Search Results (178)

This study demonstrates how structured algorithmic optimization can enhance intelligent visual measurement systems in mining engineering. Real-time visual measurement of mining conveyor belts is critical for operational safety, yet achieving high-precision anomaly detection under complex environmental conditions remains a significant challenge. Conventional approaches often struggle to balance detection accuracy with computational efficiency due to inefficient feature representation and optimization strategies. To address this, this study proposes FDSE-DETR, a lightweight end-to-end framework designed for real-time anomaly evaluation. The framework eliminates Non-Maximum Suppression (NMS) to streamline inference. Specifically, this study introduces a deformation-aware sampling mechanism to enhance feature representation of irregular hazards, alongside a cost-effective multi-scale aggregation strategy to preserve fine cues within strict device budgets. Furthermore, a reformulated loss objective is developed to rebalance hard samples under severe class imbalance, improving the detection confidence. Experimental results on mining conveyor belt foreign object datasets show a 4.5% improvement in mean average precision (mAP), a 3.9% improvement in overall recall and a 22.5% reduction in computational cost, achieving 120.7 FPS. This study aims to address the problems of insufficient accuracy and low efficiency in real-time material flow measurements on mining conveyor belts under high-dust and low-illumination conditions. Full article

Accurate individual tree crown identification is essential for urban forestry, yet existing datasets often lack exhaustive annotations and multi-temporal diversity. To address this limitation, an exhaustively annotated dataset was curated for crown instance segmentation, comprising 47,754 labeled individual crowns from approximately 110 species across three temporal phases. Anchored in a “crown geometry” labeling criterion focusing on upper-canopy individuals visible in the imagery, and the high-resolution imagery captured seasonal variations in shape, color, and texture, providing an empirical basis for within-site robustness. Utilizing this dataset, this study (1) compared five instance segmentation models; (2) evaluated their generalization capabilities across different temporal phases; and (3) tested a multi-temporal joint training strategy and a non-maximum suppression (NMS)-based fusion. The experiments revealed significant overfitting in single-temporal models. While ConvNeXt-V2 achieved a high segmentation mean Average Precision (Segm_mAP) of 0.852 within the same temporal phase, its performance dropped sharply to 0.361 across phases. Bi-temporal joint training significantly mitigated this issue, improving cross-temporal performance to 0.665 and further increasing within-phase accuracy to 0.874. In contrast, tri-temporal training reduced accuracy (0.748), demonstrating that effective generalizability depends on the strategic selection of complementary temporal phases rather than the mere accumulation of data. The multi-temporal training framework provided in this study could serve as a practical reference and a foundational benchmark for further urban forest structural monitoring research. Full article

Low-grade highway maintenance faces the challenge of high demand yet limited resources. Accurately identifying road damage is a key task to improve maintenance efficiency, which is crucial for addressing this demand–resource contradiction. To address this issue, YOLOv5s was selected as the foundational model due to its superior balance of detection accuracy, speed, and computational efficiency compared to other YOLO variants. Comprehensive optimizations were then implemented to further enhance its performance, including the development of a Global Context Squeeze (GS) module, a modified loss function, optimized Non-Maximum Suppression (NMS), and targeted image preprocessing strategies. The GS module is designed to effectively integrate contextual information, expand the receptive field, capture long-range dependencies, and strengthen feature extraction capabilities. A suburban road section in Shanghai with typical pavement damage was selected as the experimental site, where 8515 images were collected for model training and testing. Experiments demonstrated that the optimized YOLOv5s-G model achieved a mean average precision (mAP) of 90.7% for crack detection, a relative improvement of 18.6% over the original YOLOv5s. Furthermore, it outperformed models employing conventional optimization strategies, such as those with added small object detection layers or standard attention mechanisms. The superior performance of the YOLOv5s-G model significantly enhances pavement crack detection accuracy, offering technical support to improve low-grade highway maintenance efficiency and alleviate pressures from resource limitations. Full article

The global rise in electronic waste (e-waste), especially in semiconductor components such as circuit boards and microchips, underscores a critical need for improved recycling technology. Current industrial sorters often miss small, high-value components. This leads to the loss of precious metals and inefficient recycling processes. This paper introduces an automated detection framework for detecting semiconductor components in e-waste. It assesses ensemble learning methods that leverage the strengths of multiple YOLO (You Only Look Once) object detection models, including YOLOv5, YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLOv12. Three ensemble fusion strategies are systematically compared: standard Non-Maximum Suppression (NMS), voting-based strategies (Affirmative, Consensus, Unanimous), and Weighted Box Fusion (WBF) with both static and dynamic weight optimization. Our simulations demonstrate that using multiple models together is far more effective than a single model for the following reasons. 1. Higher Accuracy: The best configuration, Top-4 Consensus Voting ensemble strategy, achieved an mAP@0.5 of 59.63%, a 10.3% improvement over the best individual model (YOLOv8s, 54.04%); 2. Greater Reliability: It significantly reduced “false negatives” (missed detections), even in cluttered or crowded e-waste scenarios; 3. Enhanced Detection: While the individual YOLOv8 model is fast (taking only 62.6 ms), supporting real-time detection, the best ensemble configuration (Consensus Top-4) takes 384.9 ms, creating a trade-off between detection accuracy and speed; 4. Well-Balanced Performance: Some fusion strategies showed slight trade-offs in mAP for certain parts, but collectively achieved a 7% rise in F1-score, indicating a better balance between precision and recall. This research marks significant progress in smart recycling. Improved component identification allows for more efficient recovery of high-purity materials. This promotes a circular economy by ensuring that rare and strategic materials in electronics are reused instead of discarded. Full article

The effects of Fe non-stoichiometry on crystal structure, microstructural evolution, and thermoelectric transport properties were systematically investigated in bornite (Cu₅Fe_1+yS₄; −0.06 ≤ y ≤ 0.06) synthesized by mechanical alloying followed by hot pressing. X-ray diffraction analysis confirmed the formation of a single-phase orthorhombic bornite structure over the entire composition range. Anisotropic lattice distortion was observed with increasing Fe non-stoichiometry, manifested as contraction along the a-axis and expansion along the b- and c-axes, with a non-linear dependence on composition. Crystallite sizes estimated from Lorentzian peak fitting increased from 64.1 nm for the stoichiometric composition to 70.6–76.3 nm for Fe-deficient samples and 73.2–90.9 nm for Fe-excess samples. Hall-effect measurements revealed p-type semiconducting behavior for the stoichiometric composition, degenerate p-type transport with increased hole concentration under Fe-deficient conditions, and a transition to n-type behavior with reduced carrier mobility under Fe-excess conditions. While Fe-deficient samples retained high electrical conductivity and positive Seebeck coefficients, Fe-excess samples exhibited negative Seebeck coefficients at low temperatures with sign reversal at elevated temperatures. As a consequence, the power factor of Fe-deficient samples was enhanced by approximately 20–30% relative to the stoichiometric composition. In addition, the total thermal conductivity remained below 0.8 W·m⁻¹·K⁻¹ for all samples, and Fe non-stoichiometry effectively suppressed lattice thermal conductivity. Consequently, the Cu₅Fe_0.94S₄ composition achieved a maximum dimensionless figure of merit of ZT = 0.61 at 673 K, representing a performance enhancement of approximately 30–70% compared with the stoichiometric composition (ZT = 0.36 at 673 K and 0.47 at 723 K). Full article

Robotic peach harvesting represents a pivotal strategy for reducing labor costs and improving production efficiency. The fundamental prerequisite for a harvesting robot to successfully complete picking tasks is the accurate recognition of fruit growth posture subsequent to target identification. This study proposes a novel methodology for peach growth posture recognition by integrating an enhanced YOLOv8 algorithm with the RTMpose keypoint detection framework. Specifically, the conventional Neck network in YOLOv8 was replaced by an Atrous Feature Pyramid Network (AFPN) to bolster multi-scale feature representation. Additionally, the Soft Non-Maximum Suppression (Soft-NMS) algorithm was implemented to suppress redundant detections. The RTMpose model was further employed to locate critical morphological landmarks, including the stem and apex, to facilitate precise growth posture recognition. Experimental results indicated that the refined YOLOv8 model attained precision, recall, and mean average precision (mAP) of 98.62%, 96.3%, and 98.01%, respectively, surpassing the baseline model by 8.5%, 6.2%, and 3.0%. The overall accuracy for growth posture recognition achieved 89.60%. This integrated approach enables robust peach detection and reliable posture recognition, thereby providing actionable guidance for the end-effector of an autonomous harvesting robot. Full article

Oriented object detection in remote sensing images rapidly evolves as a pivotal technique, driving transformative advancements across geospatial analytics, intelligent transportation systems, and urban infrastructure planning. However, the inherent characteristics of remote sensing objects, including complex background interference, multi-scale variations, and high-density distribution, pose critical challenges to balance detection accuracy and computational efficiency. This paper presents an anchor-free framework that eliminates the intrinsic constraints of anchor-based detectors, specifically the positive–negative sample imbalance and the computationally expensive non-maximum suppression (NMS) process. By effectively integrating adaptive kernel module with boundary refinement network, we achieved lightweight and efficient detection. Our method adaptively generates convolutional kernels tailored for multi-scale objects to extract discriminative features, while utilizing a boundary refinement network to precisely capture oriented bounding boxes. Experiments were carried out on the widely recognized HRSC2016 and DOTA datasets for the oriented bounding box (OBB) task. The proposed approach achieves 90.13% mAP (VOC07 metric) on HRSC2016 with 61.60 M parameters and 158.84 GFLOPS. For the DOTA benchmark, we attain 75.84% mAP with 45.96 M parameters and 131.39 GFLOPs. Our work highlights a lightweight yet powerful architecture that effectively balances accuracy and efficiency, making it particularly suitable for resource-constrained edge platforms. Full article

This study presents a geometry-based post-processing framework developed to refine deep-learning detections of tornado-damaged trees. The YOLO11-based instance segmentation framework served as the baseline, but its predictions often included multiple masks for a single tree or incomplete fragments of the same trunk, particularly in dense canopy areas or within tiled orthomosaics. Overlapping masks led to duplicated predictions of the same tree, while fragmentation broke a single fallen trunk into disconnected parts. Both issues reduced the accuracy of tree-count estimates and weakened orientation analysis, two factors that are critical for treefall methods. To resolve these problems, a Shape-Aware Non-Maximum Suppression (SA-NMS) procedure was introduced. The method evaluated each mask’s collinearity and, based on its geometric condition, decided whether segments should be merged, separated, or suppressed. A spatial assessment then aggregated prediction vectors within a defined Region of Interest (ROI), reconnecting trunks that were divided by obstacles or tile boundaries. The proposed method, applied to high-resolution orthomosaics from the December 2021 Land Between the Lakes tornado, achieved 76.4% and 77.1% instance-level orientation agreement accuracy in two validation zones. Full article

The rational design of highly efficient bifunctional SAPO-11 catalysts for hydroisomerization of n-C₁₆ requires unprecedented control over both acidic properties and diffusion characteristics. This work systematically investigates the influence of the SiO₂/Al₂O₃ molar ratio (0.1–0.4) in the initial gel on the physicochemical and catalytic properties of SAPO-11. Using a combination of characterization techniques (XRD, SEM, TEM-SAED, ²⁹Si MAS NMR, and IR-Py), it was established that this parameter serves as a simple tool for crystal engineering. The concentration of Brønsted acid sites and the external surface area demonstrate a non-linear dependency, reaching their maximum at SiO₂/Al₂O₃ = 0.3. Further increase in silicon content reduces both crystallinity and acidity due to the transition to the dominant SM2 + SM3 incorporation mechanism and the formation of silicon islands. Notably, varying the SiO₂/Al₂O₃ ratio enables control over crystal morphology—progressing systematically from truncated cones (SiO₂/Al₂O₃ = 0.1) to flat prismatic platelets (SiO₂/Al₂O₃ = 0.2) and ultimately hierarchical spherical aggregates (SiO₂/Al₂O₃ = 0.4). In n-C₁₆ hydroisomerization, the Pt/SAPO-11(0.2) catalyst demonstrated the highest yield of i-C₁₆ compared to other samples reaching 81%. The platelet morphology ensures a minimal diffusion path (<100 nm), effectively suppressing secondary hydrocracking. This finding underscores that morphology optimization is more critical than maximizing acidity for achieving high selectivity in the context of n-C₁₆ hydroisomerization over Pt/SAPO-11. Full article

Underwater debris poses a significant threat to marine ecosystems, fisheries, and the tourism industry, necessitating the development of automated vision-based detection systems. Although recent studies have sought to enhance detection performance through underwater image enhancement, improvements in visual quality do not necessarily translate into higher detection accuracy and may, in some cases, degrade performance. To address this discrepancy between perceptual quality and detection reliability, we propose DiCAF, a dual-input co-attention fusion network built upon the latest You Only Look Once v11 detector. The proposed architecture processes both original and enhanced images in parallel and fuses their complementary features through a co-attention module, thereby improving detection stability and consistency. To mitigate high-frequency noise amplified during the enhancement process, a lightweight Gaussian filter is applied as a post-processing step, enhancing robustness against speckle noise commonly introduced by suspended particles in underwater environments. Furthermore, DiCAF incorporates a non-maximum suppression (NMS)-based ensemble that integrates detection outputs from three branches—original, enhanced, and fused—enabling complementary detection of objects missed by individual models and maximizing overall detection performance. Experimental results demonstrate that the proposed single-model DiCAF with Gaussian post-processing achieves an AP@0.5 of 0.87 and an AP@0.5:0.95 of 0.71 on a marine trash dataset. With the NMS-based ensemble, performance improves to 0.91 and 0.75, respectively. Under artificially injected speckle noise conditions, the proposed method maintains superior robustness, achieving an AP@0.5 of 0.62 and consistently outperforming conventional enhancement-based models. Full article

The employment of linear features to enhance the positioning precision and robustness of point-based VIO (visual-inertial odometry) has attracted mounting attention, especially for UAV (unmanned aerial vehicle) applications where reliable 6-DoF pose estimation is critical for autonomous navigation, mission execution, and safety. This paper presents GPLVINS—GNSS (global navigation satellite system)-point-line-visual-inertial navigation system—a UAV-tailored enhancement of the nonlinear optimization-based GVINS (GNSS-visual-inertial navigation system). Unlike GVINS, which struggles with feature extraction in weak-texture environments and depends entirely on point features, GPLVINS innovatively integrates line features into its state optimization framework to enhance robustness and accuracy. While existing studies adopt the LSD (line segment detector) algorithm for line feature extraction, this approach often generates numerous short line segments in real-world scenes. Such an outcome not only increases computational costs but also degrades pose estimation performance. In order to address this issue, the present study proposes an NMS (non-maximum suppression) strategy for the refinement of LSD. The line reprojection residual is then formulated as the distance between point and line, which is incorporated into the nonlinear optimization process. Experimental validations on open-source datasets and self-collected UAV datasets across indoor, outdoor, and indoor–outdoor transition scenarios demonstrate that GPLVINS exhibits superior positioning performance and enhanced robustness for UAVs in environments with feature degradation or drastic lighting intensity variations. Full article

Detecting corroded metal fittings in UAV-based transmission line inspections is challenging due to the small object size and environmental interference, causing high false and missed detection rates. To address these, this paper proposes a novel knowledge-distilled lightweight YOLO model, integrating a densely-connected convolutional network and spatial pixel-aware self-attention mechanism in the teacher model training stage to enhance feature transfer and structured feature utilization for reducing environmental interference, while employing the lightweight MobileNet as the feature extractor in the student model training stage and optimizing candidate box migration via the teacher model’s efficient intersection-over-union non-maximum suppression (EIoU-NMS). This model overcomes the challenges of small-object fitting detection in complex environments, improving fault identification accuracy and reducing manual inspection costs and missed detection risks, while its lightweight design enables rapid deployment and real-time detection on UAV terminals, providing a reliable technical solution for unmanned smart grid operation. Experimental results on actual UAV inspection images demonstrate that the model significantly enhances detection accuracy, reduces false and missed detections, and achieves faster speeds with substantially fewer parameters, highlighting its outstanding effectiveness and practicality in power system maintenance scenarios. Full article

Reliable differentiation of crops and weeds is essential for precision agriculture, where real-time detection can minimize chemical inputs and support site-specific interventions. This study presents the large-scale and systematic benchmark of 19 YOLO-family variants, spanning YOLOv3 through YOLOv11, for cotton–weed detection using the Cotton–8 dataset. The dataset comprises 4440 annotated field images with five categories: broadleaf weeds, grass weeds, and three growth stages of cotton. All models were trained under a standardized protocol with COCO-pretrained weights, fixed seeds, and Ultralytics implementations to ensure reproducibility and fairness. Inference was conducted with a confidence threshold of 0.25 and a non-maximum suppression (NMS) IoU threshold of 0.45, with test-time augmentation (TTA) disabled. Evaluation employed precision, recall, mAP@0.5, and mAP@0.5:0.95, along with inference latency and parameter counts to capture accuracy–efficiency trade-offs. Results show that larger models, such as YOLO11x, achieved the best detection accuracy (mAP@0.5 = 81.5%), whereas lightweight models like YOLOv8n and YOLOv9t offered the fastest inference ( 27 msper image) but with reduced accuracy. Across classes, cotton growth stages were detected reliably, but broadleaf and grass weeds remained challenging, especially under stricter localization thresholds. These findings highlight that the key bottleneck lies in small-object detection and precise localization rather than architectural design. By providing the first direct comparison across successive YOLO generations for weed detection in cotton, this work offers a practical reference for researchers and practitioners selecting models for real-world, resource-constrained cotton–weed management. Full article

This paper presents an orthogonal time–frequency space (OTFS)-based integrated sensing and communication (ISAC) framework for vehicular-to-base-station (V2B) scenarios, where a synthetic road environment models vehicular mobility and multipath propagation with explicit ground truth. In the sensing stage, OTFS probing signals with Gray-coded quadrature amplitude modulation (QAM) are processed via inverse symplectic finite Fourier transform (ISFFT) and cyclic prefix orthogonal frequency-division multiplexing (CP-OFDM). The receiver applies cyclic prefix (CP) removal, fast Fourier transform (FFT), and symplectic finite Fourier transform (SFFT) to extract delay–Doppler (DD) responses. Channel estimation uses time–frequency least squares (TF-LS), robust background suppression, constant false alarm rate (CFAR) detection, and non-maximum suppression (NMS), yielding Precision = 0.79, Recall = 0.84, and F1 = 0.82. Communication decoding employs per-bin least squares, minimum mean-squared error (MMSE) equalization, and Gray-mapped QAM demapping. Across ten frames at 20 dB SNR, the system decoded $1.887\times {10}^8$ bits with $1.575\times {10}^5$ errors, producing a bit error rate (BER) of $8.34\times {10}^{-4}$. Error vector magnitude (EVM) analysis reports mean = 0.30%, median = 0.06%, confirming constellation stability. Random Forest (RF) and imbalanced RF (IRF) classifiers trained on augmented DD payloads achieve Precision = 0.94, Recall = 0.87, and F1 = 0.92. Results validate OTFS-ISAC as a robust framework for V2B communication and sensing. Full article

Wide-bandgap (WBG) perovskite solar cells (PSCs) are critical for high-efficiency tandem photovoltaic devices, but their practical application is severely limited by phase separation and poor film quality. To address these challenges, this study proposes a dual-additive passivation strategy using potassium thiocyanate (KSCN) and potassium chloride (KCl) to synergistically optimize the crystallinity and defect state of WBG perovskite films. The selection of KSCN/KCl is based on their complementary functionalities: K⁺ ions occupy lattice vacancies to suppress ion migration, Cl⁻ ions promote oriented crystal growth, and SCN⁻ ions passivate surface defects via Lewis acid-base interactions. A series of KSCN/KCl concentrations (relative to Pb) were tested, and the effects of dual additives on film properties and device performance were systematically characterized using scanning electron microscopy (SEM), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS), photoluminescence (PL), space-charge-limited current (SCLC), current-voltage (J-V), and external quantum efficiency (EQE) measurements. Results show that the dual additives significantly enhance film crystallinity (average grain size increased by 27.0% vs. control), reduce surface roughness (from 86.50 nm to 24.06 nm), and passivate defects-suppressing non-radiative recombination and increasing electrical conductivity. For WBG PSCs, the champion device with KSCN (0.5 mol%) + KCl (1 mol%) exhibits a power conversion efficiency (PCE) of 16.85%, representing a 19.4% improvement over the control (14.11%), along with enhanced open-circuit voltage (Voc: +2.8%), short-circuit current density (Jsc: +6.7%), and fill factor (FF: +8.9%). Maximum power point (MPP) tracking confirms superior operational stability under illumination. This dual-inorganic-additive strategy provides a generalizable approach for the rational design of stable, high-efficiency WBG perovskite films. Full article