Hasil untuk "Photography"

Mikhail Uzdiaev, Marina Astapova, Andrey Ronzhin et al.

The deployment of wireless seismic nodal systems necessitates the efficient identification of optimal locations for sensor installation, considering factors such as ground stability and the absence of interference. Semantic segmentation of satellite imagery has advanced significantly, and its application to this specific task remains unexplored. This work presents a baseline empirical evaluation of the U-Net architecture for the semantic segmentation of surfaces applicable for seismic sensor installation. We utilize a novel dataset of Sentinel-2 multispectral images, specifically labeled for this purpose. The study investigates the impact of pretrained encoders (EfficientNetB2, Cross-Stage Partial Darknet53—CSPDarknet53, and Multi-Axis Vision Transformer—MAxViT), different combinations of Sentinel-2 spectral bands (Red, Green, Blue (RGB), RGB+Near Infrared (NIR), 10-bands with 10 and 20 m/pix spatial resolution, full 13-band), and a technique for improving small object segmentation by modifying the input convolutional layer stride. Experimental results demonstrate that the CSPDarknet53 encoder generally outperforms the others (IoU = 0.534, Precision = 0.716, Recall = 0.635). The combination of RGB and Near-Infrared bands (10 m/pixel resolution) yielded the most robust performance across most configurations. Reducing the input stride from 2 to 1 proved beneficial for segmenting small linear objects like roads. The findings establish a baseline for this novel task and provide practical insights for optimizing deep learning models in the context of automated seismic nodal network installation planning.

Davide Antonio Mura, Luca Zedda, Andrea Loddo et al.

Early detection of Trypanosoma parasites is critical for the prompt treatment of trypanosomiasis, a neglected tropical disease that poses severe health and socioeconomic challenges in affected regions. To address the limitations of traditional manual microscopy and prior automated methods, we propose YOLO-Tryppa, a novel YOLO-based framework specifically engineered for the rapid and accurate detection of small Trypanosoma parasites in microscopy images. YOLO-Tryppa incorporates ghost convolutions to reduce computational complexity while maintaining robust feature extraction and introduces a dedicated P2 prediction head to improve the localization of small objects. By eliminating the redundant P5 prediction head, the proposed approach achieves a significantly lower parameter count and reduced GFLOPs. Experimental results on the public Tryp dataset demonstrate that YOLO-Tryppa outperforms the previous state of the art by achieving an AP50 of 71.3%, thereby setting a new benchmark for both accuracy and efficiency. These improvements make YOLO-Tryppa particularly well-suited for deployment in resource-constrained settings, facilitating more rapid and reliable diagnostic practices.

Shuyu Tang, Tingshuai Jiang, Wenqi Su et al.

PurposeThis study aimed to report the clinical characteristics, genetic findings, and treatment outcomes of a Chinese patient with Bosch–Boonstra–Schaaf optic atrophy syndrome (BBSOAS) caused by a mutation in the NR2F1 gene.MethodA retrospective chart review was conducted, including the patient’s medical history, brain magnetic resonance imaging (MRI), electroencephalogram (EEG), and brainstem auditory evoked potential (BAEP) test results. A detailed ophthalmic examination was recorded, including gaze following, fundus photography, flash-electroretinogram (f-ERG), and flash visual evoked potential (f-VEP). Genetic sequencing results from whole-exome sequencing (WES) were collected.ResultThe patient was an approximately 5-6 years old boy admitted to the hospital due to developmental delay and poor gaze following. Brain MRI revealed a cerebellar cyst, and EEG showed abnormal waveforms. BAEP indicated bilateral auditory conduction pathway impairment. Severe exotropia and optic nerve atrophy were observed in both eyes. f-ERG analysis revealed a moderate-to-severe decrease of dark-adapted (DA) amplitude in the right eye and a mild-to-moderate decrease in the left eye. WES identified a de novo heterozygous missense mutation (NM_005654.6: c.452T>C, p.Met151Thr) in the NR2F1 gene, which was determined to be the cause of the disease. The patient had been receiving neurotrophic treatment since the age of one, but no significant improvement was observed.ConclusionOur report demonstrated the pathogenicity of a variant in the NR2F1 gene, which was previously classified as a variant of uncertain significance or as a likely pathogenic variant, along with a detailed phenotypic characterization. The clinical features and treatment outcomes described here may expand the spectrum of known NR2F1 variants and serve as a reference for understanding this rare disease.

Ahmed Salem, Ebrahem Elkady, Hatem Ibrahem et al.

Densely sampled light fields are powerful tools for applications such as post-capture refocusing and virtual reality, but acquiring such data remains costly and technically demanding. While existing reconstruction methods have shown promise, they often succeed only in small-baseline settings and struggle with larger disparities or real-time efficiency. Depth-based approaches are prone to artifacts due to imperfect depth estimates, while non-depth-based methods lack geometric accuracy, fail in occluded or textureless regions, and are typically computationally intensive. In this work, we provide a more effective disentanglement of spatial, angular, and epipolar representations for light field reconstruction. Through dedicated feature extractors and a residual-in-residual architecture enhanced with channel attention, our framework efficiently captures subpixel details and long-range dependencies while adaptively emphasizing the most informative cues. Rigorous ablation studies further highlight the critical role of epipolar feature interactions—an aspect previously overlooked in the literature. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach consistently surpasses state-of-the-art methods across small- and large-baseline scenarios, delivering higher reconstruction quality while maintaining competitive efficiency.

Sofia El Amoury, Youssef Smili, Youssef Fakhri

The classification of brain tumors using MRI scans is critical for accurate diagnosis and effective treatment planning, though it poses significant challenges due to the complex and varied characteristics of tumors, including irregular shapes, diverse sizes, and subtle textural differences. Traditional convolutional neural network (CNN) models, whether handcrafted or pretrained, frequently fall short in capturing these intricate details comprehensively. To address this complexity, an automated approach employing Particle Swarm Optimization (PSO) has been applied to create a CNN architecture specifically adapted for MRI-based brain tumor classification. PSO systematically searches for an optimal configuration of architectural parameters—such as the types and numbers of layers, filter quantities and sizes, and neuron numbers in fully connected layers—with the objective of enhancing classification accuracy. This performance-driven method avoids the inefficiencies of manual design and iterative trial and error. Experimental results indicate that the PSO-optimized CNN achieves a classification accuracy of 99.19%, demonstrating significant potential for improving diagnostic precision in complex medical imaging applications and underscoring the value of automated architecture search in advancing critical healthcare technology.

Shion Ando, Ping Yeap Loh

Ultrasound imaging has been used to investigate compression of the median nerve in carpal tunnel syndrome patients. Ultrasound imaging and the extraction of median nerve parameters from ultrasound images are crucial and are usually performed manually by experts. The manual annotation of ultrasound images relies on experience, and intra- and interrater reliability may vary among studies. In this study, two types of convolutional neural networks (CNNs), U-Net and SegNet, were used to extract the median nerve morphology. To the best of our knowledge, the application of these methods to ultrasound imaging of the median nerve has not yet been investigated. Spearman’s correlation and Bland–Altman analyses were performed to investigate the correlation and agreement between manual annotation and CNN estimation, namely, the cross-sectional area, circumference, and diameter of the median nerve. The results showed that the intersection over union (IoU) of U-Net (0.717) was greater than that of SegNet (0.625). A few images in SegNet had an IoU below 0.6, decreasing the average IoU. In both models, the IoU decreased when the median nerve was elongated longitudinally with a blurred outline. The Bland–Altman analysis revealed that, in general, both the U-Net- and SegNet-estimated measurements showed 95% limits of agreement with manual annotation. These results show that these CNN models are promising tools for median nerve ultrasound imaging analysis.

Xiaojun Li, Yi Su, Junping Yao et al.

Abstract Due to differences in the quantity and size of observed targets, hyperspectral images are characterized by class imbalance. The standard deep learning classification model training scheme optimizes the overall classification error, which may lead to performance imbalance between classes in hyperspectral image classification frameworks. Therefore, a novel factor annealing decoupling compositional training method is proposed in this paper. Without requiring resampling or reweighting, it implicitly modulates the training process, so standard models can sufficiently learn the representation of the minority classes and further be trained as robust classifiers. Specifically, the label‐distribution‐aware margin loss is combined with the error‐rate‐based cross‐entropy loss via combination factor, which considers both imbalanced data representation learning and classifier overall performance. Then, a factor annealing optimization training scheme is designed to adjust the combination factor, which solves the stage division problem of two‐stage decoupling learning. Experimental results on two hyperspectral image datasets demonstrate that, as compared with other competing approaches, the proposed method can continuously and stably optimize the model parameters, achieving improvements in class average metrics and difficult classes without affecting overall classification performance.

Rushi Li, Mincheng Wu

Urban color, primarily emanating from building façades and roofs, plays a pivotal role in shaping a city’s image and influencing people’s overall impression. Understanding the nuances of color patterns contributes significantly to unraveling the uniqueness and identity of a city. This study introduces a statistical method for the systematic analysis of urban color and macroscopic urban structure. Specifically, we employ drones to collect and extract building roof and façade colors in the main urban area of Hangzhou, mapping these colors to the HSV color space. Subsequently, we establish a random walk model and an origin–destination trip model within the urban transportation network to simulate the movement of people. Our experiments reveal robust correlations between façade and roof values and passing frequency (with the Pearson correlations reaching 0.70). Through a rigorous statistical analysis, we gain insights into the distribution of urban color and the impact of architectural structures on color variations, identifying potential patterns or trends. By integrating color data with architectural structure data, our systematic research method deepens the understanding of the visual features that define cities. Beyond theoretical exploration, this approach offers practical insights for building planning and design. This study not only sheds light on the relationship between architectural structures and urban color but also provides valuable guidance for future urban development initiatives.

Niels J. de Winter, Niels J. de Winter, Sterre van Sikkeleras et al.

IntroductionGrowth experiments present a powerful tool for determining the effect of environmental parameters on growth and carbonate composition in biogenic calcifiers. For successful proxy calibration and biomineralization studies, it is vital to identify volumes of carbonate precipitated by these organisms at precise intervals during the experiment. Here, we investigate the use of strontium labelling in mollusc growth experiments.MethodsThree bivalve species (Cerastoderma edule, Mytilus edulis and Ostrea edulis) were grown under monitored field conditions. The bivalves were regularly exposed to seawater with elevated concentrations of dissolved strontium chloride (SrCl2). In addition, the size of their shells was determined at various stages during the experiment using calliper measurements and digital photography. Trace element profiles were measured in cross sections through the shells of these molluscs using laser ablation ICPMS and XRF techniques.ResultsOur results show that doses of dissolved strontium equivalent to 7-8 times the background marine value (~0.6 mmol/L) are sufficient to cause reproducible peaks in shell-incorporated strontium in C. edule and M. edulis shells. No negative effects were observed on shell calcification rates. Lower doses (3-5 times background values) resulted in less clearly identifiable peaks, especially in M. edulis. Strontium spiking labels in shells of O. edulis are more difficult to detect, likely due to their irregular growth.DiscussionStrontium spiking is a useful technique for creating time marks in cultured shells and a reproducible way to monitor shell size during the growing season while limiting physical disturbance of the animals. However, accurate reconstructions of growth rates at high temporal resolution require frequent spiking with high doses of strontium.

Mukhanov S.A., Mukhanova A.A., Morozov M.Yu.

Environmental monitoring using satellite imagery and aerial photography is an important tool for assessing the state of the environment at the global and regional level. The article discusses the process of developing an application for environmental monitoring based on the analysis of high-altitude photographs. The authors describe in detail the choice of data processing methods and technologies underlying the developed application. An analysis of algorithms for detecting and analyzing environmental changes using high-precision satellite data was carried out. The application provides users with access to real-time visualization of environmental parameters, facilitating effective monitoring and management of natural resources. The results demonstrate the potential of using modern technologies in the field of ecology and highlight the importance of developing relevant tools for sustainable environmental management.

Bingwei Ge, Fatma Najar, Nizar Bouguila

In this paper, a weighted multivariate generalized Gaussian mixture model combined with stochastic optimization is proposed for point cloud registration. The mixture model parameters of the target scene and the scene to be registered are updated iteratively by the fixed point method under the framework of the EM algorithm, and the number of components is determined based on the minimum message length criterion (MML). The KL divergence between these two mixture models is utilized as the loss function for stochastic optimization to find the optimal parameters of the transformation model. The self-built point clouds are used to evaluate the performance of the proposed algorithm on rigid registration. Experiments demonstrate that the algorithm dramatically reduces the impact of noise and outliers and effectively extracts the key features of the data-intensive regions.

Kelly Midori McCormick

Elizabeth McGoey, Elizabeth Siegel

In the 1930s, a surging interest in early American vernacular arts, collectively referred to as folk art, converged with major photographic documentation projects of the Great Depression. These twin impulses—to collect the past and record the present—flourished concurrently during this critical period in American history. As artists, curators, collectors, and even government administrators sought to define American visual identities that were distinct from Europe, they found symbols of an American culture that was egalitarian, unpretentious, and self-made. The exhibition Photography and Folk Art: Looking for America in the 1930s (The Art Institute of Chicago, 2019) brought documentary photographs and folk art objects together to explore the aesthetic and conceptual connections between two fields—linked by overlapping networks of cultural agents—that had long been studied separately in disciplinary silos. This article details the exhibition’s collaborative research and discovery process, innovative display and interpretive strategies, and ultimately present-day relevance for twenty-first century audiences.

William Kim, Torunn Sivesind

BackgroundMedical photography is used extensively in dermatology to record disease progression, measure treatment response, and help teach patients about skin disease; such photos are also commonly utilized in teledermatology, medical education, research, and medical reference websites. Understanding patient perceptions of medical photographs obtained during dermatologic care in the clinic or hospital setting is critical to enable the delivery of high-quality, patient-centered medical care. ObjectiveThe aims of this study were to elucidate patient perceptions of skin photos in dermatology and to explore possible next steps in improving the patient experience with medical photography in the hospital or clinic setting. MethodsA scoping review of the literature was performed using the PubMed database, with clinic- or hospital-based full-text publications in English spanning the last 10 years considered for inclusion. ResultsThe majority of included studies (10/11, 91%) found positive patient attitudes toward medical photographs. The majority of patients (1197/1511, 79.2%) felt that medical photographs could improve medical care in the clinic setting. Written consent detailing all photo uses, including secondary uses (such as research or teaching), was preferred, apart from in 1 study. Patients preferred or found it acceptable for the photographer of their medical photos to be a physician (1301/1444, 90.1%). Clinic-owned cameras with departmental record storage were the preferred modality. Latinx and African American patients expressed less trust in the utility of medical photographs to improve care, compared with Asian and White patients. The minimal number of available publications on this topic and the inclusion of articles older than 5 years are limitations, since patient perceptions of medical photography may have rapidly changed during this time span, particularly in light of the COVID-19 pandemic and the subsequent increase in teledermatology visits. ConclusionsPatients reported positive perceptions of dermatologic photography for improving their medical care. Ethnic disparities in patient perceptions require further exploration to better elucidate nuances and develop interventions to improve the experience of marginalized patients. Building patient trust in nonphysician photographers may enhance clinic efficiency. Although clinic-owned cameras are well-accepted by patients, improved patient education surrounding the safety of electronic medical record phone applications is needed.

V. V. Stafford

The purpose of the research is to evaluate the parasitism effects on clinical parameters of laboratory animals.Materials and methods. The venous blood of 20 rabbits aged 1 year was taken to perform biochemical and general blood tests, for which purpose hematological analyzers were used. The animals were dissected using the Shor’s method. The topography of the organ complex was evaluated, and pathological material was collected and placed to 10% buffered formalin. For pathomorphological examination, liver, spleen, lung, and kidney samples were taken. To determine the histological pattern, paraffin-embedded samples on Thermo Scientific semi-automatic equipment were used. Histologic specimens were stained with hematoxylin and eosin. The histoarchitecture of the specimens was evaluated using an Axio A1.0 microscope, and photography was conducted with the AxioVision software.Results and discussion. The article presents the data of the general and biochemical blood tests of the blood from the rabbits intended to be used in the experiment. Further, the pathoanatomical picture of the liver was shown in animals infected with Eimeria spp., and the histological pattern was presented for parenchymal organs. We found that the main biochemical values that exceeded reference values were liver values, namely, aspartate aminotransferase and alanine aminotransferase. We also observed an increase in monocytes and granulocytes in the blood. Pathological and anatomical changes were only expressed in the liver, while no changes in the macro pattern were observed in other organs. Histological examination of parenchymal organs showed a significant pathology in the liver due to endogenous stages of oocysts occurred in its structure. Additionally, we observed a strong eosinophil response in the spleen and a high content of eosinophils in the pulmonary veins.

Liza Rose Cirolia, Nobukhosi Ngwenya, Barry Christianson et al.

The vast majority of city planning literature on informal occupations has focused on how residents occupy vacant and peripheral land, developing informal structures to address their basic needs. A smaller body of work, but one with much purchase in South Africa, explores the informal occupation of existing formal structures and how residents infuse these emergent places with social and political meaning. Across this work, occupations represent a dominant mode of city-building in the Global South. Contributing to this debate on city-making and occupations, this paper departs from an unusual case of South African occupation. We explore how displaced people have occupied a multi-storey vacant hospital building situated close to Cape Town’s city centre. Using documentary photography and interviews with residents, we argue that this occupation reflects a logic of ‘retrofit city-making’. We show that, through processes of repairing, repurposing, and renovating, dwellers have retrofit an institutional building, previously designed by the state for a very different use, to meet their needs and desires. As cities become more densely built and vacant land more peripheral or scarce, the retrofit of underutilised buildings, particularly through bottom-up actions such as occupation, will become an increasingly important mode of urban development. Not only are the practices of material transformation useful to understand, so too are the ways in which occupations reflect significantly more than simply survivalist strategies, but also care and meaning-making.

Mahmood Shafiee, Zeyu Zhou, Luyao Mei et al.

With increasing global investment in offshore wind energy and rapid deployment of wind power technologies in deep water hazardous environments, the in-service inspection of wind turbines and their related infrastructure plays an important role in the safe and efficient operation of wind farm fleets. The use of unmanned aerial vehicle (UAV) and remotely piloted aircraft (RPA)—commonly known as “drones”—for remote inspection of wind energy infrastructure has received a great deal of attention in recent years. Drones have significant potential to reduce not only the number of times that personnel will need to travel to and climb up the wind turbines, but also the amount of heavy lifting equipment required to carry out the dangerous inspection works. Drones can also shorten the duration of downtime needed to detect defects and collect diagnostic information from the entire wind farm. Despite all these potential benefits, the drone-based inspection technology in the offshore wind industry is still at an early stage of development and its reliability has yet to be proven. Any unforeseen failure of the drone system during its mission may cause an interruption in inspection operations, and thereby, significant reduction in the electricity generated by wind turbines. In this paper, we propose a semiquantitative reliability analysis framework to identify and evaluate the criticality of mission failures—at both system and component levels—in inspection drones, with the goal of lowering the operation and maintenance (O&M) costs as well as improving personnel safety in offshore wind farms. Our framework is built based upon two well-established failure analysis methodologies, namely, fault tree analysis (FTA) and failure mode and effects analysis (FMEA). It is then tested and verified on a drone prototype, which was developed in the laboratory for taking aerial photography and video of both onshore and offshore wind turbines. The most significant failure modes and underlying root causes within the drone system are identified, and the effects of the failures on the system’s operation are analysed. Finally, some innovative solutions are proposed on how to minimize the risks associated with mission failures in inspection drones.

Sunyoung Park

This paper examines the history of the ROK Army Motion Picture Production Center (AMPPC), which played a significant role in the Korean film industry from the 1950s to the 1970s. Around this time, the AMPPC was an official film production institute alongside the National Film Production Center, and produced newsreels and culture films as well as fiction films. Starting with the documentary An Assault on Justice, the first film on the Korean War, and the National Defense Series, the AMPPC produced educational short films and many feature-length films. It was a large-scale film production company that produced an average of over 100 films a year until the 1970s. In addition, the military film industry provided workspace for Korean film industry professional and took care of postproduction for commercial films at a time when the film industry was considered nearly impossible. It was also an active producer that recorded significant progress in the Korean film history through technical experiments at a time when the infrastructure for the film industry had collapsed. In addition, many Korean film industry professionals were affiliated with or closely related to the center. Not only directors but also people in photography, editing, and screenwriting worked in both the mainstream film industry and the AMPPC. Moreover, military films also had a certain impact on anti-Communist films and anti-Communist television programs in its early years. Various military films produced from the 1950s to the 1970s, including the anti-Communist films produced in the military since 1948 and the first war documentary An Assault of Justice, were utilized in anti-Communist films for theaters but also television news, drama series, and documentaries, becoming archetypes for each derivative program format. In sum, the AMPPC during this time was closely related to the Korean film industry as well as the television industry in terms of quantity and quality, providing the human resources and physical basis. It is also important to imbue significance into the “militaristic” utilization of military films. Above all, the military films’ most important role in its history since the founding of the government of the Republic of Korea was its utilization as part of the Korean government’s psychological warfare waged against its people between the 1950s and 1970s under the Cold War regime. The role of military films as propaganda warfare, which became much more explicit with the outbreak of the Korean War, became strengthened through the installation of the AMPPC in 1963, dispatch of Korean soldiers for the Vietnam War and the improvement of the film production environment in 1965. Particularly with the sending of Korean troops to Vietnam, it became important for the government to produce and screen military films as propaganda for Korea’s unjustified participation in the war. In the 1970s, the AMPPC, which had to continue the Cold War by continuously placing significance on the Vietnam War throughout and even after the war, was able to produce over 130 films in various genres and lengths every year. This paper is significant in that it systematically organizes the history of the military film industry, which had not been properly explained in the past, and that it discusses the military film industry as a means to examine the overall structure of the film industry and its vibrant activities at the time. This discussion has been performed as a basis for the analysis of specific military films. I hope to delve further into the significance and the role of military films as a tool of propaganda warfare through textual analysis in future studies.

Chae Min Kim, Joo Hyun Oh, Yeo Reum Jeon et al.

Background Composite grafts are frequently used for facial reconstruction. However, the unpredictability of the results and difficulties with large defects are disadvantages. Adipose-derived stem cells (ADSCs) express several cytokines, and increase the survival of random flaps and fat grafts owing to their angiogenic potential. Methods This study investigated composite graft survival after ADSC injection. Circular chondrocutaneous composite tissues, 2 cm in diameter, from 15 New Zealand white rabbits were used. Thirty ears were randomly divided into 3 groups. In the experimental groups (1 and 2), ADSCs were subcutaneously injected 7 days and immediately before the operation, respectively. Similarly, phosphate-buffered saline was injected in the control group just before surgery in the same manner as in group 2. In all groups, chondrocutaneous composite tissue was elevated, rotated 90 degrees, and repaired in its original position. Skin flow was assessed using laser Doppler 1, 3, 6, 9, and 12 days after surgery. At 1 and 12 days after surgery, the viable area was assessed using digital photography; the rabbits were euthanized, and immunohistochemical staining for CD31 was performed to assess neovascularization. Results The survival of composite grafts increased significantly with the injection of ADSCs (P<0.05). ADSC injection significantly improved neovascularization based on anti-CD31 immunohistochemical analysis and vascular endothelial growth factor expression (P<0.05) in both group 1 and group 2 compared to the control group. No statistically significant differences in graft survival, anti-CD31 neovascularization, or microcirculation were found between groups 1 and 2. Conclusions Treatment with ADSCs improved the composite graft survival, as confirmed by the survival area and histological evaluation. The differences according to the injection timing were not significant.

Rita de Cássia Demarchi

Palavras e fotografias derivados do processo de uma pesquisa de doutorado – Ver aquele que vê: um olhar poético sobre os visitantes em museus e exposições de arte . Um problema criado: ver o outro que vê em diversos contextos, aproximar-me dele, buscar compreendê-lo sem trocar palavra, alimentar-me com a sua experiência, capturar uma imagem. O desafio de ver em meio às paisagens contemporâneas, inaugurais, nebulosas, instáveis, territórios instaurados em um universo inesgotável, que abrange arte de diferentes períodos e se desdobra em diversas instituições. O ensaio visual apresentado inclui espaços/paisagens junto às Bienais do Mercosul, de São Paulo e de Veneza; Fundação Serralves em Porto; GNAM/Galeria de Arte Moderna de Roma; e museus em Lisboa: CAM/Centro de Arte Moderna da Fundação Gulbenkian; MNAC/Museu de Arte Contemporânea do Chiado, Museu Nacional de Arte Antiga.