Search Results (1,160)

To address the issues of difficult heterogeneous image registration and low segmentation accuracy caused by the severe lack of illumination and significant modal differences in concrete cracks in extremely dark environments, this paper proposes a two-stage processing framework of registration–fusion first, and decoupling–segmentation later. In the registration and fusion stage, a registration algorithm based on morphological priors and multi-level quadtree spatial constraints is designed. This approach transforms the problem from pixel grayscale matching to spatial topological matching, achieving a feature fusion of high infrared saliency and high visible light sharpness. In the segmentation stage, a Latent Frequency-Decoupled Topological Network (LFDT-Net) is proposed. It utilizes Discrete Wavelet Transform (DWT) to achieve high-fidelity frequency decoupling of the low-frequency infrared backbone and the high-frequency visible light edges. Furthermore, a Cross-Frequency Guidance Module is utilized to eliminate double-edged artifacts, and a skeleton-aware topological loss function is introduced to constrain the topological integrity of the cracks. Experimental results on a self-built heterogeneous multi-modal crack dataset demonstrate that the proposed method significantly outperforms existing mainstream methods in registration accuracy, fusion quality, and segmentation accuracy. Achieving a mean Intersection over Union (mIoU) of 81.7%, the method effectively suppresses background noise in dark environments and precisely restores the microscopic edges and continuous topological structures of faint cracks. Full article

The accurate and explainable prediction of carbon emissions is crucial for the efficient operation of hybrid and electrified transportation systems and their integration with energy grids. An Explainable Spatio-Temporal Graph Neural Network (EST-GNN) is proposed for highly precise CO₂ emission forecasting using Lévy Flight-guided Optuna optimization. By modelling vehicles and their operational characteristics as nodes in a dynamic graph, the proposed framework can jointly learn timing and spatial correlations while sustaining interpretability. The accuracy of the EST-GNN model is compared with models based on one-hot encoded features, SMOTE-enhanced datasets, and ensemble regressors. Using a real-world dataset of 7385 vehicle registrations with 12 predictive features experiments are conducted. When applied the EST-GNN model outperformed all baseline and traditional models achieving the highest reliability (R² = 0.98754) while solving competitive error metrics (RMSE = 6.55, MAE = 2.556). There is strong indication that reasonable machine learning (ML) models can be used accurately to confirm their suitability for resource-prevented and real-time applications, while predictable ML techniques have relatively low reliability. The optimal solution ensures scalability, robustness, and independence of the deployment environment. The distribution analysis of best performing models develops the ability of EST-GNN, which accounts for the largest proportion of best results across evaluation metrics. To achieve superior predictive accuracy, graph-based learning, explainability, and advanced hyperparameter optimization are combined. EST-GNN provides a powerful tool for analyzing fleet emission levels, making energy-aware decisions, and planning sustainable transportation, while ML models continue to be a useful complement for deployment states with high computation costs and quick responses. Full article

Accurate and real-time localization is a fundamental prerequisite for the autonomous navigation of mobile robots. LiDAR–Inertial Odometry (LIO) achieves high-precision state estimation and scene reconstruction in unknown environments by effectively fusing data from LiDAR and Inertial Measurement Units (IMU). However, conventional LIO methods typically rely solely on geometric features during point cloud registration. In complex scenarios, such as outdoor unstructured or dynamic environments, these methods are often susceptible to reduced localization accuracy due to geometric degeneration or mismatches. To address these challenges, we propose SV-LIO, A Probabilistic Adaptive Semantic Voxel Map for LiDAR–Inertial Odometry, which leverages point-wise semantic information from semantic segmentation to enhance registration accuracy and system robustness. Specifically, we construct a probabilistic adaptive semantic voxel map that extracts multi-scale spatial planes attached with semantic information. Building on this representation, we employ a semantic-guided strategy for nearest-neighbor plane association between LiDAR scans and the local map, and construct semantic-weighted point-to-plane residuals to constrain pose estimation. By jointly optimizing the IMU-propagated pose prior and semantic-guided LiDAR observation constraints, SV-LIO realizes high-precision real-time state estimation and semantic scene reconstruction. Extensive experiments on the KITTI dataset demonstrate that SV-LIO achieves significant improvements in both localization accuracy compared to state-of-the-art (SOTA) LIO methods, while also constructing semantic maps capable of providing rich environmental information. Full article

Integrating existing tree-level information into harvester operator decision-making can significantly enhance precision forest management, particularly with respect to biodiversity preservation and climate-smart adaptation. During harvester operations, a primary challenge lies in positioning the machine with sufficient accuracy in real time to relate a priori individual-tree-level reference information to the operator. We propose a lightweight procedure using tree-to-tree matching to continuously register a real-time tree map collected from a harvester (or another mobile laser scanning system) to a precomputed reference map derived from an airborne laser scanner (ALS). We assess the robustness of the method using simulated tree maps and validate its real-world performance in experiments using a LiDAR-equipped harvester performing a thinning operation in a boreal forest. In simulations, registration was found to be robust up to a moderate tree density of approximately 1700 ha⁻¹, even when using a reference map with a lower positional accuracy and higher error rates than in our harvester experiments. Using real-world data from the thinning operation, the registration method was demonstrated to successfully mitigate meter-scale positioning drifts remaining in the LiDAR-inertial trajectory. After the continuous registration procedure, the positioning error was reduced to the level of 0.5 m, constrained by the accuracy of the prior map derived from sparse ALS data with ∼5 transmissions/m². Importantly, the registration procedure was shown to update in real time (at most 20 ms update time for stands with densities of at most 2000 ha⁻¹, after an initial computational phase. Notable features of the registration procedure are its low memory consumption, fast runtime and capacity to accurately position the harvester despite LiDAR-inertial positioning drift. While these results demonstrate the potential for real-time operation, full implementation requires the development of real-time tree detection and estimation of tree attributes. Full article

Accurate prediction and optimization of assembly accuracy are critical to ensuring assembly quality and efficiency for multistage connected aero-engine rotors. To mitigate the effects of residual alignment errors induced by repeated component measurements and to avoid the formation of bowed rotors caused by conventional stacking strategies that only minimize parallel misalignment, a harmonic decomposition-based registration method is proposed to unify inconsistent measurement datums among multiple setups. Meanwhile, key assembly process parameters are considered simultaneously, including front-and-rear support concentricity, front-and-rear bearing mounting face end-face runout, rotor blade-tip runout, and rotor unbalance. Taking the discrete assembly phase angles of each rotor stage as independent variables, a multi-objective genetic algorithm is adopted to realize the assembly accuracy prediction and optimization of multistage flange-bolted rotors. The proposed method is validated using a four-stage simulated rotor assembly. Experimental results show that the harmonic decomposition-based registration method improves the average geometric prediction accuracy of rotor assembly by 1.2 percentage points, with the prediction error of geometric assembly parameters for each stage not exceeding 8.4% and the unbalance prediction error not exceeding 29.0%. Compared with random assembly, four-objective comprehensive optimization achieves significant reductions in all objectives: front-and-rear support concentricity is reduced by 66.2%, front-and-rear support shoulder end-face runout by 63.9%, blade-tip runout by 16.7%, and unbalance by 33.8%. The residual alignment error compensation method and stacking optimization strategy proposed in this study provide valuable engineering guidance for improving rotor assembly prediction accuracy and enhancing assembly reliability. Full article

Synthetic Aperture Radar (SAR) and optical image fusion technology plays a crucial role in remote sensing applications. It effectively combines the high spatial resolution and rich spectral information of optical images with the all-weather and penetrating observation advantages of SAR images, thereby significantly enhancing image interpretation accuracy and task execution capabilities. This paper systematically reviews deep learning-based fusion methods for SAR and optical images, with a particular focus on recent advances in deep learning models. Furthermore, it summarizes commonly used evaluation metrics for assessing fusion image quality, providing a basis for comparing and analyzing the performance of different methods. In addition, commonly used SAR-optical fusion datasets are briefly reviewed to highlight their roles in algorithm development and performance evaluation. Unlike conventional review articles, this paper further analyzes the guidance and supporting role of fusion algorithms from the perspective of typical and specific applications. Finally, it identifies key challenges and issues faced by current fusion methods, including data registration, model lightweight design, and multimodal feature alignment, and offers perspectives on future research directions. This review aims to provide routes and references for the development of SAR and optical image fusion technology. Full article

Reliable change detection in indoor environments remains a challenge for autonomous robotic systems using 3D LiDAR. Existing methods often require manual annotation, computationally intensive architectures, or focus on outdoor scenes. This paper presents SPICD-Net, a lightweight Siamese PointNet framework for indoor 3D change detection trained exclusively on synthetically generated anomalies, eliminating manual labeling. The framework offers three deployment-oriented contributions: a three-class Siamese formulation separating no-change, changed, and geometrically inconsistent tile pairs; a pre-FPS anomaly injection strategy that aligns synthetic training with inference-time preprocessing; and a stochastic-gated Chamfer-statistics branch that complements learned embeddings with explicit geometric cues under consumer-grade hardware constraints. Evaluated on 14 controlled simulation experiments in an indoor corridor dataset, SPICD-Net achieved aggregated Precision = 0.86, Recall = 0.82, F1-score = 0.84, and Accuracy = 0.96, with zero false positives in the no-change baseline and mean inference time of 22.4 s for a 172-tile map on a single consumer GPU. Additional robustness experiments identified registration accuracy as the main operational prerequisite. A limited real-world validation in one unseen room (four scans, 67 tiles) achieved Precision = 0.583, Recall = 1.000, and F1 = 0.737. Full article

Multiple sclerosis (MS) is an inflammatory and neurodegenerative disease. Optical coherence tomography (OCT) is a non-invasive imaging technique of the retina. The thickness of the ganglion cell–inner plexiform layer (GCIPL) obtained from an OCT image is a valuable biomarker for monitoring MS. Since the functional shape (F-shape)-based technique has proven to be an effective platform for detecting glaucoma using OCT images, in this paper, we develop an F-shape-based framework to distinguish MS subjects from healthy ones using the thickness of GCIPL. The thickness of the GCIPL layers in the macula region of OCT images in a selected region of interest (ROI) for a set of healthy and MS subjects is represented as F-shape objects, which are registered to a common template using atlas registration. The residual F-shapes, defined as the difference between the F-shape of this common template and the individual registered F-shapes, are used to train an support vector machine (SVM) classifier and subsequently to detect MS. Accuracy, sensitivity, specificity, and area under the curve (AUC) are used to evaluate and compare the classification performance of the proposed F-shape-based scheme and those of sectoral-based schemes. The proposed F-shape-based scheme is shown to significantly outperform the sectoral-based schemes. The superior performance of the proposed F-shape-based scheme can be attributed to the use of (i) a highly dense mesh formed on the ROI in the macula region, (ii) atlas registration that puts the F-shapes of all the subjects on a common platform, and (iii) residual thicknesses as input features for the classification. Full article

Accurate 3D documentation of large and complex structures is essential for long-term stability assessment, structural monitoring, and conservation planning, particularly for heritage sites exposed to environmental and anthropogenic threats. This study develops an integrated workflow combining Terrestrial Laser Scanning (TLS), Global Navigation Satellite System (GNSS), and Total Station geodetic control for large-scale, high-precision documentation. The approach was implemented at the Saqqara archaeological zone, a UNESCO World Heritage Site facing significant deterioration risks, to document four major pyramids: Djoser, Unas, Teti, and Userkaf. More than 2.1 billion georeferenced points were acquired from 16 scan positions with sub-centimeter registration errors and overall geometric accuracy better than ±1 cm. From these datasets, detailed mesh models, orthoimages, Digital Elevation Models (DEMs), contour maps, and 2D plans were derived. These enabled quantitative analyses of height loss and volumetric change, indicating severe structural degradation in Unas (~53%), Teti (~66%), and Userkaf (~63%), as well as localized deformations such as 4.2 cm displacement at Teti’s south flank. The degradation results from environmental factors and anthropogenic influences. Beyond this case study, the workflow proves that integrated TLS documentation can be applied to large and complex structures, supporting deformation monitoring, stability assessment, and digital twin development. Full article

In automotive Computer-Aided Engineering (CAE), the fidelity of high-quality shell element meshes is fundamentally governed by the accuracy of mid-surface geometry extraction. Conventional manual extraction for complex automotive plastic components is labor-intensive, error-prone, and often compromises mesh quality. To address these issues, this paper proposes an automated mid-surface mesh reconstruction method based on point cloud registration, establishing an integrated framework comprising “Multimodal Registration—Displacement Binding—Surface Correction.” Using a source part with an ideal mid-surface as a template, the method integrates Random Sample Consensus (RANSAC) and Iterative Closest Point (ICP) for rigid registration and Coherent Point Drift (CPD) for non-rigid registration to achieve high-precision alignment between the target and source outer-surface point clouds. Subsequently, a K-Nearest Neighbor (K-NN) search-based displacement binding mechanism smoothly transfers the outer-surface displacement field to the source mid-surface point cloud. Following position correction and surface smoothing, a complete and high-quality target mid-surface mesh is generated. Experimental results on typical plastic snap-fit components demonstrate that the normal projection error between the generated mid-surface and the manually refined “gold standard” mesh is less than 0.05 mm. The processing time per component is approximately 38 s, representing an efficiency improvement of over 73% compared to manual extraction using commercial CAE software. This method effectively mitigates common issues such as mid-surface distortion and feature loss, offering a high-precision, fully automated solution for automotive CAE pre-processing. Full article

Noise disturbances can cause conflicts in several areas, such as residences, civil constructions, highways, subways, and airports, measured by different scales of acoustic comfort for community well-being evaluation. These disturbances also have signatures such as frequency, amplitude, and temporal patterns to compare acoustic comfort with real-time parameters. In addition, acoustic sensors should be chosen based on accuracy, price, and calibration method, and acoustic insulation should be applied with the aim of achieving reliable measurements in indoor and outdoor environments for sustainable urban living. In some situations, the lack of noise control can lead to several human disorders, from hearing loss to cardiovascular complications. Therefore, legislation and regulation should be carefully studied and applied to achieve an equilibrium between energy-efficient and healthy building designs in entertainment, work, and rest activities with measured parameters visualized through the design of interface tools that should enable the collection and organization of sound data, with proper presentation for the final user. Finally, intellectual property registrations bring recent industrial applications with aspects of noise mitigation. All these features constitute noise disturbance mitigation in a multi-dimensional integration framework of technology, health, and law to improve the quality of life in human-centric environments. Full article

Background: Accurate digital impressions are crucial for the long-term success of implant-supported prostheses, with scan bodies playing a pivotal role in transferring the implant position into the virtual model. Recent work has focused on PEEK (polyether-etherketone) scan bodies because their optical behavior may facilitate intraoral scanning; however, the breadth and quality of supporting evidence remain unclear. Methods: This scoping review followed PRISMA-ScR reporting guidelines and was registered in the Open Science Framework (OSF; Registration DOI 10.17605/OSF.IO/CU3V8). Pub-Med/MEDLINE, Embase, and Scopus were searched through September 2025. Eligible designs included in vitro studies, randomized trials, observational studies, and technical reports evaluating PEEK scan bodies in implant dentistry. Screening and data extraction were performed in duplicate, and findings were synthesized descriptively. Results: The search identified 227 records, and after screening, 31 studies met the inclusion criteria. Most studies were in vitro, with limited clinical evidence, and only one prospective clinical study was identified. Outcomes commonly addressed trueness, precision, scan time, and handling. Comparators varied (e.g., titanium, resin; splinted vs. unsplinted), and the results on accuracy were heterogeneous, with deviations typically within clinically acceptable limits (<100 µm). Conclusions: PEEK scan bodies are applicable for digital implant impressions. Clinical data are sparse, though, and methods vary. Controlled clinical studies are necessary to confirm the accuracy, reliability, and indications of this approach compared to titanium ISBs. Full article

Artificial intelligence (AI) is increasingly transforming spine surgery, with expanding applications in diagnostics, intraoperative imaging, and surgical navigation. As the field advances toward greater precision and safety, machine learning (ML) and deep learning technologies are being integrated to augment surgeon expertise and optimize operative workflows. In particular, AI-driven innovations in image acquisition and navigation are reshaping intraoperative decision-making and technical execution. This narrative review provides an overview of AI applications relevant to intraoperative imaging and navigation in spine surgery. We begin by defining key concepts in AI, ML, and deep learning and briefly outline the historical evolution of AI within spine practice. We then examine current capabilities in image recognition and automated pathology detection, emphasizing their clinical relevance. Given the central role of imaging accuracy in modern navigation-assisted procedures, we review conventional acquisition platforms, including intraoperative computed tomography (CT) systems (e.g., O-arm, GE, Airo), surface-based registration to preoperative CT (Stryker, Medtronic), and optical surface mapping technologies (e.g., 7D Surgical). Emerging AI-optimized advancements are subsequently discussed, including low-dose intraoperative CT protocols, expanded scan windows, metal artifact reduction algorithms, integration of 2D fluoroscopy with preoperative CT datasets, and 3D reconstruction derived from 2D imaging. These developments aim to improve image quality, reduce radiation exposure, and enhance navigational accuracy. By synthesizing current evidence and technological progress, this review highlights how AI-enhanced imaging systems are redefining intraoperative spine surgery and shaping the future of precision-based care. The primary purpose of this review is to outline the applications of AI and its potential for perioperative and intraoperative optimization, including radiation exposure reduction, workflow streamlining, preoperative planning, robot-assisted surgery, and navigation. The secondary purpose is to define AI, machine learning, and deep learning within the medical context, describe image and pathology recognition, and provide a historical overview of AI in orthopedic spine surgery. Full article

Children are often underserved by adult-oriented oral medicines, leading to off-label use and dosage-form manipulation that may compromise dosing accuracy. This review summarises recent advances in paediatric orodispersible tablets (ODTs), focusing on manufacturing technologies, superdisintegrants, taste masking, and in vitro disintegration testing. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidance and a protocol registered with the International Platform of Registered Systematic Review and Meta-analysis Protocols (registration number INPLASY2025110022), we searched PubMed, EMBASE, MEDLINE, Scopus, and Google Scholar for experimental studies on paediatric-relevant ODT formulation and evaluation. Two reviewers screened studies and extracted data on manufacturing methods, excipients, disintegration/dissolution testing, and key outcomes. Risk of bias was assessed using a six-domain framework. Overall, 65 studies met the inclusion criteria for this review. Direct compression was the dominant method, with freeze-drying, sublimation, spray-drying, nanoparticle-in-tablet systems, and semi-solid extrusion/3D printing also reported. Crospovidone, croscarmellose sodium, and sodium starch glycolate were the most common superdisintegrants, while natural and co-processed disintegrants showed promise as cost-effective alternatives. Disintegration was usually assessed using pharmacopoeial methods, with some modified set-ups to better simulate oral conditions. Paediatric ODT development is advancing rapidly. Broader translation requires harmonised disintegration testing, age-stratified acceptability reporting, and GMP-ready workflows, alongside benchmarking of superdisintegrants and attention to dose flexibility, packaging, and affordability. 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