Search Results (433)

Cotton, a globally significant crop grown in over 100 countries, sustains a $40 billion market and provides employment for over 350 million people worldwide. However, plastic contamination remains a persistent challenge within the industry, degrading cotton fiber quality and disrupting ginning. Manual inspection and optical machine-vision systems struggle when plastic fragments are concealed by fibers or lack sufficient color contrast. To address these challenges, we developed an ultrasonic phased-array imaging system operating at 40 kHz under field-programmable gate array (FPGA) control. Transmitter elements emit pulsed ultrasound along radial paths, separate reflection receivers record echo amplitudes to form acoustic images, and a set of transmission receivers captures signal attenuation, which is overlaid onto the reflection-based image to highlight potential contaminants. In preliminary laboratory-based tests on both seed cotton and lint samples, the system successfully detected visually obscured plastic fragments as small as $2\mathrm{cm}\times 2\mathrm{cm}$ with an angular resolution limit of $\pm 3^{\circ }$. Distinct reflection peaks and corresponding attenuation overlays were produced across the field of view, validating the system’s detection capabilities. These results demonstrate the feasibility of using ultrasonic imaging to reveal concealed plastics in cotton processing. Integrating this approach with existing optical methods could enhance contaminant-removal workflows and improve overall fiber quality and processing efficiency. Full article

To address unstable localization and sparse mapping for autonomous vehicles operating in GPS-denied and low-visibility environments, this paper proposes GTS-SLAM, a tightly coupled dense visual SLAM framework integrating Generalized Iterative Closest Point (GICP) and 3D Gaussian Splatting (3DGS). The system is designed for intelligent driving platforms such as underground mining vehicles, inspection robots, and tunnel autonomous navigation systems. The front-end performs covariance-aware point-cloud registration using GICP to achieve robust pose estimation under low texture, dust interference, and dynamic disturbances. The back-end employs probabilistic dense mapping based on 3DGS, combined with scale regularization, scale alignment, and keyframe factor-graph optimization, enabling synchronized optimization of localization and mapping. A Compact-3DGS compression strategy further reduces memory usage while maintaining real-time performance. Experiments on public datasets and real underground-like scenarios demonstrate centimeter-level trajectory accuracy, high-quality dense reconstruction, and real-time rendering. The system provides reliable perception capability for vehicle autonomous navigation, obstacle avoidance, and path planning in confined and weak-light environments. Overall, the proposed framework offers a deployable solution for autonomous driving and mobile robots requiring accurate localization and dense environmental understanding in challenging conditions. Full article

Identifying microscopic textural anomalies and filtering out complicated industrial background noise remain significant hurdles in inspecting metallic surfaces. To tackle these operational bottlenecks, our research introduces a refined multi-scale detection framework built upon the YOLOv8l architecture. Specifically, we engineer a fine-grained detection pathway utilizing the P2 layer, which aims to preserve critical details of miniature flaws that are otherwise discarded during feature extraction. Furthermore, a Bi-directional Feature Pyramid Network model is embedded to reconstruct the feature fusion path, balancing the preservation of shallow geometric textures with enhanced multi-scale representation capabilities. To bolster anti-interference performance, a Convolutional Block Attention Module (CBAM) is integrated prior to the detection head, employing adaptive channel and spatial weighting to suppress unstructured background noise. Experimental results utilizing TTA demonstrate that the mAP@0.5 reached 76.3%. Detection accuracies for patches and inclusions reached 93.1% and 85.3%. Full article

Background/Objectives: Impella support is increasingly utilized as a crucial bridge to durable left ventricular assist device (LVAD) in patients with refractory cardiogenic shock. However, the transvalvular path of the Impella catheter raises concerns regarding mechanical trauma, potentially precipitating or accelerating aortic regurgitation (AR). We aimed to characterize the complete longitudinal trajectory of AR following Impella bridge-to-LVAD and to determine its association with clinical and hemodynamic sequelae. Methods: We conducted a single-center retrospective cohort study including all patients bridged from Impella to durable LVAD between 2013 and 2024 (n = 19). At Impella initiation, all patients met the retrospective SCAI shock stage D or worse criteria. At LVAD implantation, all patients were classified as INTERMACS 1–2 (INTERMACS 2, n = 13). The Impella models were 5.0 in 11 (axillary access), 2.5 in 5 (femoral access), and CP in 3 (femoral access); no periprocedural Impella complications were recorded. The implanted LVAD systems were HeartMate II (n = 7), HVAD (n = 3), and HeartMate III (n = 9). Patients undergoing concomitant aortic valve intervention were excluded. Transthoracic/TEE echocardiography was performed at prespecified time points (pre-Impella, pre-LVAD, post-LVAD discharge, 12 months, and 24 months) with standardized aortic regurgitation (AR) grading. Right ventricular (RV) function was assessed qualitatively when quantitative indices (TAPSE) were unavailable. Primary endpoints were new or progressive AR and AR severity at LVAD implantation. Secondary endpoints included survival, renal dysfunction, biomarkers, and rehospitalization. Univariate analyses were used to compare outcomes according to AR severity. Results: Nineteen patients (68% male, median age 57 years, IQR 47–60) underwent Impella support for 13.3 ± 9.9 days before HeartMate 3 (84%) or HVAD (16%) implantation. All patients had competent aortic valves (grade 0 AR) at the time of LVAD implantation. AR ≥ mild developed in 9/18 (50%) at discharge, 12/15 (80%) at 12 months, and 13/15 (87%) at 24 months, and 8/15 (53%) progressed to ≥ moderate AR by 24 months. Patients with moderate-to-severe AR had higher NT-proBNP levels at 12 months (median 6318 vs. 2336 pg/mL, p = 0.137). Thirty-day and 24-month survival rates were 95% and 79%, respectively. Conclusions: Aortic regurgitation frequently develops or progresses from the pre-LVAD period to follow-up in patients bridged from Impella to durable LVAD. Although limited by a small sample size and incomplete quantitative RV metrics, these observations support structured echocardiographic surveillance after Impella use and management strategies—routine valve inspection at LVAD implantation and post-LVAD speed/blood pressure targets that encourage aortic valve opening—to mitigate the risk and clinical impact of aortic regurgitation. Full article

A coupled non-destructive testing (NDT) workflow is proposed that integrates active infrared thermography (IRT) with laser-scanning-based reverse engineering (RE) to increase the reliability of detecting and interpreting damage in composite wind turbine blades across laboratory specimens and real components. IRT provides rapid, image-based qualitative localisation of potential anomalies, while 3D scan analysis supplies quantitative, geometry-aware verification and measurement of defect magnitude, reducing both false positives (design-related thermal signatures) and false negatives (weak thermal contrast). On polystyrene-filled profiles, IRT alone produced thermal anomalies unrelated to delamination; co-registered scan maps identified or ruled out local indentation, correctly attributing heat-flow patterns to internal design rather than damage. Outcome: the fused method disambiguates thermal indications and quantifies defect magnitude. On a vertical-axis wind turbine (VAWT) blade, the integration distinguished genuine geometric change from architectural effects under unknown internal structure and without CAD/reference scans, preventing false calls. For three horizontal-axis wind turbine (HAWT) blades, fleet-level scan comparison detected a significant tip deviation despite no clear local IRT anomalies, demonstrating complementary roles: scan = global quantitative homogeneity; and IRT = local qualitative verification. These findings operationalise thermal–geometric cross-validation and outline a path toward UAV-enabled inspections combining passive IRT and laser scanning for hard-to-access structures under real environmental conditions. Full article

The irregular geometry of highway tunnel linings, combined with uneven terrain and external disturbances, often causes inspection robots to deviate from their predefined paths. Due to the strong coupling inherent in robotic systems, these deviations propagate to the end-effector, significantly compromising automated inspection accuracy and effectiveness. To tackle these issues, this study introduces an Enhanced Extended Sliding Mode Predictive Control (EESMPC) method, which integrates an adaptive Extended State Observer (ESO). The algorithm is derived from the robot chassis model and a desired trajectory error model, enabling precise contour profile tracking. Crucially, the integrated ESO actively estimates and compensates for unmodeled disturbances and system uncertainties within the state feedback, thereby enhancing both path tracking stability and precision. Comparative MATLAB simulations and experimental path tracking tests evaluated the performance against three other controllers. The results demonstrate that the EESMPC algorithm achieves superior tunnel lining tracking performance, exhibiting marked improvements in both tracking accuracy and system robustness. Consequently, this approach significantly enhances the automated inspection accuracy and operational efficiency of highway tunnel inspection robots. Full article

With the increasing demands for autonomy and coverage efficiency in tasks such as security patrol and post-disaster exploration using mobile robots, achieving random, efficient, and complete coverage path planning has become a critical challenge. Traditional chaotic path planning methods, while capable of generating unpredictable trajectories, still have limitations in terms of randomness strength, traversal uniformity, and convergence coverage. To address this, this study proposes a complete-coverage random path planning method based on a novel four-dimensional fractal-fractional multi-scroll chaotic system. The main contributions of this research are as follows: First, by introducing additional state variables and fractal-fractional operators into the classical Chen system, a fractal-fractional chaotic system with a multi-scroll attractor structure is constructed. The output of this system is then mapped into robot angular velocity commands to achieve area coverage in unknown environments. Key findings include: the novel chaotic system possesses two positive Lyapunov exponents; Spectral Entropy (SE) and Complexity (CO) analyses indicate that when parameter B is fixed and the fractional order α increases, the dynamic complexity of the system significantly rises; in a 50 × 50 grid environment, the robot driven by this system achieved a coverage rate of 98.88% within 10,000 iterations, outperforming methods based on Lorenz, Chua systems, and random walks; ablation experiments further demonstrate that the combined effects of the fractal order β, fractional order α, and multi-scroll nonlinear terms are key to enhancing system complexity and coverage performance. The significance of this study lies in that it not only provides new ideas for constructing complex chaotic systems but also offers a reliable theoretical foundation and practical solution for mobile robots to perform efficient, random, and high-coverage autonomous inspection tasks in unknown regions. Full article

As manufacturing progresses, the demand for precision inspection of complex parts has intensified. To guarantee functionality and sensory performance, high-efficiency 3D shape measurement is required. In this paper, a collaborative robot-based approach for efficient and high-precision 3D shape inspection of complex parts is proposed. The system employs a collaborative robot to drive the scanner along optimized trajectories. First, the configuration of the inspection system is presented, and the ideal measurement mode for the sensor is analyzed. Subsequently, adaptive viewpoints are generated through parametric discretization based on surface geometric features. For inter-region scanning path planning, the problem is modeled as the Shortest Path Problem (SPP) within the framework of the Traveling Salesman Problem (TSP) and solved by constructing a Successive Approximation Algorithm (SAA). Furthermore, a Modified Denavit-Hartenberg (MDH) method is applied to establish the precise kinematic model of the collaborative robot. Inverse kinematics solutions are derived to convert planned viewpoints into target joint configurations, thereby achieving precise end-effector pose control. Simulation and experimental results on an engine cover and a cylinder head demonstrate that the proposed approach enables comprehensive 3D shape inspection of complex parts in a single setup and achieves higher efficiency and accuracy compared to existing methods. This work offers a viable solution for integrating robotic actuation and active sensing in the automated inspection of complex geometries. Full article

Ubiquitous aerial sensing with unmanned aerial vehicles (UAVs) is becoming an essential component of AI-native perception systems, motivated by the trend toward edge deployment and potential integration with future sixth-generation (6G)-connected aerial networks. In this work, we focus on improving the perception-side accuracy and computational efficiency of small-object detection in UAV imagery. However, small object detection in high-altitude UAV imagery remains highly challenging due to the extremely low pixel occupancy of targets and the severe multi-scale interference introduced by complex backgrounds. To address these limitations, we propose a Multi-scale Attention Fusion Network (MAF-Net), an AI-native paradigm for real-time small object detection in UAV imagery. The proposed approach enhances small-target representation and robustness through three key designs. First, a density-adaptive anchor optimization strategy is developed by combining K-means++ clustering with an IoU-based distance metric, enabling anchors to better match scale variation under diverse object densities. Second, a multi-scale feature reinforcement module is introduced to strengthen fine-grained detail preservation by integrating shallow feature maps via skip connections and hierarchical aggregation. Third, a dual-path attention mechanism is employed to jointly model channel importance and spatial localization, improving discriminative feature calibration in cluttered aerial scenes. Extensive experiments on three public benchmarks (AI-TOD, DOTA, and RSOD) demonstrate that MAF-Net consistently outperforms the baseline detector, achieving mAP@0.5 gains of 14.1%, 11.28%, and 22.09%, respectively. These results confirm that MAF-Net provides an effective and deployment-friendly solution for robust small object detection, supporting real-time UAV-based inspection and AI-native ubiquitous aerial sensing applications. Full article

In response to the challenges of low detection efficiency, high omission rate in small target detection and high model complexity in wood surface defect detection, this study proposes a lightweight detection model based on YOLO, which integrates a dual-path integrated attention network (DFA-Net). The model is built on the enhanced YOLOv5 framework and achieves a balance of accuracy and efficiency through the collaborative optimization of multiple modules. Specifically, this paper designs a dual-path downsampling convolutional module (DP-DCM), combining wavelet transform with dual-path feature fusion to improve multi-scale feature extraction capabilities while reducing the number of parameters. Next, a fusion attention module (FAM) is designed to dynamically focus on defect features in complex backgrounds through channel and spatial attention mechanisms. Furthermore, a focal modulation network (FMNet) is introduced to enhance the robustness of the augmentation model in detecting small defects. Finally, the NWD Loss function is used to mitigate the localization bias of small targets. Experimental results show that the improved model achieves a 92.8% mAP rate on five types of defect datasets (dead knots, live knots, cracks, notches, and marrow). Compared with the baseline model, YOLOv5s, the performance of this model has been improved by 6.5%. The model runs at a detection speed of 105 FPS, and the number of parameters is only 5.8 million, which is better than models such as YOLOv8 and YOLOv9-t. While maintaining a lightweight design, this method achieves high precision and real-time performance on a consumer-grade GPU platform, indicating its practical applicability in automated wood inspection scenarios. The proposed approach provides an efficient solution for intelligent wood sorting, contributing to improved wood utilization and enhanced processing automation. Full article

This paper proposes a substation operation risk situational awareness method based on the health state of the main equipment, with the goal of assessing the substation operation risk posture and performing risk prevention and control based on the situational awareness framework. Firstly, a risk propagation model considering the health state of the main equipment is proposed with reference to the SI (Susceptible–Infected) virus propagation model to simulate the risk propagation process among the main equipment of the substation; then, the potential risk severity index of the equipment is constructed based on the temporal set of risk propagation among the equipment within the substation to quantify the operational risk posture of the substation; finally, a case analysis is carried out by using a dual-voltage-level substation, and the results show that the method proposed in this paper can effectively simulate the risk propagation paths between the main equipment of a substation and the severity of the operational risk of each piece of main equipment. Based on the results of the substation operation risk situation assessment, it is used to guide the substation operation and inspection department to optimize the substation main equipment operation and inspection plan formulation, and to find the main equipment defects in time for overhaul and maintenance. Full article

In contemporary 5G network environments, intrusion detection systems must balance detection accuracy with operational efficiency, as improvements in one dimension are often achieved at the expense of the other. This study addresses this trade-off by proposing a lightweight two-stage intrusion detection architecture that augments a standard decision-tree classifier with a conditional counter-inspection mechanism. At inference time, a global decision tree produces an initial classification for each traffic record, which is selectively validated by a small set of class-biased expert trees trained under controlled minority exposure. Only experts associated with the opposite class of the initial prediction are activated, and decision revision is governed by a unanimous-dissent rule, ensuring conservative and deterministic correction while avoiding over-correction. Experiments conducted on the 5G-NIDD dataset in a binary benign/malicious setting show that the proposed architecture consistently improves upon the standalone decision tree, reducing false negatives from 51 to 27 (−47.1%) and false positives from 48 to 30 (−37.5%), and achieving an F1-score of 0.99981 on a held-out test set. Ablation and paired statistical tests confirm that these gains arise from selective validation and the unanimous-dissent mechanism rather than from uniform ensembling. The complete pipeline operates in the microsecond inference regime per record, evaluates fewer models on average than flat voting strategies, and preserves full interpretability through deterministic decision paths, making it suitable for practical and resource-constrained 5G intrusion detection deployments. Full article

Confronted with the severe imperatives to food security posed by a growing population and the urgent need for sustainable development amid climate change, traditional agricultural models face significant resource-intensive efficiency bottlenecks. Deep learning-based image recognition is driving a future-oriented intelligent agricultural revolution by enabling high-throughput phenotyping and autonomous decision-making across the production chain. This paper systematically reviews key advancements in image recognition within modern agriculture, mapping the fundamental paradigm shift from traditional hand-crafted feature engineering to adaptive deep feature learning. We critically analyze technological implementation and performance across five core application scenarios: high-precision pest and disease diagnosis, spatio-temporal growth monitoring and yield prediction through multi-source image fusion, agricultural robots for automated harvesting, non-destructive quality inspection of products, and intelligent precision management of farmland. The review further identifies critical challenges hindering large-scale technology adoption, primarily centered on the high costs of constructing high-quality agricultural datasets and model robustness in complex field environments. Consequently, this study provides a comprehensive and forward-looking reference for advancing the deep integration of vision technology, thereby offering a strategic path toward achieving more intelligent, efficient, and sustainable global agricultural production systems in the digital era. Full article

Automated verification of preflight aircraft inspection—a critical safety procedure—is addressed by integrating multi-camera tracking with procedural knowledge through a symmetry-aware spatio-temporal graph model. Departing from conventional tracking paradigms, the framework encodes operational protocols and structural symmetries of the aircraft as explicit constraints for trajectory association. Semantically consistent inspection zones are derived from geometric symmetry, and reliable tracklets extracted within them are connected using rules that enforce temporal order and identity consistency. Verification is formulated as a constrained shortest-path search over this graph, ensuring sequential and complete coverage of all mandatory zones by a single inspector. Evaluated on real-world airport surveillance data across diverse conditions, the proposed approach achieves a Complete Inspection Success Rate of 86.5%, significantly outperforming state-of-the-art tracking and re-identification baselines. The results demonstrate that explicit procedural integration substantially enhances the reliability and interpretability of automated compliance verification in safety-critical industrial monitoring. Full article

Objectives: Global infertility rates are rapidly increasing. Assisted reproductive technologies combined with artificial intelligence are the next hope for overcoming infertility. In vitro fertilization (IVF) is gaining popularity owing to its increasing success rates. The success rate of IVF essentially depends on the assessment and inspection of blastocysts. Blastocysts can be segmented into several important compartments, and advanced and precise assessment of these compartments is strongly associated with successful pregnancies. However, currently, embryologists must manually analyze blastocysts, which is a time-consuming, subjective, and error-prone process. Several AI-based techniques, including segmentation, have been recently proposed to fill this gap. However, most existing methods rely only on raw grayscale intensity and do not perform well under challenging blastocyst image conditions, such as low contrast, similarity in textures, shape variability, and class imbalance. Methods: To overcome this limitation, we developed a novel and lightweight architecture, the microscopic multimodal interaction segmentation network (MiMics-Net), to accurately segment blastocyst components. MiMics-Net employs a multimodal blastocyst stem to decompose and process each frame into three modalities (photometric intensity, local textures, and directional orientation), followed by feature fusion to enhance segmentation performance. Moreover, MiMic dual-path grouped blocks have been designed, in which parallel-grouped convolutional paths are fused through point-wise convolutional layers to increase diverse learning. A lightweight refinement decoder is employed to refine and restore the spatial features while maintaining computational efficiency. Finally, semantic skip pathways are induced to transfer low- and mid-level spatial features after passing through the grouped and point-wise convolutional layers. Results/Conclusions: MiMics-Net was evaluated using a publicly available human blastocyst dataset and achieved a Jaccard index score of 87.9% while requiring only 0.65 million trainable parameters. Full article