Search Results (75)

Multi-view fringe projection profilometry systems that integrate a telecentric projector with multiple oblique-view cameras offer unique advantages for inspecting high dynamic-range surfaces featuring densely packed, intricate microstructures. Nevertheless, such systems encounter fundamental calibration challenges, namely, sign ambiguity in the rotation matrices and truncated extrinsic parameters inherent to telecentric projector models, as well as difficulties in multi-view point cloud registration. This paper introduces a novel calibration framework with three principal contributions. First, we resolve the sign ambiguity by calibrating the telecentric projector under a quasi pinhole model and directly transferring the extrinsic sign conventions, thereby obviating the need for costly precision displacement stages or elaborate virtual targets. Second, we fix the axial-gauge freedom by constraining the origin of the projector coordinate system to lie on the XY-plane of the camera coordinate system. Third, we establish precise relative poses between all cameras and a designated reference camera, enabling unified multi-view point cloud registration directly within the projector coordinate frame, which substantially reduces alignment errors and accelerates data processing. Experimental results demonstrate marked improvements in accuracy: reprojection root-mean-square errors of 0.084 pixels for the cameras and 0.106 pixels for the projector, corresponding to in-plane spatial resolutions of 0.21 µm and 0.26 µm, respectively. The proposed method offers a robust solution for micron-level inspection in semiconductor packaging and precision manufacturing. Full article

Robust monocular distance estimation under varying illumination conditions is critical for autonomous driving safety. While state-of-the-art monocular 3D detection models achieve high accuracy in daylight conditions, they rely on computationally heavy architectures and degrade significantly in low-light environments. Lightweight 2D detectors (e.g., YOLO variants) offer real-time performance but lack the geometric constraints required for accurate depth estimation. To address this limitation, we propose the Anisotropic Geometry Loss (AGL) framework. This lightweight framework enforces ground-plane consistency through an anisotropic bottom-edge constraint derived from the pinhole camera model. In addition, a luminance-channel contrast enhancement module (CLAHE) is applied at inference to improve low-light visibility. Experimental results on the Dark-KITTI dataset show that the proposed method achieves an RMSE of 10.91 ± 0.68 m, improving over YOLOv10n (11.53 ± 0.56 m) and YOLOv26n (11.99 ± 0.58 m), while maintaining a 2.71 M-parameter footprint and real-time inference (>160 FPS). With CLAHE, RMSE is further reduced to 10.55 ± 0.72 m. Stratified by kinematic safety zone, the proposed method achieves 2.42 ± 0.03 m in the Near range (0–15 m), 5.94 ± 0.19 m in the Medium range (15–30 m), and 17.41 ± 1.25 m in the Far range (>30 m), corresponding to Euro NCAP AEB (Autonomous Emergency Braking) stopping distances. AGL provides its largest measurable accuracy improvement in the medium-distance range while maintaining comparable performance in the far-distance range. A complementary luminance-channel CLAHE preprocessor recovers bottom-edge gradients in synthetic and real low-light frames; zero-shot generalization is qualitatively corroborated on the ExDark dataset. These results demonstrate that explicit geometric constraints provide an effective and efficient solution for robust cross-illumination resistance in monocular distance estimation. The framework also shows practical potential for camera-only AEB systems deployed on edge-computing platforms aligned with Euro NCAP safety protocols. Full article

Vulnerable road users in informal urban environments confront a distinct set of hazards that standard computer vision datasets are ill-equipped to represent: artisanal speed bumps constructed without regulatory compliance, deteriorated road markings, and the mototaxi—a three-wheeled motorized vehicle that constitutes the primary informal transport mode in intermediate Andean cities yet is absent from all major international repositories. This paper presents QHAWAY—from Quechua qhaway, a transitive verb meaning “to look; to observe”—an Advanced Driver Assistance System (ADAS) predicated on instance segmentation, monocular distance estimation via the pinhole camera model, and Time-to-Collision (TTC) computation, developed for the road environment of Ayacucho, Peru (2761 m a.s.l.), a city recognised by UNESCO as a Creative City of Crafts and Folk Art since 2019. A hybrid dataset comprising 25,602 images with 127,525 annotated instances across 12 classes was assembled by combining an original local collection of 4598 images (10,701 instances) captured through four complementary acquisition methods across the five urban districts of the Huamanga province with three established international datasets (BDD100K, BSTLD, RLMD; 21,004 images, 116,824 instances). A three-phase progressive training strategy with monotonically increasing resolution (640, 800, and 1024 pixels) was evaluated as an ablation study. A multi-architecture comparison spanning YOLOv8L-seg and the YOLO26 family (nano, small, large) identified YOLO26L-seg as the best-performing model, attaining mAP50 Box of 0.829 and mAP50 Mask of 0.788 at epoch 179. The integration of ByteTrack multi-object tracking with the pinhole equation $D=(H_{\mathrm{real}}\times f)/h_{\mathrm{px}}$ delineates operational risk zones aligned with the NHTSA forward collision warning standard (danger: <3 m; caution: 3–7 m; TTC threshold ≤ 2.4 s). The system sustains processing rates of 19.2–25.4 FPS on an NVIDIA RTX 5080 GPU. A systematic field survey established that 96% of the audited speed bumps fail to comply with MTC Directive No. 01-2011-MTC/14, constituting the first quantitative record of informal road infrastructure non-compliance in the Andean region. Validation was conducted under naturalistic driving conditions without staged scenarios. Grad-CAM explainability analysis, encompassing three complementary visualisation algorithms (Grad-CAM, Grad-CAM++, and EigenCAM), confirmed that model attention concentrates consistently on safety-critical objects. Full article

Three-dimensional (3D) reconstruction technology has found widespread applications across various domains, including intelligent driving and underwater exploration. But the existing imaging systems and methods still have deficiencies in terms of reconstruction accuracy, detection distance and system volume. Herein, this paper presents a three-dimensional detection and reconstruction method based on a compact Risley-prism 3D imaging system that achieves multi-viewpoint imaging by rotating the Risley prism to adjust the camera’s optical axis. A refractive camera model that integrates the pinhole camera model with the vector form of Snell’s law is established to precisely describe beam trajectory. A forward projection method suitable for refractive interfaces is developed based on Fermat’s principle, and the influence of systematic errors on the reconstruction is analyzed in detail through simulation. Furthermore, a new 3D reconstruction method combining error calibration based on the optimization iteration is introduced to avoid the influence of error and improve reconstruction quality. Experimental results demonstrate that the proposed approach markedly enhances 3D reconstruction accuracy, reducing the Normalized Root Mean Square Error (NRMSE) from 0.9076 to 0.0207. Full article

To address the calibration challenge caused by the nonlinear variation in intrinsic parameters during continuous camera zooming in UAV electro-optical pods, this paper proposes an online calibration method based on IMU-visual fusion. Traditional offline calibration cannot adapt to dynamic scenarios, while existing self-calibration methods suffer from slow convergence and insufficient robustness. The proposed method aims to achieve real-time and accurate estimation of camera intrinsic parameters during zooming. Specifically, we first construct a unified state estimation framework that encodes the internal and external parameters of the camera and the 3D positions of scene feature points into a high-dimensional state vector, then establish a camera motion model based on IMU data, construct a visual observation model by combining the pinhole camera and second-order radial distortion model to establish a nonlinear mapping from 3D feature points to 2D pixel coordinates, and adopt an improved ORB algorithm for feature extraction and LK optical flow method to achieve high-precision cross-frame feature matching to enhance the stability of visual observation. Most importantly, we design a tight-coupling fusion strategy based on the Extended Kalman Filter (EKF) prediction-update iteration mechanism, which fuses IMU high-frequency motion constraints and visual geometric constraints in real time to suppress parameter drift induced by focal length changes. Finally, we recursively solve the state vector to complete the online dynamic estimation of intrinsic parameters. Monte Carlo simulation experiments and real UAV flight experiments confirm that the method has both high estimation accuracy and strong environmental adaptability, can meet the high-precision calibration needs of UAVs in dynamic scenarios, and provides reliable technical support for accurate target positioning. Full article

The integration of outdoor camera images with three-dimensional (3D) geographic information on the observed scene is of interest for many video acquisition applications. To solve this data fusion problem, camera images have to be matched with the 3D geometry provided by a geographic information system (GIS). Considering a camera with a known geographical position, this paper proposes the use of a dense local azimuth–elevation map (LAEM) derived from a gridded digital elevation model (DEM) to represent the data and thus facilitate the matching of GIS and image data. To each regularly sampled azimuth and elevation angle pair, this map assigns the geographic point derived from the DEM viewed in this direction. The problem of computing the LAEM from the DEM is closely related to that of surface rendering, for which solutions exist in computer graphics. However, rendering software cannot be used directly in this case, since their view directions are constrained by the pinhole camera model and the apparent colour, rather than the position of the viewed point, is assigned to the viewing direction. Therefore, this paper also proposes a specific algorithm for the computation of the LAEM from the DEM. A MATLAB^® implementation of the algorithm is also provided, which is tailored to process the DEM dataset swissALTI3D from the Swiss Federal Office of Topography swisstopo. Full article

As the primary power transmission conduits, aircraft hydraulic pipelines are critical for actuating flight control surfaces and landing gear systems. Accurate in situ strain evaluation of these pipelines is essential, as installation-induced pre-loads directly compromise fatigue life and sealing performance, threatening overall system reliability. However, such evaluation is frequently hindered by the perspective distortions and limited depth of field inherent in conventional imaging systems. To overcome these metrological limitations, this study presents a novel virtual telecentric camera array system designed for high-precision, non-contact strain measurement. Unlike traditional pinhole models, the proposed system leverages a catadioptric setup with planar mirrors to create a virtual four-eye telecentric array from a single physical lens, ensuring constant magnification within the depth of field. A comprehensive simulation framework was established to rigorously compare the reprojection errors and scale accuracies between telecentric and pinhole projection models, quantitatively demonstrating the superior stability of the telecentric approach. Furthermore, a dedicated calibration strategy for non-overlapping telecentric fields of view was developed and validated. Experimental results from pipeline installation tests indicate a high concordance with strain gauge data, confirming that the proposed telecentric system effectively mitigates parallax errors and provides a robust solution for static and quasi-static micro-scale deformation monitoring in complex assembly environments. Full article

Physicians performing cardiac angiography are exposed to scattered radiation originating from the patient, and visualizing scattered radiation sources could help optimize radiation protection strategies. In this study, an existing scattered radiation source visualization system comprising a high-sensitivity CMOS camera, thallium-activated cesium iodide scintillator, and pinhole collimator was extended to incorporate a depth camera and employed to visualize scattered radiation sources in three dimensions under conditions simulating clinical cardiac angiography. Scattered radiation source images were captured using a patient phantom under multiple irradiation directions of a biplane angiography system, and changes in the images and dose rate reaching the system were evaluated with and without radiation protection equipment and for various ceiling-mounted radiation shielding positions. The scattered radiation source was visualized on the patient phantom surface for a 5-s exposure in three-dimensional images and was observed around the X-ray tube in one direction. Radiation protection equipment reduced both the scattered radiation source intensity and dose rate. The greatest reduction occurred when the ceiling-mounted radiation shielding was positioned near the physician. Irradiation at caudal angles caused the highest increase in scattered radiation source intensity and dose rate. These findings suggest that this system can support the optimization of radiation protection practices and education. Full article

Ellipsometric mapping measurements and Bayesian evaluation were performed with a non-collimated, imaging ellipsometer using an LCD monitor as a light source. In such a configuration, the polarization state of the illumination and the local angle of incidence vary spatially and spectrally, rendering conventional spectroscopic ellipsometry inversion methods hardly applicable. To address these limitations, a multilayer optical forward model is augmented with instrument-specific correction parameters describing the polarization state of the monitor and the angle-of-incidence map. These parameters are determined through a Bayesian calibration procedure using well-characterized Si-SiO₂ reference wafers. The resulting posterior distribution is explored by global optimization based on simulated annealing, yielding a maximum a posteriori estimate, followed by marginalization to quantify uncertainties and parameter correlations. The calibrated correction parameters are subsequently incorporated as informative priors in the Bayesian analysis of unknown samples, including polycrystalline–silicon layers deposited on Si-SiO₂ substrates and additional Si-SiO₂ wafers outside the calibration set. The approach allows consistent propagation of calibration uncertainties into the inferred layer parameters and provides credible intervals and correlation information that cannot be obtained from conventional least-squares methods. The results demonstrate that, despite the broadband nature of the RGB measurement and the limited number of analyzer orientations, reliable layer thicknesses can be obtained with quantified uncertainties for a wide range of technologically relevant samples. The proposed Bayesian framework enables a transparent interpretation of the measurement accuracy and limitations, providing a robust basis for large-area ellipsometric mapping of multilayer structures. Full article

To address the critical problem of 3D object detection in autonomous driving scenarios, we developed a novel digital twin architecture. This architecture combines AI models with geometric optics algorithms of camera systems for autonomous vehicles, characterized by low computational cost and high generalization capability. The architecture leverages monocular images to estimate the real-world heights and 3D positions of objects using vanishing lines and the pinhole camera model. The You Only Look Once (YOLOv11) object detection model is employed for accurate object category identification. These components are seamlessly integrated to construct a digital twin system capable of real-time reconstruction of the surrounding 3D environment. This enables the autonomous driving system to perform real-time monitoring and optimized decision-making. Compared with conventional deep-learning-based 3D object detection models, the architecture offers several notable advantages. Firstly, it mitigates the significant reliance on large-scale labeled datasets typically required by deep learning approaches. Secondly, its decision-making process inherently provides interpretability. Thirdly, it demonstrates robust generalization capabilities across diverse scenes and object types. Finally, its low computational complexity makes it particularly well-suited for resource-constrained in-vehicle edge devices. Preliminary experimental results validate the reliability of the proposed approach, showing a depth prediction error of less than 5% in driving scenarios. Furthermore, the proposed method achieves significantly faster runtime, corresponding to only 42, 27, and 22% of MonoAMNet, MonoSAID, and MonoDFNet, respectively. Full article

Spinning disk confocal microscopy enables fast optical sectioning with low phototoxicity but is often inaccessible due to high hardware costs. We present a lower-cost solution using a 25-megapixel machine vision CMOS camera and a custom-built spinning disk. This camera uses a back-illuminated sensor with high quantum efficiency and low read noise. High-resolution images of Thy1-GFP mouse brain slices, Drosophila embryos and larvae, and H&E-stained rat testis verified performance across 3D tissue volumes. The measured resolution was 215.8 nm in X, Y and 521.9 nm in Z with a 60×/1.42 NA objective. The custom disk, made with 18 µm pinholes (180 µm pitch) on a chrome photomask and mounted to an optical chopper motor, enables stable, near-telecentric imaging at lower magnifications. Micromanager software integration allows synchronized control of all hardware, which demonstrates that affordable CMOS sensors can potentially replace sCMOS in spinning disk microscopy, offering an open-access, scalable solution for advanced imaging. Full article

Automated Optical Inspection (AOI) of Printed Circuit Boards (PCBs) suffers from scarce labeled data and frequent domain shifts caused by variations in camera optics, illumination, and product design. These limitations hinder the development of accurate and reliable deep-learning models in manufacturing settings. To address this challenge, this study systematically benchmarks three Parameter-Efficient Fine-Tuning (PEFT) strategies—Linear Probe, Low-Rank Adaptation (LoRA), and Visual Prompt Tuning (VPT)—applied to two representative foundation vision models: the Contrastive Language–Image Pretraining Vision Transformer (CLIP-ViT-B/16) and the Self-Distillation with No Labels Vision Transformer (DINOv2-S/14). The models are evaluated on six-class PCB defect classification tasks under few-shot (k = 5, 10, 20) and full-data regimes, analyzing both performance and reliability. Experiments show that VPT achieves 0.99 ± 0.01 accuracy and 0.998 ± 0.001 macro–Area Under the Precision–Recall Curve (macro-AUPRC), reducing classification error by approximately 65% compared with Linear and LoRA while tuning fewer than 1.5% of backbone parameters. Reliability, assessed by the stability of precision–recall behavior across different decision thresholds, improved as the number of labeled samples increased. Furthermore, class-wise and few-shot analyses revealed that VPT adapts more effectively to rare defect types such as Spur and Spurious Copper while maintaining near-ceiling performance on simpler categories (Short, Pinhole). These findings collectively demonstrate that prompt-based adaptation offers a quantitatively favorable trade-off between accuracy, efficiency, and reliability. Practically, this positions VPT as a scalable strategy for factory-level AOI, enabling the rapid deployment of robust defect inspection models even when labeled data is scarce. Full article

Calibrating cameras accurately requires the identification of projection and distortion models that effectively account for lens-specific deviations. Conventional formulations, like the pinhole model or radial–tangential corrections, often struggle to represent the asymmetric and nonlinear distortions encountered in complex environments such as autonomous navigation, robotics, and immersive imaging. Although neural methods offer greater adaptability, they demand extensive training data, are computationally intensive, and often lack transparency. This work introduces a symbolic model discovery framework guided by physical knowledge, where symbolic regression and genetic programming (GP) are used in tandem to identify calibration models tailored to specific optical behaviors. The approach incorporates a broad class of known distortion models, including Brown–Conrady, Mei–Rives, Kannala–Brandt, and double-sphere, as modular components, while remaining extensible to any predefined or domain-specific formulation. Embedding these models directly into the symbolic search process constrains the solution space, enabling efficient parameter fitting and robust model selection without overfitting. Through empirical evaluation across a variety of lens types, including fisheye, omnidirectional, catadioptric, and traditional cameras, we show that our method produces results on par with or surpassing those of established calibration techniques. The outcome is a flexible, interpretable, and resource-efficient alternative suitable for deployment scenarios where calibration data are scarce or computational resources are constrained. Full article

Galileo and the telescope revolutionized the concept of the Sun. The discovery of its rotation was possible due to the continuous observation of the sunspots. The faculae and the maculae with umbra and penumbra became accessible daily to new instruments, leaving the perfectly lucid disk to the realm of symbolism. Was this new view possible before the telescope? Technically, pinhole cameras can show the largest sunspots, as well as the naked eye under very particular conditions. However such observations were too scattered to produce any change in the established understanding of the Sun. Synoptic observations of the largest sunspots of the XXV solar cycle made with the naked eye, pinhole camera, and a telescope in camera obscura are presented and compared with the historical ones. Sunspots could have been discovered in Florence as early as 1475 with the pinhole meridian line of S. Maria del Fiore: the Spörer minimum (1460–1550) of the solar activity prevented it. Indications of white light flares and prominence observations appear in a drawing dated back to 1635, well before the first H-alpha inspections in the 19th century. Full article

Digital holographic microscopes provide a microscopy solution with a resolution in the low-micrometre range that offers similar performance to optical microscopy, but as a relatively low-cost alternative. The most significant cost saving is due to the ability to reconstruct microscopic images from holograms using low-cost components without the need for an optical stack. The cost saving opens up the avenue towards a feasible solution for geographically distributed in situ microscopic sensing in rural areas for problems like air and water pollution monitoring. The most significant contributors to cost are the camera sensor module, the pinhole, and the processing platform. The latter two components are addressed, at least in part, in this work. We successfully manufactured sub-100 $\mu$m diameter pinholes using ultraviolet (UV) laser cutting with an LPKF printed circuit board (PCB) prototyping platform and present the low-cost micromachining method. The pinholes were utilised within a prototype field-programmable gate array (FPGA) demonstrator that successfully reconstructed the holographic images. The choice for the FPGA approach as the initial step, albeit more complex, lends itself towards the easier development of a dedicated reconstructed application-specific integrated circuit (ASIC) to ultimately drive the cost down even further. Full article