Search Results (2,634)

The correlation analysis between current surface cracks of structures and external loads can provide important insights into determining the structural residual bearing capacity. The classical regression assessment method based on experimental data not only relies on costly structure experiments; it also lacks interpretability. Therefore, a novel load estimation method for RC beams, based on correlation analysis between detected crack images and strain contour plots calculated by FEM, is proposed. The distinct discrepancies between crack images and strain contour figures, coupled with the stochastic nature of actual crack distributions, pose considerable challenges for load estimation tasks. Therefore, a new correlation index model is initially introduced to quantify the correlation between the two types of images in the proposed method. Subsequently, a deep neural network (DNN) is trained as a FEM surrogate model to quickly predict the structural strain response by considering material uncertainties. Ultimately, the range of the optimal load level and its confidence interval are determined via statistical analysis of the load estimations under different random fields. The validation results of RC beams under four-point bending loads show that the proposed algorithm can quickly estimate load levels based on numerical simulation results, and the mean absolute percentage error (MAPE) for load estimation based solely on a single measured structural crack image is 20.68%. Full article

Drowsy driving contributes to over 6000 fatal incidents annually in the US, underscoring the need for effective, non-intrusive drowsiness detection. This study seeks to address detection challenges, particularly in non-standard head positions. Our innovative approach leverages computer vision by combining facial feature detection using Dlib, head pose estimation with the HOPEnet model, and analyses of the percentage of eyelid closure over time (PERCLOS) and the percentage of mouth opening over time (POM). These are integrated with traditional machine learning models, such as Support Vector Machines, Random Forests, and XGBoost. These models were chosen for their ability to process detailed information from facial landmarks, head poses, PERCLOS, and POM. They achieved a high overall accuracy of 86.848% in detecting drowsiness, with a small overall model size of 5.05 MB and increased computational efficiency. The models were trained on the National Tsing Hua University Driver Drowsiness Detection Dataset, making them highly suitable for devices with a limited computational capacity. Compared to the baseline model from the literature, which achieved an accuracy of 84.82% and a larger overall model size of 37.82 MB, the method proposed in this research shows a notable improvement in the efficiency of the model with relatively similar accuracy. These findings provide a framework for future studies, potentially improving sleepiness detection systems and ultimately saving lives by enhancing road safety. Full article

Humanity has always aspired beyond the human. The technological development in recent decades has been extraordinary, leading to new attempts to overcome the all-too-human condition. We dream of conquering death, upgrading our bodies into perfect performance machines and enhancing our intelligence through bio-nanotechnology. We are familiar with the side effects: alienation, stress, anxiety, depression. This article contends that Franz Kafka’s enigmatic oeuvre at its core harbors a yearning to transcend the human. Through a close reading of the narrative In the Penal Colony, it is demonstrated that this yearning is far more radical and uncompromising than the modern vision of extending and optimizing human life. Instead of the modern ego-concerned affirmation of life and the body that hides behind much of AI and modern technology, Kafka seeks a radical vision of total transformation and transcending the human into ‘nothingness’. The article shows that this transformation corresponds to core concepts in Arthur Schopenhauer’s philosophy, primarily his doctrine of the denial of the will to live and asceticism. Instead of the species-narcissistic affirmation of life and the body that lurks behind much of AI and modern technology, Kafka strives for a definitive overcoming of the life we desire. Full article

Portland cement concrete is widely used in road construction due to its durability and minimal maintenance needs. However, its susceptibility to spall highlights the drawbacks of conventional repair methods, including cost inefficiencies, delays, environmental impacts, and safety risks from road closures. To address these challenges, this study evaluated the environmental benefits of a spall detection and repair method employing artificial-intelligence-based computer vision technology. By utilizing machine vision techniques, this approach detects spall damage without road closures and automates the calculation of repair areas and material requirements through a proprietary estimation program. Environmental impact assessments were conducted using life cycle assessment across three frameworks, TRACI, ReCiPe, and ILCD, to compare this method with conventional practices. The results revealed a 79% reduction in the overall environmental impacts, including significant decreases in global warming due to shorter road closures and reduced material waste. Resource usage improved through optimized processes, and air pollution decreased, with lower emissions of smog and particulates. This study highlights the potential of machine-vision-driven repair material quantity takeoff as a more efficient and sustainable alternative. The results of this study will help institutional engineers and practitioners adopt sustainable strategies for green infrastructure repair and integrate them into various infrastructure maintenance practices to contribute to the development of sustainable urban environments. Full article

The present work constitutes the initial experimental effort to characterise the dynamic tensile performance of basalt fibre grids employed in TRM systems. The tensile behaviour of a bi-directional basalt fibre grid was explored using a high-speed servo-hydraulic testing machine with specialised grips. Deformation and failure modes were captured using a high-speed camera. Tensile strain values were extracted from the recorded images using the MATLAB computer vision tool, ‘vision.PointTracker’. The specimens, consisting of one and four rovings, were tested at intermediate (1–8/s) and quasi-static (10⁻³/s) strain rates. After the tensile tests, scanning electron microscopy (SEM) analyses were performed to examine the microscopic failure of the material. Linear and non-linear stress–strain behaviours were observed in the range of 10⁻³ to 1/s and 4 to 8/s, respectively. Tensile strength, ultimate strain, toughness, and elastic modulus increased at intermediate strain rates. Overall, the dynamic increase factors for these properties, except for the latter, were between 1.4 and 2.3. At the macroscopic level, the grid failed in a brittle manner. However, microscopic analyses revealed that the failure modes of the fibre and polymer coating were strain-rate sensitive. The enhanced tensile performance of the grid under dynamic loading conditions rendered it suitable for retrofitting structures prone to extreme loading conditions. Full article

The transition from Industry 4.0 to Industry 5.0 gives more prominence to human-centered and sustainable manufacturing practices. This paper proposes a conceptual design framework based on Vision Transformers (ViTs) and digital twins, to meet the demands of Industry 5.0. ViTs, known for their advanced visual data analysis capabilities, complement the simulation and optimization capabilities of digital twins, which in turn can enhance predictive maintenance, quality control, and human–machine symbiosis. The applied framework is capable of analyzing multidimensional data, integrating operational and visual streams for real-time tracking and application in decision making. Its main characteristics are anomaly detection, predictive analytics, and adaptive optimization, which are in line with the objectives of Industry 5.0 for sustainability, resilience, and personalization. Use cases, including predictive maintenance and quality control, demonstrate higher efficiency, waste reduction, and reliable operator interaction. In this work, the emergent role of ViTs and digital twins in the development of intelligent, dynamic, and human-centric industrial ecosystems is discussed. Full article

Foggy weather poses significant challenges to outdoor computer vision tasks, such as object detection, by degrading image quality and reducing algorithm reliability. In this paper, we present a novel model for estimating fog density in outdoor scenes, aiming to enhance object detection performance under varying foggy conditions. Using a support vector machine (SVM) classification framework, the proposed model categorizes unknown images into distinct fog density levels based on both global and local fog-relevant features. Key features such as entropy, contrast, and dark channel information are extracted to quantify the effects of fog on image clarity and object visibility. Moreover, we introduce an innovative region selection method tailored to images without detectable objects, ensuring robust feature extraction. Evaluation on synthetic datasets with varying fog densities demonstrates a classification accuracy of 85.8%, surpassing existing methods in terms of correlation coefficients and robustness. Beyond accurate fog density estimation, this approach provides valuable insights into the impact of fog on object detection, contributing to safer navigation in foggy environments. Full article

Wheat is a globally cultivated cereal crop with substantial protein content present in its seeds. This research aimed to develop robust methods for predicting seed protein concentration in wheat seeds using bench-top hyperspectral imaging in the visible, near-infrared (VNIR), and shortwave infrared (SWIR) regions. To fully utilize the spectral and texture features of the full VNIR and SWIR spectral domains, a computer-vision-aided image co-registration methodology was implemented to seamlessly align the VNIR and SWIR bands. Sensitivity analyses were also conducted to identify the most sensitive bands for seed protein estimation. Convolutional neural networks (CNNs) with attention mechanisms were proposed along with traditional machine learning models based on feature engineering including Random Forest (RF) and Support Vector Machine (SVM) regression for comparative analysis. Additionally, the CNN classification approach was used to estimate low, medium, and high protein concentrations because this type of classification is more applicable for breeding efforts. Our results showed that the proposed CNN with attention mechanisms predicted wheat protein content with R² values of 0.70 and 0.65 for ventral and dorsal seed orientations, respectively. Although, the R² of the CNN approach was lower than of the best performing feature-based method, RF (R² of 0.77), end-to-end prediction capabilities with CNN hold great promise for the automation of wheat protein estimation for breeding. The CNN model achieved better classification of protein concentrations between low, medium, and high protein contents, with an R² of 0.82. This study’s findings highlight the significant potential of hyperspectral imaging and machine learning techniques for advancing precision breeding practices, optimizing seed sorting processes, and enabling targeted agricultural input applications. Full article

In order to plan suitable navigation operation paths for the characteristics of rice fields in the middle and lower reaches of the Yangtze River and the operational requirements of straw rotary burying, this paper proposes a combination of the Hough matrix and RANSAC algorithms to extract the starting routes of straw boundaries; the algorithm adopts the Hough matrix to extract the characteristic points of the straw boundaries and remove the redundancies, and then reduces the influence of noise points caused by different straw shapes using the RANSAC algorithm to improve the accuracy of the starting route extraction. The algorithm extracts the starting routes of straw boundaries and the characteristic points of the straw boundaries and removes the redundancies, so as to improve the accuracy of the starting route extraction. The extraction test shows that under different scenes, the recognition accuracy of the path extraction method combining the Hough matrix and RANSAC algorithm is above 90%, and the algorithm takes no more than 0.51 s. Finally, the road test shows that the method meets the characteristics of tractor operation with a large turning radius and without reversing and satisfies the unmanned operation requirements of straw rotary burying in the field. Full article

The positioning of lithium battery tabs in electric vehicles is a crucial aspect of the power battery assembly process. During the pre-tightening process of the lithium battery stack assembly, cells and foams undergo different deformations, leading to varying displacements of cells at different levels. Consequently, determining tab positions poses numerous challenges during the pre-tightening process of the stack assembly. To address these challenges, this paper proposes a method for detecting feature points and calculating the displacement of lithium battery stack tabs based on the MicKey method. This research focuses on the cell tab, utilizing the hue, saturation, and value (HSV) color space for image segmentation to adaptively extract the cell tab region and further obtain the ROI of the cell tab. In order to enhance the accuracy of tab displacement calculation, a novel method for feature point detection and displacement calculation of lithium battery stacks based on the MicKey (Metric Keypoints) method is introduced. MicKey can predict the coordinates of corresponding keypoints in the 3D camera space through keypoint matching based on neural networks, and it can acquire feature point pairs of the subject to be measured through its unique depth reduction characteristics. Results demonstrate that the average displacement error and root mean square error of this method are 0.03 mm and 0.04 mm, respectively. Compared to other feature matching algorithms, this method can more consistently and accurately detect feature points and calculate displacements, meeting the positioning accuracy requirements for the stack pole ear in the actual assembly process. It provides a theoretical foundation for subsequent procedures. Full article

Tomatoes are among the most widely cultivated and consumed vegetable crops worldwide. They are usually harvested in large quantities that need to be promptly and accurately classified into healthy and defective categories. Traditional methods for tomato classification are labor-intensive and prone to human error. Therefore, this study proposes an approach that leverages feature fusion from two pre-trained convolutional neural networks (CNNs), VGG16 and ResNet-50, to enhance classification performance. A comprehensive evaluation of multiple individual and hybrid classifiers was conducted on a dataset of 43,843 tomato images, which is heavily imbalanced toward the healthy class. The results showed that the best-performing classifier on fused features achieved an average precision (AP) and accuracy of 0.92 and 0.97, respectively, on the test set. In addition, the experimental evaluation revealed that fused features improved classification performance across multiple metrics, including accuracy, AP, recall, and F1-score, compared to individual features of VGG16 and ResNet-50. Furthermore, the proposed approach was benchmarked against three standalone CNN models, namely MobileNetV2, EfficientNetB0, and DenseNet121, and demonstrated superior performance in all evaluated metrics. These findings highlight the efficacy of deep feature fusion in addressing class imbalance and improving automated tomato defect detection. Full article

Biogenic reefs support marine biodiversity and play a key role in a healthy marine environment. Protecting and enhancing reef-building species, such as Sabellaria spinulosa, require mapping and monitoring strategies. A multi-scale and multi-sensor mapping campaign, including a multi-beam echosounder, side-scan sonar (SSS), box corer and ROV with an attached video camera, has been carried out in the northern Brown Bank (Dutch Continental Shelf) in August 2023. A semi-automated classification workflow, based on a support vector machine (machine learning), was developed to map Sabellaria reefs using SSS and video data. Elevated Sabellaria reefs were classified with a precision and sensitivity of 52% and 49%, respectively. The classified SSS images were merged into full-coverage percentage maps of Sabellaria reef coverage. Located between the swales of the tidal ridges, it was estimated that the reefs cover an area of 3.8 to 5.7% within the surveyed areas. The maps indicate (1) on the large-scale a preference of Sabellaria spinulosa for settlement to the east of the deepest part of the swale and (2) on the small-scale a preference for the troughs towards the stoss side of the megaripples. The employed survey strategy and the developed classification workflow can be extended to other environmental areas and further developed into a standard monitoring procedure. Full article

This paper presents a comprehensive overview of cutting-edge autonomous forklifts, with a strong emphasis on sensors, object detection and system functionality. It aims to explore how this technology is evolving and where it is likely headed in both the near and long-term future, while also highlighting the latest developments in both academic research and industrial applications. Given the critical importance of object detection and recognition in machine vision and autonomous vehicles, this area receives particular attention. The article provides an in-depth summary of both commercial and prototype forklifts, discussing key aspects such as design features, capabilities and benefits, and offers a detailed technical comparison. Specifically, it clarifies that all available data pertains to commercially available forklifts. To obtain a better understanding of the current state-of-the-art and its limitations, the analysis also reviews commercially available autonomous forklifts. Finally, this paper includes a comprehensive bibliography of research findings in this field. Full article

Object detection is a pivotal research domain within computer vision, with applications spanning from autonomous vehicles to medical diagnostics. This comprehensive survey presents an in-depth analysis of the evolution and significant advancements in object detection, emphasizing the critical role of machine learning (ML) and deep learning (DL) techniques. We explore a wide spectrum of methodologies, ranging from traditional approaches to the latest DL models, thoroughly evaluating their performance, strengths, and limitations. Additionally, the survey delves into various metrics for assessing model effectiveness, including precision, recall, and intersection over union (IoU), while addressing ongoing challenges in the field, such as managing occlusions, varying object scales, and improving real-time processing capabilities. Furthermore, we critically examine recent breakthroughs, including advanced architectures like Transformers, and discuss challenges and future research directions aimed at overcoming existing barriers. By synthesizing current advancements, this survey provides valuable insights for enhancing the robustness, accuracy, and efficiency of object detection systems across diverse and challenging applications. Full article

As highway tunnel operations continue over time, structural defects, particularly cracks, have been observed to increase annually. Coupled with the rapid expansion of tunnel networks, traditional manual inspection methods have proven inadequate to meet current demands. In recent years, machine vision and deep learning technologies have gained significant attention in civil engineering for the detection and analysis of structural defects. However, rapid and accurate defect identification in highway tunnels presents challenges due to complex background conditions, numerous interfering factors, and the relatively low proportion of cracks within the structure. Additionally, the intensive labor requirements and limited efficiency in labeling training datasets for deep learning pose significant constraints on the deployment of intelligent crack segmentation algorithms. To address these limitations, this study proposes an automatic labeling and optimization algorithm for crack sample sets, utilizing crack features and the watershed algorithm to enable efficient automated segmentation with minimal human input. Furthermore, the deep learning-based crack segmentation network was optimized through comparative analysis of various network depths and residual structure configurations to achieve the best possible model performance. Enhanced accuracy was attained by incorporating axis extraction and watershed filling algorithms to refine segmentation outcomes. Under diverse lining surface conditions and multiple interference factors, the proposed approach achieved a crack segmentation accuracy of 98.78%, with an Intersection over Union (IoU) of 72.41%, providing a robust solution for crack segmentation in tunnels with complex backgrounds. Full article