Search Results (141)

Dual-LiDAR systems are widely deployed in autonomous driving, yet extrinsic calibration remains challenging in non-overlapping field-of-view (FoV) configurations where correspondence-based methods are unreliable. We propose an engineering-oriented 2.5D calibration framework that estimates horizontal extrinsics $(x,y,\mathrm{yaw})$ via motion-guided planar alignment and then refines them using Gaussian Process Implicit Surfaces (GPIS), which provide continuous and probabilistic surface constraints from spatially disjoint scans. This design avoids calibration targets and reduces dependence on strong scene assumptions, improving robustness under noise and weak structure. Extensive high-fidelity simulation experiments demonstrate centimeter-level lateral accuracy and sub-degree yaw error, consistently outperforming representative motion-based and BEV-based baselines under both clean and noisy settings. To further assess real-world applicability, we conduct a preliminary nuScenes case study by splitting LiDAR scans into front and rear subsets to emulate a non-overlapping dual-LiDAR setup, achieving improved yaw accuracy and competitive lateral precision. Overall, the proposed method serves as a practical refinement stage for non-overlapping dual-LiDAR calibration, with a favorable balance of accuracy, robustness, and engineering feasibility. Full article

The powder-mixed electric-discharge machining (PMEDM) process has been the focus of researchers for quite some time. This method overcomes the constraints of conventional machining, viz., low material removal rate (MRR) and high surface roughness (SR) in hard-cut materials, tool failure, and a high tool wear ratio (TWR). However, to determine the optimal machining parameter levels for improving MRR, surface finish must be measured during actual experimentation using various parameter levels across different materials. It is a very costly and time-consuming process for industries. However, in the age of Industry 4.0 and artificial intelligence machine learning (AI-ML), it provides an efficient solution to real manufacturing problems when big data is available. In this study, experimentation was conducted on AISI D2 steel using the PMEDM process for SR analysis with different parameters, viz. current, voltage, cycle time (T_On), powder concentration (PC), and duty factor (DF). Moreover, machine learning models were used to predict SR values for selected parameter levels in the PMEDM process. In this research, Gaussian process regression (GPR) with a squared exponential kernel, support vector machines, and ensemble regression models were used for computational analysis. The results of this work showed that Gaussian regression, support vector machine, and ensemble regression achieved 95%, 92%, and 83% accuracy, respectively. The GPR model achieved the best predictive performance among these three models. Full article

This paper develops a unified synchronization framework for octonion-valued fractional-order neural networks (FOOVNNs) subject to mixed delays, Lévy disturbances, and topology switching. A fractional sliding surface is constructed by combining $I^{1-\mu }{e}_g$ with integral terms in powers of $|e_g|$. The controller includes a nonsingular term $-{\rho }_{2g}{s}_g^{c_2}\mathrm{sign}\left(s_g\right)$, a disturbance-compensation term $-{\widehat{\theta }}_g\mathrm{sign}\left(s_g\right)$, and a delay-feedback term $-{\lambda }_g{e}_g(t-\tau )$, while dimension-aware adaptive laws ${\phantom{,}}^C{D}_t^{\mu }{\rho }_g=k_{1g}N{\parallel s_g\parallel }^{c_2}$ and ${\phantom{,}}^C{D}_t^{\mu }{\widehat{\theta }}_g=k_{2g}N\parallel s_g\parallel$ ensure scalability with network size. Fixed-time convergence is established via a fractional stochastic Lyapunov method, and predefined-time convergence follows by a time-scaling of the control channel. Markovian switching is treated through a mode-dependent Lyapunov construction and linear matrix inequality (LMI) conditions; non-Gaussian perturbations are handled using fractional Itô tools. The architecture admits observer-based variants and is implementation-friendly. Numerical results corroborate the theory: (i) Two-Node Baseline: The fixed-time design drives ${\parallel e\left(t\right)\parallel }_1$ to $\mathcal{O}\left({10}^{-4}\right)$ by $t\approx 0.94\mathrm{s}$, while the predefined-time variant meets a user-set $T_p=0.5\mathrm{s}$ with convergence at $t\approx 0.42\mathrm{s}$. (ii) Eight-Node Scalability: Sliding surfaces settle in an $\mathcal{O}\left(1\right)$ band, and adaptive parameter means saturate well below their ceilings. (iii) Hyperspectral (Synthetic): Reconstruction under Lévy contamination achieves a competitive PSNR consistent with hypercomplex modeling and fractional learning. (iv) Switching Robustness: under four modes and twelve random switches, the error satisfies ${max}_t{\parallel e\left(t\right)\parallel }_1\le 0.15$. The results support octonion-valued, fractionally damped controllers as practical, scalable mechanisms for robust synchronization under non-Gaussian noise, delays, and time-varying topologies. Full article

Morphometric traits are closely linked to body condition, health, welfare, and productivity in livestock. In recent years, contactless 3D reconstruction technologies have been increasingly adopted to improve the accuracy and efficiency of morphometric evaluations. Conventional approaches for 3D reconstruction mainly employ Light Detection and Ranging (LiDAR) or photogrammetry. In contrast, emerging Artificial Intelligence (AI)-based methods, such as Neural Surface Reconstruction, 3D Gaussian Splatting, and Neural Radiance Fields, offer new opportunities for high-fidelity digital modeling. Smartphones’ affordability represents a cost-effective and portable platform for deploying these advanced tools, potentially supporting enhanced agricultural performance, accelerating sector digitalization, and thus reducing the urban–rural digital gap. This preliminary study assessed the viability of using smartphone-based LiDAR, photogrammetry, and AI models to obtain body measurements of Marchigiana cattle. Five morphometric traits manually collected on animals were compared with those extracted from smartphone-based 3D reconstructions. LiDAR measurements offer more consistent estimates, with relative error ranging from −1.55% to 4.28%, while photogrammetry demonstrated accuracy ranging from 0.75 to −14.56. AI-based models (NSR, 3DGS, NeRF) reported more variability between accuracy results, pointing to the need for further refinement. Overall, the results highlight the preliminary potential of portable 3D scanning technologies, particularly LiDAR-equipped smartphones, for non-invasive morphometric data collection in cattle. Full article

The application prospects of photorealistic 3D reconstruction are broad in smart cities, cultural heritage preservation, and related domains. However, existing methods face persistent challenges in balancing reconstruction accuracy, computational efficiency, and robustness, particularly in complex scenes characterized by reflective surfaces, vegetation, sparse viewpoints, or large-scale structures. In this study, an enhanced 3D Gaussian Splatting (3DGS) framework that integrates three key innovations is proposed: (i) a depth-aware regularization module that leverages metric depth priors from the pre-trained Depth-Anything V2 model, enabling geometrically informed optimization through a dynamically weighted hybrid loss; (ii) a gradient-driven adaptive densification mechanism that triggers Gaussian adjustments based on local gradient saliency, reducing redundant computation; and (iii) a neighborhood density-based floating artifact detection method that filters outliers using spatial distribution and opacity thresholds. Extensive evaluations are conducted across four diverse datasets—ranging from architectures, urban scenes, natural landscapes with water bodies, and long-range linear infrastructures. Our method achieves state-of-the-art performance in both reconstruction quality and efficiency, attaining a PSNR of 34.15 dB and SSIM of 0.9382 on medium-sized scenes, with real-time rendering speeds exceeding 170 FPS at a resolution of 1600 × 900. It demonstrates superior generalization on challenging materials such as water and foliage, while exhibiting reduced overfitting compared to baseline approaches. Ablation studies confirm the critical contributions of depth regularization and gradient-sensitive adaptation, with the latter improving training efficiency by 38% over depth supervision alone. Furthermore, we analyze the impact of input resolution and depth model selection, revealing non-trivial trade-offs between quantitative metrics and visual fidelity. While aggressive downsampling inflates PSNR and SSIM, it leads to loss of high-frequency detail; we identify 1/4–1/2 resolution scaling as an optimal balance for practical deployment. Among depth models, Vitb achieves the best reconstruction stability. Despite these advances, memory consumption remains a challenge in large-scale scenarios. Future work will focus on lightweight model design, efficient point cloud preprocessing, and dynamic memory management to enhance scalability for industrial applications. Full article

Background: Gross tumor volume (GTV) segmentation of Nasopharyngeal Carcinoma (NPC) crucially determines the precision of image-guided radiation therapy (IGRT) for NPC. Compared to other cancers, the clinical delineation of NPC is especially challenging due to its capricious infiltration of the adjacent rich tissues and bones, and it routinely requires multimodal information from CT and MRI series to identify its ambiguous tumor boundary. However, the conventional deep learning-based multimodal segmentation method suffers from limited prediction accuracy and frequently performs as well as or worse than single-modality segmentation models. The limited multimodal prediction performance indicates defective information extraction and integration from the input channels. This study aims to develop a 3D Gaussian-prompted Diffusion Model (3DG-PDM) for more clinically targeted information extraction and effective multimodal information integration, thereby facilitating more accurate and clinically interpretable GTV segmentation for NPC. Methods: We propose a 3D-Gaussian-Prompted Diffusion Model (3DGS-PDM) that operates NPC tumor contouring in multimodal clinical priors through a guided stepwise process. The proposed model contains two modules: a Gaussian Initialization Module that utilizes a 3D-Gaussian-Splatting technique to distill 3D-Gaussian representations based on clinical priors from CT, MRI-t2 and MRI-t1-contract-enhanced-fat-suppression (MRI-t1-cefs), respectively, and a Diffusion Segmentation Module that generates tumor segmentation step-by-step from the fused 3D-Gaussians prompts. We retrospectively collected data on 600 NPC patients from four hospitals through paired CT, MRI series and clinical GTV annotations, and divided that dataset into 480 training volumes and 120 testing volumes. Results: Our proposed method can achieve a mean dice similarity cofficient (DSC) of 84.29 ± 7.33, a mean average symmetric surface distance (ASSD) of 1.31 ± 0.63, and a 95th percentile of Hausdorff (HD₉₅) of 4.76 ± 1.98 on primary NPC tumor (GTVp) segmentation, and a DSC of 79.25 ± 10.01, an ASSD of 1.19 ± 0.72 and an HD₉₅ of 4.76 ± 1.71 on metastasis NPC tumor (GTVnd) segmentation. Comparative experiments further demonstrate that our method can significantly improve the multimodal segmentation performance on NPC tumors, with superior advantages over five other state-of-the-art comparative methods. Visual evaluation on the segmentation prediction process and a three-step ablation study on input channels further demonstrate the interpretability of our proposed method. Conclusions: This study proposes a performant and interpretable multimodal segmentation method for GTV of NPC, contributing greatly to precision improvement for NPC therapy treatment. Full article

This study introduces a versatile seed 3D reconstruction method that is applicable to multiple crops—including maize, wheat, and rice—and designed to overcome the inefficiency and subjectivity of manual measurements and the high costs of laser-based phenotyping. A panoramic video of the seed is captured and processed through frame sampling to extract multi-view images. Structure-from-Motion (SFM) is employed for sparse reconstruction and camera pose estimation, while 3D Gaussian Splatting (3DGS) is utilized for high-fidelity dense reconstruction, generating detailed point cloud models. The subsequent point cloud preprocessing, filtering, and segmentation enable the extraction of key phenotypic parameters, including length, width, height, surface area, and volume. The experimental evaluations demonstrated a high measurement accuracy, with coefficients of determination (R²) for length, width, and height reaching 0.9361, 0.8889, and 0.946, respectively. Moreover, the reconstructed models exhibit superior image quality, with peak signal-to-noise ratio (PSNR) values consistently ranging from 35 to 37 dB, underscoring the robustness of 3DGS in preserving fine structural details. Compared to conventional multi-view stereo (MVS) techniques, the proposed method can achieve significantly improved reconstruction accuracy and visual fidelity. The key outcomes of this study confirm that the 3DGS-based pipeline provides a highly accurate, efficient, and scalable solution for digital phenotyping, establishing a robust foundation for its application across diverse crop species. Full article

Photogrammetry offers a non-contact and efficient alternative for monitoring structural deformation and is particularly suited to large or complex surfaces such as masonry walls. This study proposes a spatio-temporal photogrammetric refinement framework that enhances the accuracy of three-dimensional (3D) deformation and strain analysis by integrating advanced filtering techniques into markerless image-based measurement workflows. A hybrid methodology was developed using natural image features extracted using the Speeded-Up Robust Features algorithm and refined through a three-stage filtering process: median absolute deviation filtering, Gaussian smoothing, and representative point selection. These techniques significantly mitigated the influence of noise and outliers on deformation and strain analysis. Comparative experiments using both manually placed targets and automatically extracted feature points on a full-scale masonry wall under destructive loading demonstrated that the proposed spatio-temporal filtering effectively improves the consistency of displacement and strain fields, achieving results comparable to traditional marker-based methods. Validation against laser rangefinder measurements confirmed sub-millimeter accuracy in displacement estimates. Additionally, strain analysis based on filtered data captured crack evolution patterns and spatial deformation behavior. Therefore, integrating photogrammetric 3D point tracking with spatio-temporal refinement provides a practical, accurate, and scalable approach to monitor structural deformation in civil engineering applications. Full article

The proposed study explores the consistency of the geometrical character of surfaces under scaling, rotation and translation. In addition to its mathematical significance, it also exhibits advantages over image processing and economic applications. In this paper, the authors used partition-based principal component analysis similar to two-dimensional Sub-Image Principal Component Analysis (SIMPCA), along with a suitably modified atypical wavelet transform in the classification of 2D images. The proposed framework is further extended to three-dimensional objects using machine learning classifiers. To strengthen fairness, we benchmarked against both Random Forest (RF) and Support Vector Machine (SVM) classifiers using nested cross-validation, showing consistent gains when TIFV is included. In addition, we carried out a robustness analysis by introducing Gaussian noise to the intensity channel, confirming that TIFV degrades much more gracefully compared to traditional descriptors. Experimental results demonstrate that the method achieves improved performance compared to traditional hand-crafted descriptors such as measured values and histogram of oriented gradients. In addition, it is found to be useful that this proposed algorithm is capable of establishing consistency locally, which is never possible without partition. However, a reasonable amount of computational complexity is reduced. We note that comparisons with deep learning baselines are beyond the scope of this study, and our contribution is positioned within the domain of interpretable, affine-invariant descriptors that enhance classical machine learning pipelines. Full article

Micro- and nanopatterning is crucial for advanced photonic, electronic, and sensing devices. Yet achieving large-area periodic nanostructures with a 75 nm half-pitch on low-cost laboratory systems remains difficult, because conventional near-ultraviolet laser interference lithography (LIL) suffers from Gaussian-beam non-uniformity and a narrow exposure latitude. Here, we report a cost-effective deep-ultraviolet (DUV) dual-beam LIL system based on a 266 nm laser and diffractive flat-top beam shaping, enabling large-area patterning of periodical nanostructures. At this wavelength, a moderate half-angle can be chosen to preserve a large beam-overlap region while still delivering 150 nm period (75 nm half-pitch) structures. By independently tuning the incident angle and beam uniformity, we pattern one-dimensional (1D) gratings and two-dimensional (2D) arrays over a Ø 1.0 cm field with critical-dimension variation < 5 nm (1σ), smooth edges, and near-vertical sidewalls. As a proof of concept, we transfer a 2D pattern into Si to create non-metal-coated nanodot arrays that serve as surface-enhanced Raman spectroscopy (SERS) substrates. The arrays deliver an average enhancement factor of ~1.12 × 10⁴ with 11% intensity relative standard deviation (RSD) over 65 sampling points, a performance near the upper limit of all-dielectric SERS substrates. The proposed method overcomes the uneven hotspot distribution and complex fabrication procedures in conventional SERS substrates, enabling reliable and large-area chemical sensing. Compared to electron-beam lithography, the flat-top DUV-LIL approach offers orders-of-magnitude higher throughput at a fraction of the cost, while its centimeter-scale uniformity can be scaled to full wafers with larger beam-shaping optics. These attributes position the method as a versatile and economical route to large-area photonic metasurfaces and sensing devices. Full article

Accurate 3D semantic occupancy perception is critical for autonomous driving, enabling robust navigation in unstructured environments. While vision-based methods suffer from depth inaccuracies and lighting sensitivity, LiDAR-based approaches face challenges due to sparse data and dependence on expensive manual annotations. This work proposes LiGaussOcc, a novel self-supervised framework for dense LiDAR-based 3D semantic occupancy prediction. Our method first encodes LiDAR point clouds into voxel features and addresses sparsity via an Empty Voxel Inpainting (EVI) module, refined by an Adaptive Feature Fusion (AFF) module. During training, a Gaussian Primitive from Voxels (GPV) module generates parameters for 3D Gaussian Splatting, enabling efficient rendering of 2D depth and semantic maps. Supervision is achieved through photometric consistency across adjacent camera views and pseudo-labels from vision–language models, eliminating manual 3D annotations. Evaluated on the nuScenes-OpenOccupancy benchmark, LiGaussOcc achieved performance competitive with 30.4% Intersection over Union (IoU) and 14.1% mean Intersection over Union (mIoU). It reached 91.6% of the performance of the fully supervised LiDAR-based L-CONet, while completely eliminating the need for costly and labor-intensive manual 3D annotations. It excelled particularly in static environmental classes, such as drivable surfaces and man-made structures. This work presents a scalable, annotation-free solution for LiDAR-based 3D semantic occupancy perception. Full article

To enable intelligent inspection of underground cable systems, this study presents a gecko-inspired quadruped robot that integrates multi-degree-of-freedom motion with a deep learning-based visual detection system. Inspired by the gecko’s flexible spine and leg structure, the robot exhibits strong adaptability to confined and uneven tunnel environments. The motion system is modeled using the standard Denavit–Hartenberg (D–H) method, with both forward and inverse kinematics derived analytically. A zero-impact foot trajectory is employed to achieve stable gait planning. For defect detection, the robot incorporates a binocular vision module and an enhanced YOLOv8 framework. The key improvements include a lightweight feature fusion structure (SlimNeck), a multidimensional coordinate attention (MCA) mechanism, and a refined MPDIoU loss function, which collectively improve the detection accuracy of subtle defects such as insulation aging, micro-cracks, and surface contamination. A variety of data augmentation techniques—such as brightness adjustment, Gaussian noise, and occlusion simulation—are applied to enhance robustness under complex lighting and environmental conditions. The experimental results validate the effectiveness of the proposed system in both kinematic control and vision-based defect recognition. This work demonstrates the potential of integrating bio-inspired mechanical design with intelligent visual perception to support practical, efficient cable inspection in confined underground environments. Full article

The corrosion of high-strength steel wires is a key factor impacting the durability and reliability of cable-stayed bridges. In this study, the corrosion pit features on a high-strength steel wire, which had been in service for 27 years, were extracted and modeled using three-dimensional point cloud data obtained through 3D surface scanning. The Otsu method was applied for image binarization, and each corrosion pit was geometrically represented as an ellipse. Key pit parameters—including length, width, depth, aspect ratio, and a defect parameter—were statistically analyzed. Results of the Kolmogorov–Smirnov (K–S) test at a 95% confidence level indicated that the directional angle component (θ) did not conform to any known probability distribution. In contrast, the pit width (b) and defect parameter (Φ) followed a generalized extreme value distribution, the aspect ratio (b/a) matched a Beta distribution, and both the pit length (a) and depth (d) were best described by a Gaussian mixture model. The obtained results provide valuable reference for assessing the stress state, in-service performance, and predicted remaining service life of operational stay cables. Full article

This research introduces an automated 3D virtual reconstruction system tailored for architectural heritage (AH) applications, contributing to the ongoing paradigm shift from traditional CAD-based workflows to artificial intelligence-driven methodologies. It reviews recent advancements in machine learning and deep learning—particularly neural radiance fields (NeRFs) and its successor, Gaussian splatting (GS)—as state-of-the-art techniques in the domain. The study advocates for replacing point cloud data in heritage building information modeling workflows with image-based inputs, proposing a novel “photo-to-BIM” pipeline. A proof-of-concept system is presented, capable of processing photographs or video footage of ancient ruins—specifically, Romanesque–Mudéjar churches—to automatically generate 3D mesh reconstructions. The system’s performance is assessed using both objective metrics and subjective evaluations of mesh quality. The results confirm the feasibility and promise of image-based reconstruction as a viable alternative to conventional methods. The study successfully developed a system for automated 3D mesh reconstruction of AH from images. It applied GS and Mip-splatting for NeRFs, proving superior in noise reduction for subsequent mesh extraction via surface-aligned Gaussian splatting for efficient 3D mesh reconstruction. This photo-to-mesh pipeline signifies a viable step towards HBIM. Full article

This study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetry. The research targets artifacts smaller than 5 cm, characterized by complex geometries and reflective surfaces that pose challenges for conventional recording methods. To address the limitations of traditional methods without resorting to the high costs associated with laser scanning, this study explores NeRF and GS as cost-effective and efficient alternatives. A comprehensive experimental framework was established, incorporating ground-truth data obtained using a metrological articulated arm and a rigorous quantitative evaluation based on root mean square (RMS) error, Chamfer distance, and point cloud density. The results indicate that while NeRF outperforms GS in terms of geometric fidelity, both techniques still exhibit lower accuracy compared to SfM, particularly in preserving fine geometric details. Nonetheless, NeRF demonstrates strong potential for rapid, high-quality 3D documentation suitable for visualization and dissemination purposes in cultural heritage. These findings highlight both the current capabilities and limitations of neural rendering techniques for archaeological documentation and suggest promising future research directions combining AI-based models with traditional photogrammetric pipelines. Full article