Search Results (999)

The high-fidelity 3D digitization of small, detailed cultural heritage objects, such as Oracle Bones, presents significant challenges for which existing reconstruction workflows are often inadequate. Methods based on Structure-from-Motion (SfM) often lack the geometric density required to capture fine inscription details, while Light Detection and Ranging and RGB-Depth approaches may introduce high data overhead and unstable color mapping. Recent specialized studies have utilized multi-shading-based techniques to extract such hidden surface textures, yet integrating these results into a cohesive mesh remains difficult. To address these limitations, we propose a digitization framework specifically designed for object-level archaeological artifacts. Our method combines semi-automatic alignment with ICP-based refinement for robust camera pose estimation, reducing misalignment issues associated with feature-only registration. Furthermore, we employ an efficient mesh-based representation with vertex-level coloring, enabling detailed geometry and consistent texturing while maintaining compact storage requirements. Our contributions include: (1) a high-quality mesh reconstruction framework that preserves fine inscription geometry; (2) a hybrid camera pose estimation strategy that improves alignment robustness; and (3) an integrated hardware-assisted workflow tailored for digitizing small archaeological artifacts under controlled acquisition conditions. Experimental results on physical Oracle Bone artifacts demonstrate that the proposed method achieves a mean geometric reconstruction error of approximately 0.075 mm with a Hausdorff distance of 1 mm. These results demonstrate the effectiveness of the proposed workflow for digitization of oracle bone artifacts. Full article

Teleoperated open-pit excavation requires fast and reliable 3D scene modeling under lightweight sensor configurations. To this end, this paper proposes a monocular camera–LiDAR fusion-based fast 3D Gaussian reconstruction method tailored for teleoperated open-pit excavation. The proposed approach uses only two sensors, a monocular camera and LiDAR, and integrates SPNet, a depth completion network, to improve the geometric completeness of the reconstructed scene. It further introduces a stride-aware initialization strategy that leverages the depth–stride correlation to jointly construct the initial Gaussian set and estimate the initial scales. During optimization, scale and color regularization are applied to prevent uncontrolled growth of Gaussians. Experiments in a Carla-simulated open-pit excavation scenario show that, under high-resolution input of 1920 × 1080, the proposed method achieves a stable 3D model update rate of approximately 2.5 Hz. The reconstruction quality under training viewpoints reaches PSNR 30.5388, SSIM 0.9161, and LPIPS 0.1333. Compared with 4DTAM and MonoGS, the proposed method achieves better overall reconstruction quality. It also maintains a much higher update rate than 4DTAM and a comparable update rate to MonoGS. Ablation studies further verify the critical contribution of the depth completion module and the stride-aware initialization strategy to the overall reconstruction performance. In addition, preliminary validation on field data further demonstrates the applicability of the proposed method under real-world open-pit excavation-loading conditions. The proposed method generates stable and usable 3D models of rock-pile working face under a lightweight sensor configuration, providing a reliable geometric basis for remote situational awareness and excavation assistance. Full article

Corrosion in steel pipelines can cause critical failures in industrial systems, while conventional inspection methods such as radiography and ultrasonic testing are costly and require specialized personnel. This study presents a mobile computer vision system for automated corrosion detection inside steel pipes using deep learning-based visual analysis. The proposed system consists of a Raspberry Pi 4-based mobile robot equipped with a high-resolution camera for internal inspection. Acquired images were processed using color-space transformations (RGB–HSV), filtering, and segmentation. Convolutional neural networks and semantic segmentation models, including YOLOv8-seg (Instance segmentation) and DeepLabV3 (Semantic segmentation), were trained on a custom corrosion image dataset to identify corroded regions. Real-time visualization was implemented via Flask-based video streaming. Experimental results demonstrated high detection accuracy for uniform corrosion, achieving a mean Intersection over Union (mIoU) above 0.98 and a precision of 0.99 with the YOLOv8-seg model. These results indicate that the proposed system enables reliable and automated corrosion inspection, with the potential to reduce inspection costs and improve operational efficiency. Future work will focus on enhancing real-time performance through hardware optimization. Full article

Vision-only driving perception systems are highly sensitive to illumination variations, particularly under low-light conditions where reduced contrast and structural degradation impair detection and segmentation accuracy. Rather than treating enhancement as a post-processing step, this work investigates the system-level impact of relocating low-light enhancement to the FPGA-based front end within a heterogeneous FPGA–ARM architecture. A hardware-accelerated visual pipeline is designed to perform color space conversion, fixed-point convolutional enhancement, and multi-channel fusion prior to high-level perception on the ARM processor. Experimental results demonstrate that the proposed FPGA-based front-end enhancement introduces only 13 ms of additional processing latency, which executes in parallel with the preceding frame’s neural network inference and therefore imposes zero net overhead on the end-to-end pipeline. In contrast, an equivalent software-based back-end enhancement approach would add its full processing time serially to the inference stage, increasing total system latency proportionally. The system achieves a sustained throughput of 58 fps while supporting real-time multi-task perception including lane detection (YOLOPv2, 539 ms per frame), object detection and emergency braking (YOLOv5, 432 ms per frame), and hardware-level multi-camera synchronization. Full article

To address the difficulty of accurately localizing automotive chassis bolts during the assembly process—caused by non-uniform illumination, limited camera installation space, and occlusions from the vehicle body structure—a fiducial-marker-based localization method is proposed. In this method, a concentric ring-shaped fiducial marker is affixed to the bottom of the assembly wrench, and its region of interest (ROI) is extracted using an HSV color space segmentation algorithm. To overcome interference from uneven lighting and insufficient brightness in industrial environments, an improved Retinex-based image enhancement algorithm is introduced, which significantly improves the robustness and accuracy of ROI extraction. The extracted ROI image is subjected to ellipse fitting, and the fitting process is optimized by incorporating the Leitz criterion. Experimental results show that the optimized ellipse fitting algorithm achieves higher accuracy and significantly enhances the reliability of fitting. Since perspective projection of spatial circles leads to displacement of the circle center, the actual projected center of the fiducial marker in the image is calculated by estimating the normal vector of the circular plane using vanishing lines and the ellipse parameter matrix. This enables spatial localization of the bolt end. The proposed method is validated by comparing the localization results with the theoretical coordinates of the bolt holes. Experimental results demonstrate that the method offers high localization accuracy and strong robustness, meeting the practical precision requirements for automatic bolt assembly in industrial applications. Full article

Digital photoelasticity enables non-contact, full-field stress analysis through optical fringe patterns, yet its practical deployment is often constrained by experimental complexity and the limited availability of open, standardized datasets. The emergence of multi-polarizer array cameras provides polarization-resolved measurements with high information content, enabling advanced analysis strategies beyond conventional single-image approaches. This work presents a public experimental dataset composed of synchronized image sequences acquired using a polarizer array camera and a conventional RGB camera under incremental mechanical loading. The dataset comprises nine experiments, including four benchmark specimens and five bio-inspired geometries, each recorded over 720 load steps. In total, the dataset releases 25,920 polarization-resolved images and 6480 RGB images, all provided in lossless format and accompanied by experiment-specific segmentation templates. Although classical and hybrid load-stepping methods are used to demonstrate the utility of the dataset, its scope is not limited to this application. The dataset is intended as a flexible platform for exploring a wide range of photoelastic analysis techniques that leverage polarization information, while enabling direct comparison with conventional color demodulation techniques. Full article

Accurate color property measurements are critical for advancing artificial vision in real-time industrial applications. RGB imaging remains highly applicable and widely used due to its practicality, accessibility, and high spatial resolution. However, significant uncertainties in extracting chromatic information highlight the need to define when conventional digital images can reliably provide accurate color data. This work simultaneously compares six chromatic properties across 700 Pantone^® TCX fabric samples, using optical data acquired simultaneously from both hyperspectral (HSI) and digital (RGB) cameras. The results indicate that the accurate interpretation of optical information from RGB (sRGB and REC2020) images is significantly influenced by lightness ($L^{*}$) values. Samples with bright and unsaturated colors ($L^{*}>$ 50) reach ratio-to-performance-deviation (RPD) values above 2.5 for four properties ($L^{*}, a^{*}, b^{*}$ $h_{ab}$), indicating a good correlation between HSI and RGB information. Absolute color difference comparisons (${∆E}_a$) between HSI and RGB images yield values exceeding 5.5 units for red-yellow-green samples and up to 9.0 units for blue and purple tones. In contrast, relative color differences (${∆E}_r$) comparisons show a significant decrease, with values falling below 3.0 for all lightness values, indicating the practical equivalence of both methodologies according to the Two One-Sided Test (TOST) statistical analysis. These results confirm that RGB imagery achieves reliable color consistency when evaluated against a practical reference. Full article

The effectiveness of deep learning methods in image segmentation has led to interest in their deployment for 3D point cloud segmentation, particularly in the context of pre-grasp identification of a unique object amongst distractors. However, existing 3D object datasets are not ideal for training and evaluation of these methods. Datasets developed for grasp planning are often CAD models that are too clean for sim-to-real transfer. Real-world datasets can lack texture information or have been collected using sets of objects and/or specialized sensor setups that are hard to reproduce. In this work, we introduce the MiniMarket80 dataset to address this gap.The dataset consists of 1200 colored point cloud partial views, each of 80 standard grocery objects, collected with widely used Realsense RGB-D cameras (D415 and D435) under variable lighting conditions. We also provide a complete pipeline to generate a per-object segmentation dataset from these partial views suitable for use in training. We use this dataset to evaluate 11 state-of-the-art point cloud segmentation methods. Only four of these are able to (partially) segment the target object in a real-world test, still producing significant false positives and false negatives. Full article

The use of depth cameras in low-texture environments is crucial for ensuring the feasibility of visual simultaneous localization and mapping (SLAM) algorithms. Nevertheless, in underwater scenarios, light propagation through multi-layered media gives rise to refractive distortion. Directly utilizing distorted images acquired by depth cameras for visual SLAM computations inevitably introduces substantial errors in localization and mapping. Additionally, the waterproof glass mounted in front of the depth camera renders traditional air-based camera calibration ineffective, thereby introducing calibration inaccuracies. To mitigate these challenges, we propose a comprehensive SLAM algorithm framework for underwater multi-layered media refraction correction based on RGB-D cameras. Firstly, a multi-layer refraction calibration module is developed to calibrate the depth camera in air. Subsequently, the calibrated parameters are leveraged to construct an underwater multi-layer refraction correction module, which retrieves undistorted color images and aligned depth images. Finally, the corrected color images and depth images are fed into the front-end of the visual SLAM algorithm to generate dense point cloud maps. Both simulation and real-world experiments are conducted to validate the accuracy of the multi-layer refraction calibration results and the precision of the dense point clouds obtained via multi-layer refraction correction. Furthermore, the superiority of the proposed method is demonstrated through both qualitative and quantitative evaluations. Full article

Capillary refill time (CRT) is widely used in pediatric and emergency medicine as an indicator of peripheral circulation. CRT is defined as the time required for the skin to return to its original color after external compression is applied and then released. In current clinical practice, however, CRT assessment remains qualitative and relies heavily on the magnitude and consistency of compression applied by the measurer, as well as on subjective visual color perception, which together result in limited measurement reliability. To improve measurement reliability, several quantitative CRT measurement devices have been developed. Nevertheless, these devices are dedicated specifically to CRT measurement, which limits their versatility and complicates clinical implementation. In this study, we developed a simple and quantitative CRT measurement method using a smartphone. Based on skin color changes captured by the rear camera, we proposed a method to assess the adequacy of the applied compression force and implemented an application to calculate CRT. In addition, we investigated an algorithm to reduce the influence of pulse waves observed in the post-release waveform, enabling more stable CRT estimation. Furthermore, a dedicated smartphone case was designed to immobilize the finger during measurement, thereby improving measurement reliability. The feasibility of the proposed method was evaluated by examining agreement with a previously developed CRT measurement device and by assessing intraexaminer reliability, confirming its effectiveness. Full article

A method for simultaneous classification of fabric material and color based on hyperspectral imaging and visual detection is proposed. Fabric material classification is performed using hyperspectral imaging (HSI) combined with a one-dimensional convolutional neural network (1D-CNN), while fabric color recognition is achieved using an red-green-blue (RGB) camera and a color classification model. Material and color features from the same fabric sample are matched to realize synchronous classification. Experiments were conducted on three fabric materials (cotton, polyester, and cotton–polyester blend) and eight colors. At a conveyor speed of 1 m/s, the sorting success rates reach 95.0% for cotton, 97.5% for polyester, and 85.0% for cotton–polyester blended fabrics. The proposed method demonstrates reliable performance for single-material fabrics and good industrial applicability for automated fabric sorting. Full article

A galvanometer-based laser 3D projection system requires accurate mapping between galvanometer control signals and workpiece coordinates to ensure reliable on-part marking. This study presents a calibration and verification pipeline that uses a color camera and a depth sensor to reconstruct 3D target points and estimate the extrinsic parameters between the projector and the workpiece. Laser spot centers are localized in color images, and corresponding depth values are acquired after color–depth alignment. The resulting 3D points are back-projected and transformed into the workpiece coordinate frame. A hybrid solver is employed: the Whale Optimization Algorithm (WOA) provides a global initial estimate, followed by Levenberg–Marquardt (LM) refinement to enhance convergence stability under noisy and small-sample conditions. Experimental validation on an independent 13-point set demonstrates sub-millimeter accuracy, with a mean error of approximately 0.37 mm and a maximum error of 0.87 mm. A further rectangular contour projection test confirms consistent performance, yielding a mean error of 0.434 mm and a maximum error of 0.879 mm, with all errors remaining below 1 mm. Full article

Dense foliage, severe illumination variations, and interference from multiple individuals with similar appearances in complex orchard environments pose significant challenges for vision-based following robots in maintaining persistent target perception and identity consistency, thereby compromising the stability and safety of fruit transportation operations. To address these challenges, we propose a novel framework, DeepDIMP-ReID, which integrates the Deep Implicit Model Prediction (DIMP) tracker with a person re-identification (ReID) module based on EfficientNet. This visual perception and autonomous following framework is designed for differential-drive orchard transportation robots, aiming to achieve robust target perception and reliable identity maintenance in unstructured orchard settings. The proposed framework adopts a hierarchical perception–verification–control architecture. Visual tracking and three-dimensional localization are jointly achieved using synchronized color and depth data acquired from a RealSense camera, where target regions are obtained via the discriminative model prediction (DIMP) method and refined through an elliptical-mask-based depth matching strategy. Front obstacle detection is performed using DBSCAN-based point cloud clustering techniques. To suppress erroneous following caused by occlusion, target switching, or target reappearance after occlusion, an enhanced HOReID person re-identification module with an EfficientNet backbone is integrated for identity verification at critical decision points. Based on the verified perception results, a state-driven motion control strategy is employed to ensure safe and continuous autonomous following. Extensive long-term experiments conducted in real orchard environments demonstrate that the proposed system achieves a correct tracking rate exceeding 94% under varying human walking speeds, with an average localization error of 0.071 m. In scenarios triggering re-identification, a target discrimination success rate of 93.3% is obtained. These results confirm the effectiveness and robustness of the proposed framework for autonomous fruit transportation in complex orchard environments. Full article

This study examines the efficacy of phasor analysis in distinguishing between healthy and diseased retinas using multispectral imaging data together with machine learning approaches. Our results demonstrate that phasor analysis of multispectral images surpasses average reflectance values in classification performance, serving as an effective dimensionality reduction technique to extract essential features, with the first harmonic yielding optimal results when paired with Z-score normalization. To compare the effectiveness of multispectral images with that of a conventional color fundus camera, we extracted three spectral bands corresponding to the red, green, and blue regions and combined them to create RGB-like images, which were then subjected to the same analysis. Our study found that phasor analysis of multispectral images provided more accurate classification results than phasor analysis of RGB-like images. An examination of different regions of interest showed that using the entire retina yields the best classification performance, likely due to the advanced stage of the diseases, which had progressed to affect the entire fundus. Our findings suggest that phasor analysis of multispectral images and machine learning are a powerful tools for retinal disease classification. Full article

Artificial vision and artificial intelligence (AI) are increasingly interconnected in cybersecurity. This work presents an overview of OpenCV-based visual computing as a core tool for intelligent security systems that analyze real-time visual data. It includes practical exercises on face, edge, motion, and color detection, forming the basis for advanced object recognition using YOLOv10. Real applications, such as document processing and camera-based anomaly detection, are implemented in a microservice architecture with OpenCV, and deep learning frameworks. Integrating computer vision and AI is shown to be essential for developing resilient and autonomous cybersecurity infrastructures. Full article