Hasil untuk "Photography"

R. Rioboo, M. Marengo, C. Tropea

Giusy Macrina, L. Pugliese, F. Guerriero et al.

Abstract The interest in using drones in various applications has grown significantly in recent years. The reasons are related to the continuous advances in technology, especially the advent of fast microprocessors, which support intelligent autonomous control of several systems. Photography, construction, and monitoring and surveillance are only some of the areas in which the use of drones is becoming common. Among these, last-mile delivery is one of the most promising areas. In this work we focus on routing problems with drones, mostly in the context of parcel delivery. We survey and classify the existing works and we provide perspectives for future research.

J. Prosser

Zhongmin Jiang, Zhen Wang, Wenju Wang et al.

There were two errors in the original publication [...]

Wenjie Huang, Ruiqing Kang, Lingyan Li et al.

In the realm of image classification, the capsule network is a network topology that packs the extracted features into many capsules, performs sophisticated capsule screening using a dynamic routing mechanism, and finally recognizes that each capsule corresponds to a category feature. Compared with previous network topologies, the capsule network has more sophisticated operations, uses a large number of parameter matrices and vectors to express picture attributes, and has more powerful image classification capabilities. However, in the practical application field, the capsule network has always been constrained by the quantity of calculation produced by the complicated structure. In the face of basic datasets, it is prone to over-fitting and poor generalization and often cannot satisfy the high computational overhead when facing complex datasets. Based on the aforesaid problems, this research proposes a novel enhanced capsule network topology. The upgraded network boosts the feature extraction ability of the network by incorporating a multi-scale feature extraction module based on proprietary star structure convolution into the standard capsule network. At the same time, additional structural portions of the capsule network are changed, and a variety of optimization approaches such as dense connection, attention mechanism, and low-rank matrix operation are combined. Image classification studies are carried out on different datasets, and the novel structure suggested in this paper has good classification performance on CIFAR-10, CIFAR-100, and CUB datasets. At the same time, we also achieved 98.21% and 95.38% classification accuracy on two complicated datasets of skin cancer ISIC derived and Forged Face EXP.

Tamika M. Wopereis, Kirsten J. Roman, Sanne K. Djojosoeparto et al.

Abstract Background (Commercial) food cues in outdoor public spaces are environmental drivers of unhealthy diets. This study aimed to explore residents’ perceptions of food cues in outdoor public spaces in relation to their perceived food environment, eating behaviour, and their opinion on governmental outdoor food cue regulations. Methods A photovoice study, consisting of a photography assignment followed by semi-structured interviews, was conducted among 15 adult residents of the municipality of Wageningen, the Netherlands. Participants had one week to take photographs of outdoor food cues they encountered in their municipality, using a mobile app “myfoodenvironment”, that were central to the interview afterwards. Results Participants mainly noticed unhealthy food cues, which they viewed as constant ‘reminders’ that unhealthy food was easily accessible and affordable. Their views varied on the extent to which food cues affected their own eating behaviour, but generally believed that food cues affected that of others. Participants identified several factors that amplify outdoor food cues’ influence on eating behaviour, including hunger, fatigue and attractiveness of the cues. The findings revealed support for government regulation of food cues, while acknowledging the complexity of this issue and the diverse perspectives on how such regulations should be designed (e.g., where, for whom), with one notable counterargument being concerns about feeling patronized by such policies. Conclusions Current findings may inform health professionals and (local) policy makers about the unhealthy food cues encountered by residents in outdoor public spaces, which unconsciously influence their eating behaviour, while also providing insights into designing food cue regulations that attract policy support by balancing public health goals with considerations of consumer autonomy and citizen preferences.

Images Editorial Team

Na okładce niniejszego numeru „Images”, który oddajemy w ręce Czytelników, znajduje się kadr z reportażu autorstwa Bolesława Matuszewskiego, jednego z pionierów światowej kinematografii, teoretyka i praktyka filmowego medium. Prezentowane zdjęcie zapobiegło wybuchowi skandalu dyplomatycznego w 1897 r., ponieważ dowodziło, że ówczesny prezydent Francji Félix Faure (1841–1899) nie uchybił protokołowi dyplomatycznemu i zdjął nakrycie głowy, kiedy oddawał należną cześć wojskowemu sztandarowi. Spoglądając na zdjęcie Matuszewskiego z dzisiejszej perspektywy, po blisko 130 latach od wydarzenia upamiętnionego na fotografii, można stwierdzić, że jest ona doskonałym przykładem artefaktu należącego do kategorii historii wizualnej. Sam kadr, bez znajomości kontekstu sytuacji, wydaje się dość typowy dla swoich czasów – ukazuje moment oficjalnych uroczystości w przestrzeni publicznej. Gdy jednak weźmiemy pod uwagę liczne konteksty, które towarzyszą zdjęciu autora kanonicznych tekstów Nowe źródło historii oraz Nowe źródło historii. Ożywiona fotografia. Czym jest, czym być powinna, widać, jak ogromne znaczenie może zawierać pojedynczy artefakt wizualny.

Paloma Conde, Jesús Rivera-Navarro, Marta Gutiérrez-Sastre et al.

Objective: To compare, from an empirical point of view, the use of focus group and photovoice as we conducted two studies on food environment in neighbourhoods with different socio-economic profiles. Method: The European project Heart Healthy Hoods studied the association between the physical and social environment of Madrid (Spain) and the cardiovascular health of its residents. Two ancillary studies were developed to further expand the study of urban health inequalities using focus group and photovoice. Both studies, similar in their objectives and study populations, are the basis for comparing both techniques. The comparison considered the following methodological aspects: study design, logistic aspects, commitment and involvement, ethical issues, and data analysis. Results: We identified differences, similarities, potentialities, and limitations of each technique with their corresponding results. We found that depending on the research objectives, one technique was more beneficial than the other. If the objective is producing new knowledge, using focus group would be the most appropriate technique, whereas if the objective includes generating social change, photovoice would be more suitable. We found that photovoice is a powerful technique in public health, especially studying social processes related to population health, requiring extra effort from researchers and a special care with the related ethical considerations. Conclusions: Increasing participants’ awareness, involving decision makers to channel proposals, the atypical role of researchers and ethical implications of photography are aspects to be considered when choosing photovoice instead of focus group. Resumen: Objetivo: Comparar empíricamente el uso del grupo focal y el fotovoz en investigación sobre el entorno alimentario en barrios con diferente perfil socioeconómico. Método: El proyecto europeo Heart Healthy Hoods estudió la asociación entre el entorno físico y social de Madrid y la salud cardiovascular de sus residentes. Dentro de él se desarrollaron dos estudios para analizar las desigualdades en salud utilizando las técnicas del grupo focal y el fotovoz. Ambos estudios, similares en sus objetivos y población diana, fueron la base para comparar las dos técnicas. Consideramos los siguientes aspectos metodológicos: diseño, aspectos logísticos, compromiso e implicación del equipo investigador y de las personas participantes, cuestiones éticas y análisis de los datos. Resultados: Identificamos diferencias, similitudes, potencialidades y limitaciones de cada técnica utilizada con sus correspondientes resultados. Dependiendo de los objetivos, una técnica sería más beneficiosa que la otra. Si el objetivo es producir nuevo conocimiento, el grupo focal sería la técnica más adecuada, mientras que, si el objetivo incluye generar cambio social, el fotovoz sería más apropiado. Consideramos el fotovoz una técnica muy provechosa para la investigación en salud pública, especialmente para estudiar procesos sociales en relación con la salud de la población, aunque requiere un esfuerzo adicional por parte del equipo investigador y de los participantes, y un cuidado especial con las consideraciones éticas. Conclusiones: Aumentar la conciencia de las personas participantes, involucrar a decisores políticos para canalizar las propuestas resultantes, el papel atípico del equipo investigador y las implicaciones éticas de la fotografía son aspectos a considerar si elegimos el fotovoz frente al grupo focal.

Md Nuho Ul Alam, Erfanul Hoque Bahadur, Abdul Kadar Muhammad Masum et al.

Diabetic Retinopathy (DR) is a serious eye condition that occurs due to high blood sugar levels in patients with Diabetes Mellitus. If left untreated, DR can potentially result in blindness. Using automated neural network-based methods to grade DR shows potential for early detection. However, the uneven and non-quadrilateral forms of DR lesions provide difficulties for traditional Convolutional Neural Network (CNN)-based architectures. To address this challenge and explore a novel algorithm architecture, this work delves into the usage of contrasting cluster assignments in retinal fundus images with the Swapping Assignments between multiple Views (SwAV) algorithm for DR grading. An ablation study was made where SwAV outperformed other CNN and Transformer-based models, independently and in ensemble configurations with an accuracy of 87.00% despite having fewer parameters and layers. The proposed approach outperforms existing state-of-the-art models regarding classification metrics, complexity, and prediction time. The findings offer great potential for medical practitioners, allowing for more accurate diagnosis of DR and earlier treatments to avoid visual loss.

Halenur Altan, Rabia Erağca Yilmaz

Abstract Background Resin infiltration is a micro-invasive treatment for molar incisor hypomineralisation (MIH). In this study it was aimed to evaluate the masking effect of resin infiltration treatment (ICON) on hypomineralised enamel surface of permanent anterior teeth by using laser fluorescence, spectrophotometer, and cross-polarisation photography. Methods A total of 116 permanent central incisors in 37 patients were included in the study. The resin infiltration treatment (Icon®) was applied to the teeth with MIH; the healthy teeth received no treatment (control). Hypomineralised enamel lesions were evaluated by ICDAS II criteria. DIAGNOdent Pen was used to assess the lesions and healthy enamel surface quantitatively. Colour changes in enamel lesions were evaluated by using a spectrophotometer (VITA EasyShare). Each enamel lesion was imaged using a cross-polarization technique before and after treatment. All photos were assessed using Image J to evaluate the changes in lesion size. Enamel lesions were evaluated before; immediately after; 1; 3; and 6 months after treatment. Statistical significance was set as p < 0.05. Results After the resin infiltration, significant decreases were found in the mean DIAGNOdent values for the treatment group (p < 0.05). The colour differences before and after treatment significantly differed in all follow-ups (p < 0.05). In the treatment group, lesion areas decreased significantly after treatment (p < 0.05). Conclusions The resin infiltration treatment has a masking effect on MIH lesions without cavities, with stable outcomes after six months. The cross-polarization photography technique may be use to evaluate the lesion size instead of photography with flash. Trial registration. NCT04685889 (registered 28 December 2020).

Molly McPhee

In this article, I explore performances of letter writing within the archives of the London-based theatre company Clean Break, who work with justice-experienced women and women at risk. Clean Break’s archive at the Bishopsgate Institute in London contains an extensive collection of production ephemera and letters. Charting the company’s development across forty years of theatre productions, public advocacy, and work in prisons and community settings, these materials of the archive—strategic documents, annotated playscripts and rehearsal notes, production photography and correspondence—reveal the acute importance of the letter to people living on the immediate borderlands of the prison. Despite these generative resonances, however, the epistolary form is very rarely used in Clean Break’s theatre: as the archive reveals, since the company was founded by two women in HM Prison Askham Grange in 1979, stagings of letters have occurred in only a handful of instances. In this archival exploration of the epistolary in three works by Clean Break—a film broadcast by the BBC, a play staged at the Royal Court, and a circular chain-play written by women in three prisons—I investigate what lifeworlds beyond prison epistolary forms in performance propose.

Daniel Vera-Yanez, António Pereira, Nuno Rodrigues et al.

This paper presents a systematic review of articles on computer-vision-based flying obstacle detection with a focus on midair collision avoidance. Publications from the beginning until 2022 were searched in Scopus, IEEE, ACM, MDPI, and Web of Science databases. From the initial 647 publications obtained, 85 were finally selected and examined. The results show an increasing interest in this topic, especially in relation to object detection and tracking. Our study hypothesizes that the widespread access to commercial drones, the improvements in single-board computers, and their compatibility with computer vision libraries have contributed to the increase in the number of publications. The review also shows that the proposed algorithms are mainly tested using simulation software and flight simulators, and only 26 papers report testing with physical flying vehicles. This systematic review highlights other gaps to be addressed in future work. Several identified challenges are related to increasing the success rate of threat detection and testing solutions in complex scenarios.

Yinhuan Zhang, Qinkun Xiao, Xing Liu et al.

Abstract In occlusion and interaction scenarios, human action recognition (HAR) accuracy is low. To address this issue, this paper proposes a novel multi‐modal fusion framework for HAR. In this framework, a module called improved attention long short‐term memory (IAL) is proposed, which combines the improved SE‐ResNet50 (ISE‐ResNet50) with long short‐term memory (LSTM). IAL can extract the video sequence features and the skeleton sequence features of human behaviour. To improve the performance of HAR at a high semantic level, the obtained multi‐modal sequence features are fed into a couple hidden Markov model (CHMM), and a multi‐modal IAL+CHMM method called IALC is developed based on a probability graph model. To test the performance of the proposed method, experiments are conducted on the HMDB51, UCF101, Kinetics 400k, and ActivityNet datasets, and the obtained recognition accuracy are 86.40%, 97.78%, 81.12%, and 69.36% on the four datasets, respectively. The experimental results show that when the environment is complex, the proposed multi‐modal fusion method for HAR based on the IALC can achieve more accurate target recognition results.

Lisa K. Lundy

This article discusses the important role that photographs play in science communication. Tips are given for enhancing photography using smartphones.

Rafael Dueire Lins, Rodrigo Bernardino, Ricardo da Silva Barboza et al.

The intrinsic features of documents, such as paper color, texture, aging, translucency, the kind of printing, typing or handwriting, etc., are important with regard to how to process and enhance their image. Image binarization is the process of producing a monochromatic image having its color version as input. It is a key step in the document processing pipeline. The recent Quality-Time Binarization Competitions for documents have shown that no binarization algorithm is good for any kind of document image. This paper uses a sample of the texture of the scanned historical documents as the main document feature to select which of the 63 widely used algorithms, using five different versions of the input images, totaling 315 document image-binarization schemes, provides a reasonable quality-time trade-off.

LI Wentao, PENG Li

The current implementation of small object detection algorithms is mainly to design various feature fusion modules. It is difficult to achieve a balance between the detection effect and the model complexity. In addition, compared with regular object, small object has less information and is difficult to extract features. To solve these two problems, a channel attention module is adopted to use a local cross-channels interaction strategy without dimensionality reduction. This module realizes the information association between channels and learns the correlation between features of different channels by considering the weight allocation of features of each channel. In addition, an improved feature fusion module is applied to integrating both the low-level and high-level features for multi-scale object detection. Through such a manner, the accuracy of small object detection is improved. The backbone network adopts ResNet with strong feature expression ability and fast speed, which ensures the convergence of the network while acquiring more network features. The loss function adopts Focal Loss to reduce the weight of easy-to-classify samples, making the model pay more attention to the classification of difficult-to-classify samples during training. The algorithm framework has the mAP of 82.7% on the VOC data set, 86.8% on the aerial photography data set.

Anna V. Naumova, Gregory Kicska, Kiana Pimentel et al.

(1) Background: The accuracy of the left ventricular volume (LVV) and contractility measurements with cardiac magnetic resonance imaging (CMRI) is decreased if the papillary muscles are abnormally enlarged, such as in hypertrophic cardiomyopathy in human patients or in pig models of human diseases. The purpose of this work was to establish the best method of LVV quantification with CMRI in pigs. (2) Methods: The LVV in 29 Yucatan minipig hearts was measured using two different techniques: the “standard method”, which uses smooth contouring along the endocardial surface and adds the papillary volume to the ventricular cavity volume, and the “detailed method”, which traces the papillary muscles and trabeculations and adds them to the ventricular mass. (3) Results: Papillary muscles add 21% to the LV mass in normal and infarcted hearts of Yucatan minipigs. The inclusion or exclusion of these from the CMRI analysis significantly affected the study results. In the normal pig hearts, the biggest differences were found in measurements of the LVV, ejection fraction (EF), LV mass and indices derived from the LV mass (<i>p</i> < 0.001). The EF measurement in the normal pig heart was 11% higher with the detailed method, and 19% higher in the infarcted pig hearts (<i>p</i> < 0.0001). The detailed method of endocardium tracing with CMRI closely represented the LV mass measured <i>ex vivo</i>. (4) Conclusions: The detailed method, which accounts for the large volume of the papillary muscles in the pig heart, provides better accuracy and interobserver consistency in the assessment of LV mass and ejection fraction, and might therefore be preferable for these analyses.

Jeehey Kim

Maja DOBRAJC, Sebastjan RADIŠEK, Jernej JAKŠE et al.

Whiteflies (Aleyrodidae) is small group of insects (Insecta) that comprises around 1500 species from 160 genera. Whiteflies damage important cultivated and ornamental plants by sucking plants juice. Most of the species are from tropical area, in our region they are the most common in greenhouses. Because worldwide transport, whiteflies become invasive all around the world. The identification of whiteflies species in adult stage is problematic. Morphological differentiation of pupae is one of the better methods for determining identity of species, but it may vary depending on the host plant on which they develop which can lead to misidentifications and erroneous naming of new species. The application of genetic diagnostics under the umbrella of classical taxonomy was imperative for successful development and delivery of the biological control program, phylogenetics and plans for biological control. The most common modern techniques for whiteflies determination are computer programs for photography analysis, molecular methods with DNA isolation and sequencing.

Feng Liu, Mingming Xu, Tongfeng He