional method, sufficient conditions are derived to prove that the closed-loop system remains uniformly ultimately bounded (UUB) under the joint effects of approximation errors, disturbances, and attacks. Simulation results on a two-link manipulator demonstrate that the proposed secure control scheme effectively counters aggressive DoS attacks while achieving a 56.8% reduction in network transmissions compared with conventional periodic sampling paradigms, striking a favorable balance between tracking accuracy and resource efficiency. Full article

This paper addresses the high-precision position tracking control problem for the rotary direct-drive valve (RDDV) subject to complex nonlinear dynamics and unknown external disturbances. To achieve superior transient and steady-state performance, a novel adaptive neural network preset-time control (ANNPTC) strategy is proposed. Distinct from conventional finite-time or fixed-time control schemes, the proposed ANNPTC ensures that the tracking error converges to a prescribed neighborhood of the origin within a prescribed residual set after the user-defined time $T_c$ under the admissible initial condition. Specifically, adaptive radial basis function neural networks (RBFNNs) are utilized to estimate and compensate for unmodeled dynamics and disturbances, significantly enhancing the steady-state precision of the system. The uniform ultimate boundedness of all signals in the closed-loop system and the prescribed-performance property are established via Lyapunov stability analysis. Finally, extensive simulation results on a high-fidelity RDDV model demonstrate that the proposed method yields faster response speed and higher tracking accuracy compared with benchmark controllers, thereby validating its efficacy and superiority in RDDV applications. Full article

This paper addresses the challenges of achieving robust coordination in discrete-time multi-robot systems subject to uncertainties and Byzantine attacks affecting both actuator and sensor channels. Such adversarial disruptions degrade system performance by corrupting control inputs and state measurements, ultimately threatening stability and consensus in networked robotic systems. To overcome these limitations, a novel discrete-time adaptive control framework is proposed that ensures reliable tracking and stability under both uncoupled and coupled robot dynamics. The approach integrates a modified graph-theoretic structure with node-dependent weighting to capture heterogeneous robot interactions, while explicitly modeling attack effects within the system dynamics. An adaptive control law is developed using a nonlinear basis function approximation to handle unknown system uncertainties, along with a dynamic weight update mechanism that compensates for adversarial disturbances in real time. For the uncoupled case, stability is established through a composite Lyapunov function incorporating logarithmic and quadratic terms, guaranteeing boundedness of all closed-loop signals and asymptotic convergence of the tracking error. This framework is further extended to systems with coupled dynamics by introducing an auxiliary estimation mechanism to reconstruct unmeasurable interactions, leading to a unified adaptive controller capable of mitigating both internal uncertainties and external attacks. Rigorous Lyapunov-based analysis demonstrates that the proposed method ensures asymptotic tracking performance despite the presence of Byzantine disturbances. Numerical simulations validate the theoretical results, showing improved resilience, accurate trajectory tracking, and enhanced robustness compared to existing approaches. Full article

In modern farm management, accurate detection of estrus behavior in dairy cows is essential for improving reproductive efficiency and enabling intelligent decision-making. Although fisheye lenses offer a wider field of view, they often introduce image distortion. This leads to geometric and scale deformation of cow mounting behavior features, which reduces detection accuracy. To address this issue, a lightweight model called Boundary-Enhanced Frequency-Domain Feature Pyramid Network YOLO (BFFPN-YOLO) was developed. It is designed for detecting dairy cow mounting behavior under fisheye imaging, incorporating boundary enhancement and frequency-domain compensation. Initially, the backbone network was equipped with the multi-scale dilated fusion structure SPPELAN. This structure expands the receptive field and preserves detailed information, thereby enhancing boundary modeling for targets with scale variations. Subsequently, a boundary-enhanced frequency-domain feature pyramid network (BFFPN) module was designed for reconstructing the top-down transmission path in the Neck. The module is composed of the frequency-domain detail compensation FreqFusion and the spatial attention enhancement SEAM. By strengthening boundary responses, compensating for high-frequency details, and replacing the traditional upsampling and concatenation operations, it effectively mitigates blurred target boundaries in images of dairy cow mounting behavior. The improved algorithm demonstrates strong detection performance, achieving a Precision of 88%, a Recall of 84.5%, and an mAP@0.5 of 92.7%. Compared with the original YOLOv11, these metrics were increased by 3.8, 2.3, and 4.6 percentage points, respectively. The model parameter count was reduced by 1.10 × 10⁶. In complex scenarios, edge features and high-frequency details of dairy cow mounting behavior are more accurately captured by the improved model. These improvements provide a reliable technical basis for the intelligent detection of estrus behavior. Full article

This paper presents a decentralized adaptive generalized-minimum-variance (GMV) control framework for large-scale stochastic nonlinear systems composed of interconnected multi-input multi-output (MIMO) Hammerstein subsystems with unknown time-varying parameters. Each subsystem consists of a coupled multivariable static nonlinearity represented on a known invertible basis, followed by a matrix-polynomial dynamic block affected by colored noise and delayed input–output interconnections. The proposed scheme estimates only identifiable composite Hammerstein parameters through a decentralized recursive extended least-squares algorithm with forgetting, thereby avoiding the non-unique separation of nonlinear and linear gains. A constructive matrix Diophantine identity is established to derive an optimal multi-step predictor, leading to a GMV control law expressed as a multivariable polynomial equation in the current input. Sufficient conditions for real solvability, mean-square boundedness, and near-optimal adaptive tracking are provided using Hadamard–Lévy global-diffeomorphism, minimum-phase, small-gain, persistent-excitation, strict-positive-realness, and convex-projection arguments, and the implemented controller—inexact Newton solver with fallback and persistent dither—is itself covered by the analysis. The analysis further shows that delayed interconnections become measurable and can be exactly compensated, while robustness to basis under-modeling is explicitly quantified. Simulation results on an interconnected two-subsystem MIMO Hammerstein process with coupled cubic nonlinearities, colored noise, delayed interactions, and time-varying parameters—run in the forgetting-factor regime required by the theory, with measured persistent excitation and complete solver diagnostics—demonstrate operational-noise-floor tracking and a $2.3$-fold mean-RMSE reduction relative to the strongest linear-MIMO surrogate, while a channel-wise SISO Hammerstein design fails structurally and a feedback-linearization controller with exactly known nonlinearity offers no advantage. The study further demonstrates scalability on a chain of four subsystems with size-independent per-subsystem computational cost, validates a physically motivated interconnected coupled-tank network with progressive-valve nonlinearities, and confirms agreement between the observed stability limits and the predicted small-gain boundary. Full article