Search Results (338)

With the strict requirements of national policies on truck dimensions, axle loads, and weight limits, along with the implementation of tolls based on vehicle types, rapid and accurate identification of vehicle axle types has become essential for toll station management. To address the limitations of existing methods in distinguishing between drive and driven axles, complex equipment setup, and image evidence retention, this article proposes a panoramic image detection technology for vehicle chassis based on enhanced ORB and YOLOv11. A portable vehicle chassis image acquisition system, based on area array cameras, was developed for rapid on-site deployment within 20 min, eliminating the requirement for embedded installation. The FeatureBooster (FB) module was employed to optimize the ORB algorithm’s feature matching, and combined with keyframe technology to achieve high-quality panoramic image stitching. After fine-tuning the FB model on a domain-specific area scan dataset, the number of feature matches increased to 151 ± 18, substantially outperforming both the pre-trained FB model and the baseline ORB. Experimental results on axle type recognition using the YOLOv11 algorithm combined with ORB and FB features demonstrated that the integrated approach achieved superior performance. On the overall test set, the model attained an mAP@50 of 0.989 and an mAP@50:95 of 0.780, along with a precision (P) of 0.98 and a recall (R) of 0.99. In nighttime scenarios, it maintained an mAP@50 of 0.977 and an mAP@50:95 of 0.743, with precision and recall both consistently at 0.98 and 0.99, respectively. The field verification shows that the real-time and accuracy of the system can provide technical support for the axle type recognition of toll stations. Full article

Fine-grained sedimentary rocks exhibit significant textural heterogeneity, often obscured by conventional grain size analysis techniques that require sample disaggregation. We propose a non-destructive, image-based grain size characterization workflow, utilizing stitched polarized thin-section photomicrographs, k-means clustering, and watershed segmentation algorithms. Validation against laser granulometry data indicates strong methodological reliability (absolute errors ranging from −5% to 3%), especially for particle sizes greater than 0.039 mm. The methodology reveals substantial internal heterogeneity within Es3 laminated shale samples from the Shahejie Formation (Bohai Bay Basin), distinctly identifying coarser siliceous laminae (grain size >0.039 mm, Φ < 8 based on Udden-Wentworth classification) indicative of high-energy depositional environments, and finer-grained clay-rich laminae (grain size <0.039 mm, Φ > 8) representing low-energy conditions. Conversely, massive mudstones exhibit comparatively homogeneous grain size distributions. Additionally, a multifractal analysis (Multifractal method) based on the S_50bi/S_50si ratio further quantifies spatial heterogeneity and pore-structure complexity, significantly enhancing facies differentiation and reservoir characterization capabilities. This method significantly improves facies differentiation ability, provides reliable constraints for shale oil reservoir characterization, and has important reference value for the exploration and development of the Bohai Bay Basin and similar petroliferous basins. Full article

The durability and safety of modern concrete architecture and infrastructure are critically impacted by early-stage surface cracks. Timely and appropriate identification and management of these cracks are therefore essential to enhance structural longevity and stability. This study utilizes computer vision technology to construct a large-scale database, comprising 106,998 concrete surface crack images from various research sources. Through data augmentation, the database is extended to 140,000 images to fully leverage the advantages of deep learning models. For concrete surface crack detection, this study proposed a lightweight convolutional neural network (CNN) model, achieving 92.27% accuracy, 94.98% recall, and a 92.39% F1 score. Notably, the model runs smoothly on lightweight office notebooks without GPUs. Additionally, an image stitching algorithm that seamlessly stitches multiple images was proposed to generate high-quality panoramic views of bridges. The image stitching algorithm demonstrates robustness when applied to multiple images, successfully achieving stitching without visible seams or errors, providing efficient and reliable technical support for bridge panorama generation. The research outcomes demonstrate significant practical value in bridge inspection, providing robust technical support for safe and efficient bridge inspection. Moreover, our findings offer valuable references for future research and applications in related fields. Full article

Full-length radiography is essential for evaluating spinal deformities, limb length discrepancies, and preoperative planning in orthopedics, yet the measurement accuracy of different radiographic methods remains unclear. This phantom study compared the accuracy of rotational stitching, one-shot and slot-scanning full-length radiography across six radiographic systems in quantifying distances between anatomical landmarks. Measurement errors were statistically analyzed using appropriate nonparametric tests. The results demonstrated significant differences in measurement accuracy among the three methods (H (2) = 15.86, p < 0.001). Slot-scanning exhibited the highest accuracy, with a mean error of −1.19 ± 10.13 mm, while both rotational stitching and one-shot imaging showed greater systematic underestimation, with mean errors of −18.95 ± 13.77 mm and −15.32 ± 12.38 mm, respectively. These negative biases (approximately 1.9 cm and 1.5 cm) are clinically meaningful because, if unrecognized, they can alter mechanical axis estimation and alignment planning in procedures such as high tibial osteotomy (HTO). Post hoc analysis confirmed the superior accuracy of slot-scanning compared to the other two methods, while no significant difference was found between rotational stitching and one-shot imaging. These findings indicate that system choice substantially impacts measurement accuracy, supporting preferential use of slot-scanning when precise quantitative assessment is required. Full article

Autonomous ground vehicles (AGVs) are of major importance in exploration missions since they perform difficult tasks in changing or harmful environments. Mapping and exploration is crucial in hazardous areas, or areas inaccessible to humans, demanding autonomous navigation. This paper proposes a lightweight, low-cost AGV platform, which will be used in resource-constrained situations and aimed at scenarios like exploration missions (e.g., cave interiors, biohazard environments, or fire-stricken buildings) where there are serious security threats to humans. The proposed system relies on simple ultrasonic sensors when navigating and applied traversal algorithms (e.g., BFS, DFS, or $A^{*}$) during path planning. Since on-board microcomputers have limited memory, the traversal data and direction decisions are stored in a file located on an SD card, which supports long-term, energy-saving navigation and risk-free backtracking. A fish-eye camera set on a servo motor captures three photos ordered from left to right and stores them on the SD card for further off-line processing, integrating each frame into a low-frame-rate video. Moreover, when the battery level falls below 50%, the exploration path does not extend further and the AGV returns to the base station, thus combining a secure backtracking procedure with energy-efficient decisions. The resultant platform is low-cost, modular, and efficient at augmenting; thus it is suitable for exploring missions with applications in search and rescue, educational robotics, and real-time applications in low-infrastructure environments. Full article

The generation of 360° video is gaining prominence in immersive media, virtual reality (VR), gaming projects, and the emerging metaverse. Traditional methods for panoramic content creation often rely on specialized hardware and dense video capture, which limits scalability and accessibility. Recent advances in generative artificial intelligence, particularly diffusion models and neural radiance fields (NeRFs), are examined in this research for their potential to generate immersive panoramic video content from minimal input, such as a sparse set of narrow-field-of-view (NFoV) images. To investigate this, a structured literature review of over 70 recent papers in panoramic image and video generation was conducted. We analyze key contributions from models such as 360DVD, Imagine360, and PanoDiff, focusing on their approaches to motion continuity, spatial realism, and conditional control. Our analysis highlights that achieving seamless motion continuity remains the primary challenge, as most current models struggle with temporal consistency when generating long sequences. Based on these findings, a research direction has been proposed that aims to generate 360° video from as few as 8–10 static NFoV inputs, drawing on techniques from image stitching, scene completion, and view bridging. This review also underscores the potential for creating scalable, data-efficient, and near-real-time panoramic video synthesis, while emphasizing the critical need to address temporal consistency for practical deployment. Full article

With the advancement of precision agriculture, Unmanned Aerial Vehicle (UAV)-based remote sensing has been increasingly employed for monitoring crop water and nutrient status due to its high flexibility, fine spatial resolution, and rapid data acquisition capabilities. This review systematically examines recent research progress and key technological pathways in UAV-based remote sensing for crop water and nutrient monitoring. It provides an in-depth analysis of UAV platforms, sensor configurations, and their suitability across diverse agricultural applications. The review also highlights critical data processing steps—including radiometric correction, image stitching, segmentation, and data fusion—and compares three major modeling approaches for parameter inversion: vegetation index-based, data-driven, and physically based methods. Representative application cases across various crops and spatiotemporal scales are summarized. Furthermore, the review explores factors affecting monitoring performance, such as crop growth stages, spatial resolution, illumination and meteorological conditions, and model generalization. Despite significant advancements, current limitations include insufficient sensor versatility, labor-intensive data processing chains, and limited model scalability. Finally, the review outlines future directions, including the integration of edge intelligence, hybrid physical–data modeling, and multi-source, three-dimensional collaborative sensing. This work aims to provide theoretical insights and technical support for advancing UAV-based remote sensing in precision agriculture. Full article

Background: Urethral strictures impact millions, causing significant morbidity and millions in healthcare costs. Testing new interventions is limited by the lack of inexpensive urethral healing models. We developed an ex vivo model of early urethral wound healing using explanted rabbit urethral tissue. This was used to test the impact of six growth factors (GFs). Methods: The rabbit urethra was detubularized by cutting it between the corpora cavernosa, and then it was stitched flat using a custom 3D-printed platform. The tissue was carefully scratched to produce a visible wound, and the specimens were placed in media containing growth factors at 100 ng/mL and 10 ng/mL. Images were taken at 0, 24, 48, 72, and 96 h, and the wound area was measured by blinded reviewers to determine the rate of wound contraction. Results: Specimens with IGF at 100 ng/mL showed a statistically significant difference in wound contraction when compared to those with GF-free control medium, showing that IGF-1 supports early urethral epithelization and may improve healing. Conclusions: The developed protocol provides a simple explant platform that can be used to investigate methods of enhancing early phases of urethral healing or used to investigate other areas of urethral health, including drug delivery, infection, and mechanical properties. Full article

This study evaluates the effectiveness of transfer learning with pre-trained convolutional neural networks (CNNs) for the automated binary classification of surgical suture quality (high-quality/low-quality) using photographs of three suture types: interrupted open vascular sutures (IOVS), continuous over-and-over open sutures (COOS), and interrupted laparoscopic sutures (ILS). To address the challenge of limited medical data, eight state-of-the-art CNN architectures—EfficientNetB0, ResNet50V2, MobileNetV3Large, VGG16, VGG19, InceptionV3, Xception, and DenseNet121—were trained and validated on small datasets (100–190 images per type) using 5-fold cross-validation. Performance was assessed using the F1-score, AUC-ROC, and a custom weighted stability-aware score (Score_adj). The results demonstrate that transfer learning achieves robust classification (F1 > 0.90 for IOVS/ILS, 0.79 for COOS) despite data scarcity. ResNet50V2, DenseNet121, and Xception were more stable by Score_adj, with ResNet50V2 achieving the highest AUC-ROC (0.959 ± 0.008) for IOVS internal view classification. GradCAM visualizations confirmed model focus on clinically relevant features (e.g., stitch uniformity, tissue apposition). These findings validate transfer learning as a powerful approach for developing objective, automated surgical skill assessment tools, reducing reliance on subjective expert evaluations while maintaining accuracy in resource-constrained settings. Full article

To achieve robust and accurate collaborative 3D measurement under complex noise conditions, a global calibration method for dual-arm hand–eye systems and multi-view 3D imaging is proposed. A multi-view 3D scanning approach based on ICP (M3DHE-ICP) integrates a multi-frequency heterodyne coding phase solution with ICP optimization, effectively correcting stitching errors caused by robotic arm attitude drift. After correction, the average 3D imaging error is 0.082 mm, reduced by 0.330 mm. A global calibration method based on encoded marker points (GCM-DHE) is also introduced. By leveraging spatial geometry constraints and a dynamic tracking model of marker points, the transformation between multi-coordinate systems of the dual arms is robustly solved. This reduces the average imaging error to 0.100 mm, 0.456 mm lower than that of traditional circular calibration plate methods. In actual engineering measurements, the average error for scanning a vehicle’s front mudguard is 0.085 mm, with a standard deviation of 0.018 mm. These methods demonstrate significant value for intelligent manufacturing and multi-robot collaborative measurement. Full article

Wide-angle images often suffer from severe radial distortion, compromising geometric accuracy and challenging image correction and real-time stitching, especially in resource-constrained embedded environments. To address this, this study proposes a wide-angle image correction and stitching framework based on a Swin Transformer, optimized for lightweight deployment on edge devices. The model integrates multi-scale feature extraction, Thin Plate Spline (TPS) control point prediction, and optical flow-guided constraints, balancing correction accuracy and computational efficiency. Experiments on synthetic and real-world datasets show that the method outperforms mainstream algorithms, with PSNR gains of 3.28 dB and 2.18 dB on wide-angle and fisheye images, respectively, while maintaining real-time performance. To validate practical applicability, the model is deployed on a Jetson TX2 NX device, and a real-time dual-camera stitching system is built using C++ and DeepStream. The system achieves 15 FPS at 1400 × 1400 resolution, with a correction latency of 56 ms and stitching latency of 15 ms, demonstrating efficient hardware utilization and stable performance. This study presents a deployable, scalable, and edge-compatible solution for wide-angle image correction and real-time stitching, offering practical value for applications such as smart surveillance, autonomous driving, and industrial inspection. Full article

The health of road tunnel linings directly impacts traffic safety and requires regular inspection. Appearance defects on tunnel linings can be measured through images scanned by cameras mounted on a car to avoid disrupting traffic. Existing tunnel lining mobile scanning methods often fail in image stitching due to the lack of corresponding feature points in the lining images, or require complex, time-consuming algorithms to eliminate stitching seams caused by the same issue. This paper proposes a mobile scanning method aided by collimated lasers, which uses lasers as corresponding points to assist with image stitching to address the problems. Additionally, the lasers serve as structured light, enabling the measurement of image projection relationships. An inspection car was developed based on this method for the experiment. To ensure operational flexibility, a single checkerboard was used to calibrate the system, including estimating the poses of lasers and cameras, and a Laplace kernel-based algorithm was developed to guarantee the calibration accuracy. Experiments show that the performance of this algorithm exceeds that of other benchmark algorithms, and the proposed method produces nearly seamless, measurable tunnel lining images, demonstrating its feasibility. Full article

Real-time 3D reconstruction in minimally invasive surgery improves depth perception and supports intraoperative decision-making and navigation. However, endoscopic imaging presents significant challenges, such as specular reflections, low-texture surfaces, and tissue deformation. We present a novel, deterministic and iterative stereo-matching method based on adaptive support weights that is tailored to these constraints. The algorithm is implemented in CUDA and C++ to enable real-time performance. We evaluated our method on the Stereo Correspondence and Reconstruction of Endoscopic Data (SCARED) dataset and a custom synthetic dataset using the mean absolute error (MAE), root mean square error (RMSE), and frame rate as metrics. On SCARED datasets 8 and 9, our method achieves MAEs of 3.79 mm and 3.61 mm, achieving 24.9 FPS on a system with an AMD Ryzen 9 5950X and NVIDIA RTX 3090. To the best of our knowledge, these results are on par with or surpass existing deterministic stereo-matching approaches. On synthetic data, which eliminates real-world imaging errors, the method achieves an MAE of 140.06 μm and an RMSE of 251.9 μm, highlighting its performance ceiling under noise-free, idealized conditions. Our method focuses on single-shot 3D reconstruction as a basis for stereo frame stitching and full-scene modeling. It provides accurate, deterministic, real-time depth estimation under clinically relevant conditions and has the potential to be integrated into surgical navigation, robotic assistance, and augmented reality workflows. Full article

Sugarcane yield prediction plays a pivotal role in enabling farmers to monitor crop development and optimize cultivation practices, guiding harvesting operations for sugar mills. In this study, we established three experimental fields, which were planted with three main sugarcane cultivars in Guangxi, China, respectively, implementing a multi-gradient fertilization design with 39 plots and 810 sampling grids. Multispectral imagery was acquired by unmanned aerial vehicles (UAVs) during five critical growth stages: mid-tillering (T1), late-tillering (T2), mid-elongation (T3), late-elongation (T4), and maturation (T5). Following rigorous image preprocessing (including stitching, geometric correction, and radiometric correction), 16 VIs were extracted. To identify yield-sensitive vegetation indices (VIs), a spectral feature selection criterion combining gray relational analysis and correlation analysis (GRD-r) was proposed. Subsequently, three supervised learning algorithms—Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Support Vector Machine (SVM)—were employed to develop both single-stage and multi-stage yield prediction models. Results demonstrated that multi-stage models consistently outperformed their single-stage counterparts. Among the single-stage models, the RF model using T3-stage features achieved the highest accuracy (R² = 0.78, RMSE_V = 7.47 t/hm²). The best performance among multi-stage models was obtained using a GBDT model constructed from a combination of DVI (T1), NDVI (T2), TDVI (T3), NDVI (T4), and SRPI (T5), yielding R² = 0.83 and RMSE_V = 6.63 t/hm². This study highlights the advantages of integrating multi-temporal spectral features and advanced machine learning techniques for improving sugarcane yield prediction, providing a theoretical foundation and practical guidance for precision agriculture and harvest logistics. Full article

Flatfoot, or pes planus, is a condition where the foot’s arch collapses, leading to complications such as pain, gait abnormalities, and an increased risk of injury. Accurate and early diagnosis is critical for effective treatment. Traditional diagnostic methods, including radiographic imaging, footprint analysis, and plantar pressure measurement, often require specialized equipment and are subjective. This study proposes a novel diagnostic device that captures 2D plantar foot images to calculate key morphological indices, including the Staheli Index, Clark’s Angle, and Chippaux–Smirak Index, for flatfoot detection. The device, designed with off-the-shelf components, includes a transparent toughened glass platform and LED illumination to capture images using web cameras. A Python-based application was developed for image acquisition, segmentation, and stitching. The device was tested on 55 participants aged 18–28, and the extracted morphological indices were validated against established thresholds for flatfoot diagnosis. The results showed that the Staheli Index, Chippaux–Smirak Index, and Clark’s Angle reliably detected flatfoot in participants. The study highlights the potential of this device for non-invasive, accurate, and rapid flatfoot diagnosis. Future advancements in deep learning could enhance its capabilities, making it a valuable tool for proactive healthcare in foot deformity detection. Full article