Search Results (1,385)

Precise dimensional conformity of precast concrete members is critical for structural performance and on-site assembly accuracy, yet conventional manual inspection remains labor-intensive and unable to scale with modern production-line throughput. Existing scan-vs-BIM approaches address geometric verification in principle but are constrained by manual registration dependencies, the absence of machine-readable IFC-linked tolerance criteria, and limited validation under real factory yard conditions. This study presents a production-scale automated shape quality control (SQC) framework that closes all three gaps simultaneously. A purpose-designed two-point target device enables fully automated, repeatable registration seed-point extraction. A formal IFC property-set-linked rule engine architecture—comprising entity extraction, deviation computation, rule interpretation, and pass/fail decision stages—replaces ad hoc script-based tolerance checking with an interoperable, auditable compliance pipeline. Factory-scale validation on precast arch segments (n = 10) and wall panels (n = 12) achieved registration RMSE of 1.25–1.95 mm, pass rates exceeding 91%, and a 37.1% reduction in inspection time versus manual methods (95% CI: 34.5–39.6%; p < 0.001; Cohen’s d = 3.89). Repeatability testing yielded ICC = 0.971 and Bland–Altman limits of agreement of [−0.45, +1.07] mm. The framework represents a substantive step toward fully digital, production-integrated quality management for industrialized precast construction. Full article

With the increasing demand for low-carbon energy, automated defect detection using unmanned aerial vehicle (UAV)-based thermal inspection has become essential for maintaining the reliability of photovoltaic systems. However, existing methods still suffer from low-contrast thermal imagery, large-scale variations of defects, and subtle thermal anomalies. To address these challenges, this study proposes Grouped-Hypergraph-Modulation DEIM (GHM-DEIM), a robust end-to-end detection framework based on an improved DEIM architecture. Specifically, a grouped multi-scale aggregation attention network is introduced to enhance global thermal perception and recover discriminative features from blurred backgrounds. In addition, an enhanced encoder incorporating a hypergraph-based context encoding mechanism is designed to model high-order non-local relationships and improve feature representation across different defect scales. Furthermore, a modulation fusion module is employed to adaptively refine multi-scale feature responses and suppress environmental noise interference. Extensive experiments conducted on the ThermoSolar-PV and PV-HSD-2025 datasets demonstrate that the proposed method consistently outperforms state-of-the-art detectors, achieving mAP@50 values of 88.6% and 74.2%, respectively, with improvements of 4.7% and 2.9% over the baseline. These results demonstrate the effectiveness and robustness of GHM-DEIM for UAV-based PV thermal defect inspection. Full article

Precise segmentation of weld defects offers clearer advantages over simple localization in the modern manufacturing, which can improve reliability in high-density weld zones. In order to improve the segmentation mean Average Precision (mAP) and inference speed, we propose a hybrid WFD-YOLO that employs a wavelet-based frequency down-sampling (WFD) module, a lightweight channel-thresholding attention (CTA), and a dedicated P2 small-object layer for weld defect segmentation, where the WFD module is used for suppressing aliasing while preserving low-frequency structural details, the CTA module is used for reducing the impact of background and noise during defect segmentation, and the dedicated P2 small-object layer is used for giving explicit sensitivity to minor defects like porosity and spatters. The upgraded model improves precision by 3.5%, recall by 7.8%, mAP@0.5 by 7.3%, and mAP@0.5–0.95 by 2.7% over the original YOLO11n-seg, while achieving an inference speed of 303 FPS. The segmentation mAP for porosity and spatters, which represent the most challenging defect categories, is improved by 16% and 15.8%, respectively. These performance gains position the hybrid WFD-YOLO network as an industry-deployable tool for safety-critical weld inspection, compatible with high-speed automated welding production lines. Full article

The Draw-a-Person (DAP) test has been a widely used practical instrument in psychological and developmental assessments to measure children’s cognitive development via human-figure drawings. Unfortunately, its traditional scoring process relies on manual inspections conducted by professionals, which is highly subjective and difficult to scale. In order to resolve these problems, this paper presents a hybrid approach that leverages deep-learning-based visual recognition and rule-based structural reasoning for automated evaluation of children’s DAP drawings. Specifically, the model assesses drawings based on 40 features, including anatomical parts, appearance-derived attributes, and high-level structural-drawing relations. A multi-label CNN built upon the ResNet-50 model predicts the visibles, and rule-based geometrical reasoning is adopted to infer structures, including attachments, proportions, symmetries, and placements. These two aspects are combined into a single hybrid representation yielding interpretable feature scoring consistent with developmental-evaluation standards. The proposed framework performs very well across multiple feature analyses, achieving a Micro-F1 of 95.32% and Macro-F1 of 91.72% on the test dataset, and demonstrating robust multi-label classification ability even on rare features. It provides a promising method for evaluating Draw-a-Person drawings, while offering reliable capabilities for feature analysis and scoring with accurate anatomical feature detection and reasonable structural and higher-level feature detection despite the challenging diversity of children’s drawing styles. The enforced rule-based structural reasoning improves interpretability and objectivity. Our future work includes extending the framework to cover further detailed DAP features. Full article

Potato sorting in post-harvest processing relies heavily on manual visual inspection, which is physically demanding, subjective, and insufficiently scalable for modern packing lines. This study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection. A controlled imaging platform was constructed using commodity hardware, and a dataset of 19,805 manually annotated instances across 1361 images was collected from two geographically distinct farm locations in Slovenia. A systematic benchmark of 25 model configurations spanning five YOLO architecture families—YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLO26—was conducted across three practical quality classes (Edible, Feed, Rotten) using a strict cross-location evaluation protocol in which models were trained on one location and tested on a completely unseen second location. All models achieved strong in-distribution performance (F1 ≥ 0.906), but showed considerable variation under cross-location conditions, with external F1 ranging from 0.792 to 0.918. The yolo26_l configuration achieved the best cross-location performance (F1 = 0.918, mAP@0.5:0.95 = 0.816, ΔF1 = 0.029), demonstrating that transferable representations are achievable under a standard supervised training protocol. Per-class analysis identified feed detection as the primary generalization bottleneck. The results confirm that affordable RGB-based sorting systems are technically feasible and highlight cross-location evaluation as an essential protocol for assessing real-world deployment readiness. Full article

This study proposes a precision detection method that integrates Canny operator threshold optimization with Zernike moments to address the issue of low measurement accuracy associated with the manual inspection of circular holes in sheet metal during industrial testing. A complete automated measurement system was developed based on the MATLAB platform. First, adaptive median filtering is employed for image preprocessing, with superior performance in noise suppression and detail preservation validated through Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) metrics. Subsequently, Otsu’s thresholding method achieves robust segmentation between target and background, laying the foundation for subsequent edge detection. An innovative adaptive threshold selection strategy for the Canny operator based on composite weight scoring was proposed during edge detection, significantly enhancing circular hole edges’ continuity and geometric integrity. Finally, by integrating Zernike moments with sub-pixel localization technology, ultra-precise localization of edge points at the sub-pixel level was achieved. Experimental results demonstrate that the system achieves a measurement repeatability standard deviation of less than 0.02 mm and controls the absolute error within ±0.05 mm.This performance surpasses the ±0.3 mm precision requirement in industrial settings, providing an effective solution for automated quality inspection of sheet metal hole manufacturing. Full article

Accurate surface defect classification is a critical requirement in structural health monitoring and infrastructure inspection, where defects, including cracks, spalling, delamination and noncrack regions, often appear with low-contrast and complex background textures. Motivated by the need for a robust and discriminative framework that can enhance defect visibility and focus learning on damage-critical regions, this research proposes a novel damage-aware DenseNet-201 (DA-DenseNet-201) model for surface defect classification. As a critical novelty, a damage-aware adaptive contrast-limited adaptive histogram equalisation (DAC) filtering strategy is introduced as a preprocessing stage. The proposed DAC filter dynamically adjusts contrast enhancement parameters based on damage indicators, selectively amplifying crack edges and defect textures while preserving healthy surface regions and suppressing noise. Building on this method, enhanced images are processed using a pretrained DenseNet-201 backbone, retaining the benefits of dense feature propagation and efficient gradient flow. To strengthen the discriminative learning of DA-DenseNet-201 further, an attention refinement block is integrated into the network, combining channel attention to emphasise defect-relevant feature responses and spatial attention to localise damage regions accurately. In addition, a multiscale feature fusion mechanism aggregates feature maps from multiple dense blocks to capture fine-grained crack patterns, texture-level degradation and high-level semantic damage information. Extensive experiments conducted on surface defect datasets demonstrate its effectiveness, achieving a superior classification accuracy of 98.93%, along with notable improvements in sensitivity, specificity and the intersection over union compared with state-of-the-art models. These results confirm that the proposed DA-DenseNet-201 provides a reliable and high-performance solution for automated surface defect classification. Full article

Accurate positioning is essential for inspection robots in caged chicken houses, where long straight corridors, sparse textures, and repetitive structures challenge conventional methods. This paper proposes CVIWM (Coupled Visual-Inertial-Wheel Odometry with Markers), a tightly coupled state estimation method that fuses visual, inertial measurement unit (IMU), wheel odometry (WO), and fiducial marker observations within a factor graph optimization framework. Wheel odometry preintegration suppresses IMU horizontal drift and provides absolute scale, while sparse AprilTag markers (10 m spacing) periodically reset accumulated errors. Experiments in an 80 m corridor of a commercial caged chicken house at 0.116 m/s and 0.232 m/s showed that CVIWM achieves average positioning errors of 2.402 cm and 3.253 cm. This high precision ensured reliable image acquisition (image shift $<83$ pixels), enabling 95.7% dead hen detection and 98.9% egg detection accuracy. CVIWM offers a low-cost, easy-to-deploy, high-accuracy solution for automated poultry house inspection, supporting smart livestock farming. Full article

Automated visual inspection of photovoltaic (PV) cells is an important component of solar-module quality assurance. However, adapting modern pre-trained vision backbones to PV defect classification remains challenging because full fine-tuning requires substantial memory, naturally imbalanced datasets can reduce sensitivity to rare defect classes, and edge-oriented inspection workflows impose computational constraints. Parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA) and Quantized LoRA (QLoRA), have been widely studied in natural language processing, but their use for PV defect classification remains underexplored. This study presents a controlled benchmark of LoRA and QLoRA against full fine-tuning for PV cell defect classification. Four adaptation strategies—full fine-tuning, LoRA with rank 8, LoRA with rank 16, and 4-bit QLoRA with rank 16—are evaluated using a ConvNeXt-Tiny backbone on a 17,377-image polycrystalline PV cell electroluminescence dataset referred to as POLY, covering five classes: intact, cracked, broken, surface-diffuse, and surface-point. The natural 6.7× class imbalance is preserved without synthetic resampling, and a group-aware StratifiedGroupKFold protocol based on available cell or panel-image identifiers is used to reduce identifiable leakage across folds. All PEFT variants slightly outperform full fine-tuning in macro-F1 while training 26–52× fewer parameters. QLoRA_r16 achieves the highest macro-F1 score of 79.92 ± 0.75%, compared with 78.26 ± 0.94% for full fine-tuning, while training the same number of parameters as LoRA_r16 (1.060 M; 3.67% of the adapted model). QLoRA_r16 also improves F1 on the intact (+4.75 points) and surface-diffuse (+2.62 points) classes relative to full fine-tuning. This class-wise pattern suggests that quantized low-rank adaptation may influence minority and visually ambiguous categories; however, the present experiments do not isolate the independent effect of NF4 quantization from adapter rank, batch size, or optimization dynamics. Under the training configuration used, QLoRA_r16 records the lowest observed peak training GPU memory, approximately 30% below full fine-tuning (1727 MB versus 2478 MB). Because QLoRA_r16 was trained with batch size 16 whereas the other methods used batch size 32, this reduction should be interpreted as an end-to-end configuration effect rather than as the isolated effect of 4-bit quantization. Overall, the results indicate that PEFT is a promising and resource-efficient alternative to full fine-tuning for PV defect classification, although batch-matched memory experiments, direct embedded-device profiling, and cross-dataset validation remain necessary before making deployment-level claims. Full article

We present a 3D laser-scanning method for the fast, accurate dimensional inspection of large high-speed-rail precast box girders. The pipeline uses low-pass filtering plus sequential registration to suppress noise, and voxel filtering with curvature-aware enhancement to reduce point cloud size by 3–5× while preserving key geometry. Reconstruction employs K-nearest-neighbors and PCA to detect boundaries and curvature jumps, B-spline fitting with moving least squares for surface completion, and CSS corner detection to extract key dimensions at millimeter precision. Field tests report absolute errors ≤ 2.0 mm versus manual measurement, validating the method for automated, digital acceptance. Full article

Industrial integrated circuit (IC) chip defect inspection is hindered by diverse topologies, micro-scale structures, and the insufficient precision of traditional vision paradigms. While the Segment Anything Model (SAM) offers strong zero-shot capabilities, its heavy reliance on manual prompts and lack of domain adaptability limit its viability in automated production lines. This paper proposes IC-SAM, a highly automated framework tailored for electronic manufacturing quality control. IC-SAM synergistically integrates three core modules: Process Prior Knowledge (PPK), which embeds semiconductor domain constraints to suppress background noise; Self-Driven Semantic Prompting, which leverages CLIP to align visual features with process descriptions for autonomous target localization; and Global Feature Fusion (GFF), which optimizes boundary localization through multi-scale interaction. Extensive experiments demonstrate that IC-SAM outperforms baseline models by approximately 15% in both mIoU and mBIoU across SIC, CIC, and IGBT datasets. The framework achieves 9.6 FPS under the tested 1024 × 1024 input setting while introducing only 2.3 M learnable parameters, indicating a parameter-efficient adaptation strategy with quantified computational cost for precision IC inspection. Full article

Stainless steel pipes are critical components in industrial systems such as oil and gas transportation and nuclear power cooling. Surface defects can severely degrade their mechanical performance and operational safety. However, existing inspection methods still face challenges including difficult feature extraction, strong reflection interference, and limited accuracy in small-target detection. To address these issues, this paper proposes an improved detection algorithm termed YOLOv8s-BISW (incorporating BiFPN, SGE attention, and WIoU loss), which introduces multidimensional optimizations based on the YOLOv8s baseline. First, an image enhancement module combining Gamma correction and Contrast Limited Adaptive Histogram Equalization (CLAHE) is designed to mitigate uneven illumination and blurred defect imaging. Second, a Bidirectional Feature Pyramid Network (BiFPN) structure is introduced to strengthen multi-scale feature fusion and improve adaptability to defects of different sizes. Meanwhile, a Spatial Group-wise Enhance (SGE) attention module is embedded into the backbone to enhance defect feature representation while suppressing background interference. Furthermore, the Wise Intersection over Union (WIoU) loss function replaces Complete IoU (CIoU) to improve bounding box regression for irregular defects. Experimental results show that the proposed model achieves an mAP of 0.979 on a self-constructed Stainless-steel Tube Flaw (STF) dataset. Compared with the original YOLOv8s, precision, recall, and mAP are improved by 0.007, 0.010, and 0.033, respectively, while the average detection time per image is only 3.7 ms, achieving a favorable balance between accuracy and real-time performance. Compared with mainstream algorithms such as SSD, YOLOv3, and Faster R-CNN, the proposed method demonstrates superior overall performance, providing reliable technical support for automated surface defect detection of stainless steel pipes and offering practical value for intelligent manufacturing quality control. Full article

This article discusses a novel aircraft coordination algorithm for automated vertiport operation. New applications of Innovative Air Mobility (IAM) including inspection, logistics and security UAVs, Urban Air Mobility (UAM) or Regional Air Mobility (RAM) present a coordination challenge, especially near vertiports, as large numbers of vehicles with different characteristics share the airspace, and so avoiding collisions, optimizing resource usage and operating with low human intervention is important.In this paper, this problem is addressed by proposing a new formulation of the aircraft coordination problem that makes use of a discretized airspace to detect potential conflicts and collisions between cooperative and non-cooperative aircraft in the surroundings of a vertiport. The proposed algorithm not only considers the cells traversed by the aircraft, but also the set of adjacent cells, making the algorithm more conservative and robust than other algorithms found in the literature, and achieving a 100% conflict-detection rate. A mathematical model of aircraft dynamics is employed to turn high-level flight plans into detailed aircraft trajectories, using those trajectories to detect potential collisions. The deconfliction problem is formulated as a mixed-integer optimization program that computes orders of pass for every conflict while minimizing the divergence between requested time of arrival (RTA) and estimated time of arrival (ETA). This problem is implemented in OR-Tools to be solved by means of the CP-SAT solver. The validity of the solution is tested by extensive simulation, showing tactical coordination of up to 25 aircraft landing on a vertiport. Full article

The transition toward smart grids and Industry 4.0 demands a fundamental shift in maintenance strategies, as manual inspection methods are increasingly being supplanted by automated monitoring systems. Among the advanced technologies for smart inspection, infrared imaging has advantages including non-contact operation, intuitive visualization, and predictive capabilities, which has become a cornerstone for autonomous inspection of critical power infrastructure. This review provides recent advancements in infrared imaging, with a specific focus on automated power system inspection. The discussion starts with an overview of the fundamental principles and system architectures, emphasizing the pivotal role of infrared detectors. A detailed analysis traces the technological evolution from traditional photon detectors to current uncooled microbolometers, and critically assesses emerging low-dimensional materials. The analysis highlights inherent performance trade-offs among sensitivity, operating temperature, and fabrication cost. Subsequently, the review explores advanced signal processing algorithms, such as real-time non-uniformity correction and adaptive noise suppression, which are typically implemented on FPGA platforms. Advanced optical configurations—encompassing computational imaging, lensless designs, and scattering suppression methods—are also discussed, demonstrating how their convergence enhances image fidelity and operational reliability in complex field environments. Representative application paradigms are surveyed, including drone-based transmission line inspections, patrol robots in substations, and fault diagnosis in photovoltaic plants; for each, operational efficacy and economic benefits are assessed. Despite considerable progress, several challenges persist, notably the performance–stability–cost trilemma in novel detector development, the substantial computational demands of end-to-end optimized systems, and a lack of standardization. Finally, the review outlines future research directions, such as high-performance uncooled arrays, AI-driven co-design of optics and algorithms, and the development of standardized, low-cost, intelligent inspection platforms. Full article

Ensuring the cleanliness of precision components is critical in Hard Disk Drive (HDD) manufacturing, where microscopic dust contamination on the Voice Coil Motor Assembly (VCMA) can lead to positioning errors, unstable head movement, and long-term reliability failures. However, automated inspection of such contamination remains challenging because dust particles are extremely small, visually irregular, and often appear under complex microscopic backgrounds. This study presents an explainable hybrid deep learning framework for microscopic dust inspection by integrating object detection for precise localization and image classification for defect confirmation. Three YOLO architectures, namely YOLOv5, YOLOv8, and YOLOv11, were comparatively evaluated for dust detection, while three convolutional neural network (CNN) models, ResNet50, EfficientNetB0, and MobileNetV2, were implemented using transfer learning with frozen feature extraction layers for Good (G) and Not Good (NG) image-level classification. The experimental dataset consisted of annotated microscopic VCMA images, with data augmentation applied to the training subset to mitigate limited sample size and class imbalance. Experimental results showed that YOLOv8 achieved the strongest overall aggregate detection performance, whereas YOLOv5 was selected as the preferred detector for subsequent hybrid integration because it produced fewer false positives under reflective and textured microscopic backgrounds. YOLOv11 exhibited lower detection performance in the present setting, likely due to its architectural characteristics being less suited to the limited-data and high-background-complexity conditions of this study. In the present experimental setting, YOLOv5 achieved mAP@0.5 = 0.62, precision = 0.75, and recall = 0.69. For image-level classification, EfficientNetB0 achieved the highest classification accuracy of 93.10%, with F1-score = 0.932 and AUC = 0.986. In addition, Grad-CAM visualizations demonstrated that EfficientNetB0 consistently focused on physically meaningful dust-contaminated regions, thereby enhancing the interpretability of the classification results. Overall, the proposed hybrid framework integrating YOLOv5-based localization with EfficientNetB0-based defect confirmation showed promising potential for improving inspection reliability, false-alarm control, and explainability in automated VCMA quality inspection. These findings support the feasibility of explainable deep learning for microscopic defect inspection in HDD manufacturing and suggest its potential applicability to other precision manufacturing environments. Full article