Search Results (2,963)

Over the past few years, there has been substantial interest and research activity surrounding the application of Convolutional Neural Networks (CNNs) for post-filtering in video coding. Most current research efforts have focused on using CNNs with various kernel sizes for post-filtering, primarily concentrating on High-Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC). This narrow focus has limited the exploration and application of these techniques to other video coding standards such as AV1, developed by the Alliance for Open Media, which offers excellent compression efficiency, reducing bandwidth usage and improving video quality, making it highly attractive for modern streaming and media applications. This paper introduces a novel approach that extends beyond traditional CNN methods by integrating three different self-attention layers into the CNN framework. Applied to the AV1 codec, the proposed method significantly improves video quality by incorporating these distinct self-attention layers. This enhancement demonstrates the potential of self-attention mechanisms to revolutionize post-filtering techniques in video coding beyond the limitations of convolution-based methods. The experimental results show that the proposed network achieves an average BD-rate reduction of 10.40% for the Luma component and 19.22% and 16.52% for the Chroma components compared to the AV1 anchor. Visual quality assessments further validated the effectiveness of our approach, showcasing substantial artifact reduction and detail enhancement in videos. Full article

Brick warehouses represent interdisciplinary heritage sites developed by social, cultural, and economic impacts. This study aimed to connect warehouse details and GIS maps in augmented reality (AR) based on the former Camphor Refinery Workshop Warehouse. AR was applied as an innovation interface to communicate the differences between construction details, providing a feasible on-site solution for articulating historical brick engineering technology. A complex warehouse cluster was georeferenced by the AR models of brick details. The map was assisted by a smartphone-based comparison of the details of adjacent warehouses. Sixty AR models of warehouse details exemplified the active and sustainable preservation of the historical artifacts. The side-by-side allocation of warehouse details in AR facilitated cross-comparisons of construction differences. We found that a second reconstructed result integrated AR and reality in a novel manner based on the use of a smartphone AR. GIS and AR facilitated a management effort using webpages and cloud access from a remote site. The vocabulary of building details can be enriched and better presented in AR. Full article

A weighting algorithm for application in the Thru-Reflect-Line (TRL) calibration technique is presented to enhance the accuracy and reliability of vector network analyzer (VNA) measurements over broad frequency bands. The method addresses the inherent limitations of the traditional TRL calibration, particularly the step changes observed in banded-TRL approaches when multiple Line standards are used. By introducing a bespoke weighting function that assigns phase-dependent weights to each Line standard, smoother transitions and improved S-parameter measurements can be achieved. Experimental validation using measurements of both 3.5 mm and Type-N devices demonstrates the effectiveness of the weighted-TRL method in eliminating discontinuities and calibration artifacts across a wide range of frequencies. The results reveal the improved calibration of S-parameters this approach can yield compared to traditional TRL calibration methods. The developed weighted-TRL calibration technique offers a significant advancement in metrology-grade measurements, enabling more precise characterization of high-frequency devices across broad frequency bands. By mitigating a key limitation of the TRL calibration, this method provides a valuable tool for enhancing the accuracy and reliability of VNA measurements for precision metrology applications. Full article

Paraloid B-72 (B72), as a transparent, colorless polymer material, has good film-forming ability when dissolved in acetone and is widely used as a sealing material for metal artifacts. In order to analyze and evaluate the preservation performance of B72 as a sealing material on the substrate of metal artifacts, a variety of electrochemical methods, mainly electrochemical noise (EN), and scanning electron microscopy (SEM) were applied to evaluate the B72 coating. The results showed that the B72 coating had a good preservation effect at the initial stage, and its poor water resistance led to the loss of its effectiveness after a few days of immersion. Compared with conventional electrochemical methods, electrochemical noise is non-destructive, which cannot cause new corrosion on the metal substrate and can well characterize the corrosion rate of the test system, and the results of its time domain and frequency domain analyses can correspond well with the polarization resistance and impedance spectra. Electrochemical noise is an effective method for evaluating the anti-corrosion performance of material preservation coatings. Full article

Monitoring aircraft using synthetic aperture radar (SAR) images is a very important task. Given its coherent imaging characteristics, there is a large amount of speckle interference in the image. This phenomenon leads to the scattering information of aircraft targets being masked in SAR images, which is easily confused with background scattering points. Therefore, automatic detection of aircraft targets in SAR images remains a challenging task. For this task, this paper proposes a framework for speckle reduction preprocessing of SAR images, followed by the use of an improved deep learning method to detect aircraft in SAR images. Firstly, to improve the problem of introducing artifacts or excessive smoothing in speckle reduction using total variation (TV) methods, this paper proposes a new nonconvex total variation (NTV) method. This method aims to ensure the effectiveness of speckle reduction while preserving the original scattering information as much as possible. Next, we present a framework for aircraft detection based on You Only Look Once v8 (YOLOv8) for SAR images. Therefore, the complete framework is called SAR-NTV-YOLOv8. Meanwhile, a high-resolution small target feature head is proposed to mitigate the impact of scale changes and loss of depth feature details on detection accuracy. Then, an efficient multi-scale attention module was proposed, aimed at effectively establishing short-term and long-term dependencies between feature grouping and multi-scale structures. In addition, the progressive feature pyramid network was chosen to avoid information loss or degradation in multi-level transmission during the bottom-up feature extraction process in Backbone. Sufficient comparative experiments, speckle reduction experiments, and ablation experiments are conducted on the SAR-Aircraft-1.0 and SADD datasets. The results have demonstrated the effectiveness of SAR-NTV-YOLOv8, which has the most advanced performance compared to other mainstream algorithms. Full article

Nitrite/nitrate poisoning is an emerging problem, with an ongoing escalation of reported self-administration with suicidal intent in several countries. Nitrites toxicity mainly consists of their interaction with hemoglobin (Hb), causing its oxidization to methemoglobin (MetHb). In order to give support to the correct procedures for the analysis of these cases, this study aims to evaluate spontaneous sample degradation and consequent MetHb formation in the typical storage conditions of a forensic toxicology laboratory. Two different types of samples have been used in this study: the first stage of our study consisted of a retrospective analysis of blood samples obtained by judicial autopsies already stored in the toxicology laboratory, collected over four years (2018–2021), while the samples used for the second stage were appositely collected during judicial autopsies. The data obtained by the application of a derivative spectrophotometry method on these samples suggest that there seems not to be a maximum threshold for MetHb formation within which it is possible to state with a sufficient grade of certainty that the concentration of MetHb found is consistent with an ante-mortem formation and is not the result of an artifact due to sample degradation and storage conditions. On the other hand, the results suggest that MetHb formation depends on the time passed between sample collection and analysis, so that a tempestive sample processing, performed as soon as the samples are received in the laboratory, is crucial to obtain the maximum reliability and diagnostic values from the data when MetHb quantitation is necessary. Full article

Advanced video codecs such as High Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC) are vital for streaming high-quality online video content, as they compress and transmit data efficiently. However, these codecs can occasionally degrade video quality by adding undesirable artifacts such as blockiness, blurriness, and ringing, which can detract from the viewer’s experience. To ensure a seamless and engaging video experience, it is essential to remove these artifacts, which improves viewer comfort and engagement. In this paper, we propose a deep feature fusion based convolutional neural network (CNN) architecture (VVC-PPFF) for post-processing approach to further enhance the performance of VVC. The proposed network, VVC-PPFF, harnesses the power of CNNs to enhance decoded frames, significantly improving the coding efficiency of the state-of-the-art VVC video coding standard. By combining deep features from early and later convolution layers, the network learns to extract both low-level and high-level features, resulting in more generalized outputs that adapt to different quantization parameter (QP) values. The proposed VVC-PPFF network achieves outstanding performance, with Bjøntegaard Delta Rate (BD-Rate) improvements of 5.81% and 6.98% for luma components in random access (RA) and low-delay (LD) configurations, respectively, while also boosting peak signal-to-noise ratio (PSNR). Full article

Archaeological investigations worldwide have focused on when and how humans permanently settled in high-altitude environments. Recent evidence from Xiada Co, Qusongguo, and Dingzhonghuzhuzi in western Tibet, where lithic artifacts and radiocarbon dates with original deposits were first accessed, provides new insights into human activities in this extreme environment during the early Holocene. This paper examines the mobility and land-use patterns of foragers in western Tibet from the perspectives of lithic analysis. Assemblages from three sites suggest homogenous technologies and raw material use, as well as potential interaction network of hunter-gatherers within the plateau during the early Holocene. It further argues that the material exponents and travel cost models of site location supported permanent occupation of the western Tibetan Plateau in this period. Full article

Background: Age-related macular degeneration (AMD) is a complex eye disorder with an environmental and genetic origin, affecting millions worldwide. The study aims to explore the association between retinal morphology and the polygenic risk score (PRS) for AMD using fundus images and deep learning techniques. Methods: The study used and pre-processed 23,654 fundus images from 332 subjects (235 patients with AMD and 97 controls), ultimately selecting 558 high-quality images for analysis. The fine-tuned DenseNet121 deep learning model was employed to estimate PRS from single fundus images. After training, deep features were extracted, fused, and used in machine learning regression models to estimate PRS for each subject. The Grad-CAM technique was applied to examine the relationship between areas of increased model activity and the retina’s morphological features specific to AMD. Results: Using the hybrid approach improved the results obtained by DenseNet121 in 5-fold cross-validation. The final evaluation metrics for all predictions from the best model from each fold are MAE = 0.74, MSE = 0.85, RMSE = 0.92, R² = 0.18, MAPE = 2.41. Grad-CAM heatmap evaluation showed that the model decisions rely on lesion area, focusing mostly on the presence of drusen. The proposed approach was also shown to be sensitive to artifacts present in the image. Conclusions: The findings indicate an association between fundus images and AMD PRS, suggesting that deep learning models may effectively estimate genetic risk for AMD from retinal images, potentially aiding in early detection and personalized treatment strategies. Full article

Captured images often suffer from issues like color distortion, detail loss, and significant noise. Therefore, it is necessary to improve image quality for reliable threat detection. Balancing brightness enhancement with the preservation of natural colors and details is particularly challenging in low-light image enhancement. To address these issues, this paper proposes an unsupervised low-light image enhancement approach using a U-net neural network with Retinex theory and a Convolutional Block Attention Module (CBAM). This method leverages Retinex-based decomposition to separate and enhance the reflectance map, ensuring visibility and contrast without introducing artifacts. A local adaptive enhancement function improves the brightness of the reflection map, while the designed loss function addresses illumination smoothness, brightness enhancement, color restoration, and denoising. Experiments validate the effectiveness of our method, revealing improved image brightness, reduced color deviation, and superior color restoration compared to leading approaches. Full article

Introduction and Objective: The aim of this study was to evaluate the coronary arteries in patients undergoing thoracic CT angiography for congenital heart disease, to determine the frequency of detection of coronary artery anomalies in congenital heart diseases, and to determine which type of anomaly is more common in which disease. Materials and Methods: In our investigation, a 128-detector multidetector computed tomography machine was used to perform thorax CT angiography. The acquisition parameters were set to 80–100 kVp based on the patient’s age and mAs that the device automatically determined based on the patient’s weight. During the examination, an intravenous (IV) nonionic contrast material dose of 1–1.5 mL/kg was employed. An automated injector was used to inject contrast material at a rate of 1.5–2 mL/s. In the axial plane, 2.5 mm sections were extracted, and they were rebuilt with 0.625 mm section thickness. Results: Between October 2022 and May 2024, 132 patients who were diagnosed with congenital heart disease by echocardiography and underwent Thorax CT angiography in our department were retrospectively evaluated. Of the evaluated patients, 32 were excluded with exclusion criteria such as patients being younger than 3 months, older than 18 years, insufficient contrast enhancement in imaging and contrast-enhanced imaging, thin vascular structure, and motion and contrast artifacts; the remaining 100 patients were included in this study. The age range of these patients was 3 months to 18 years (mean age 4.4 years). Conclusion: In congenital heart diseases, attention to the coronary arteries on thoracic CT angiography examination in the presence of possible coronary anomalies may provide useful information. Full article

To address the challenges posed by the vast and complex knowledge information in cultural heritage design, such as low knowledge retrieval efficiency and limited visualization, this study proposes a method for knowledge extraction and knowledge graph construction based on graph attention neural networks (GAT). Using Tang Dynasty gold and silver artifacts as samples, we establish a joint knowledge extraction model based on GAT. The model employs the BERT pretraining model to encode collected textual knowledge data, conducts sentence dependency analysis, and utilizes GAT to allocate weights among entities, thereby enhancing the identification of target entities and their relationships. Comparative experiments on public datasets demonstrate that this model significantly outperforms baseline models in extraction effectiveness. Finally, the proposed method is applied to the construction of a knowledge graph for Tang Dynasty gold and silver artifacts. Taking the Gilded Musician Pattern Silver Cup as an example, this method provides designers with a visualized and interconnected knowledge collection structure. Full article

Additive Manufacturing has significantly impacted circular design, expanding the opportunities for designing new artifacts following circular economy principles, e.g., using secondary raw materials. Small-format 3D printing has reached a broader audience of stakeholders, including end-users, when dealing with filament feedstocks from plastic and biomass waste. However, using large-format extrusion-based additive manufacturing with recycled feedstocks remains challenging, resulting in limited applications and awareness among practitioners. This work analyzes the most relevant product applications using large-format material extrusion additive manufacturing with recycled plastics and biomass waste feedstocks. It reviews the case studies from 2010 to mid-2024 dealing with new materials and applications from academic research and practical contexts. The applications were analyzed to outline the current situation and trends for large-format 3D printing with recycled plastics- and biomass-based feedstocks, focusing on secondary raw materials, manufacturability, impact on product aesthetics, application fields, and products. Despite more consolidated sectors, new technical applications using granulate feedstock systems, e.g., transportation, are emerging. Academic research studies new secondary raw materials and distributed practices through large-format 3D printing. Practitioners are exploiting different approaches to design products, optimizing building times, costs, and material usage through different manufacturing strategies, strengthening the product identity by highlighting circularity. Spreading specific expertise could enlarge the range of application sectors and products, as well as foster real-world collaborations and scaling-up. Thanks to this work, new synergies between the research and practical contexts can be encouraged for new circular economy practices, detecting and exploring new scraps, material categories, or Additive Manufacturing processes in the future. Full article

Monitoring heart rate (HR) through photoplethysmography (PPG) signals is a challenging task due to the complexities involved, even during routine daily activities. These signals can indeed be heavily contaminated by significant motion artifacts resulting from the subjects’ movements, which can lead to inaccurate heart rate estimations. In this paper, our objective is to present an innovative necklace sensor that employs low-computational-cost algorithms for heart rate estimation in individuals performing non-abrupt movements, specifically drivers. Our solution facilitates the acquisition of signals with limited motion artifacts and provides acceptable heart rate estimations at a low computational cost. More specifically, we propose a wearable sensor necklace for assessing a driver’s well-being by providing information about the driver’s physiological condition and potential stress indicators through HR data. This innovative necklace enables real-time HR monitoring within a sleek and ergonomic design, facilitating seamless and continuous data gathering while driving. Prioritizing user comfort, the necklace’s design ensures ease of wear, allowing for extended use without disrupting driving activities. The collected physiological data can be transmitted wirelessly to a mobile application for instant analysis and visualization. To evaluate the sensor’s performance, two algorithms for estimating the HR from PPG signals are implemented in a microcontroller: a modified version of the mountaineer’s algorithm and a sliding discrete Fourier transform. The goal of these algorithms is to detect meaningful peaks corresponding to each heartbeat by using signal processing techniques to remove noise and motion artifacts. The developed design is validated through experiments conducted in a simulated driving environment in our lab, during which drivers wore the sensor necklace. These experiments demonstrate the reliability of the wearable sensor necklace in capturing dynamic changes in HR levels associated with driving-induced stress. The algorithms integrated into the sensor are optimized for low computational cost and effectively remove motion artifacts that occur when users move their heads. Full article

Current face-swapping methods often suffer from issues of detail blurriness and artifacts in generating high-quality images due to the inherent complexity in detail processing and feature mapping. To overcome these challenges, this paper introduces the Amazing Face Transformer (AmazingFT), an advanced face-swapping model built upon Generative Adversarial Networks (GANs) and Transformers. The model is composed of three key modules: the Face Parsing Module, which segments facial regions and generates semantic masks; the Amazing Face Feature Transformation Module (ATM), which leverages Transformers to extract and transform features from both source and target faces; and the Amazing Face Generation Module (AGM), which utilizes GANs to produce high-quality swapped face images. Experimental results demonstrate that AmazingFT outperforms existing state-of-the-art (SOTA) methods, significantly enhancing detail fidelity and occlusion handling, ultimately achieving movie-grade face-swapping results. Full article