Green Screen Research Articles

Semantic Guided Matting Net

Abstract Human matting refers to extracting human parts from natural images with high quality, including human detail information such as hair, glasses, hats, etc. This technology plays an essential role in image synthesis and visual effects in the film industry. When the green screen is not available, the existing human matting methods need the help of additional inputs (such as trimap, background image, etc.), or the model with high computational cost and complex network structure, which brings great difficulties to the application of human matting in practice. To alleviate such problems, we use a segmentation network as the foundation and use multiple branches to achieve human segmentation, contour detail extraction, and information fusion. We also propose a foreground probability map module, which uses the feature maps in the segmentation network to pre-estimate the foreground probabilities of each pixel and obtain Semantic Guided Matting Net. Under the condition that only a single image is needed as the input, the human matting task can be realized by making full use of the semantic information in the image. We validate our method on the P3M-10k dataset. Compared with the benchmark, our method has made significant improvements in various evaluation indicators.

Phosphor Screens Color Preferences Depending on Night Vision Experience and Luminance Level.

One of the most important factors affecting visual performance during vision aided by night vision goggles (NVGs) is image quality, which depends mainly on the image-intensifier technology used. Although NVGs with green image color (P43 phosphor) are only accepted in military aviation, white image (P45 phosphor) seems to be equally well-regarded by aviators. The aim of our study was to determine if the experience of using NVGs with the green screen affects image preference for that color, and if the screen color preference is related to luminance level. Subjects (127 military pilots, 26-56 yr, M = 37.2; 62 pilots with flight experience with NVG use) were asked to observe a model terrain board at two different luminance levels (corresponding roughly to ambient conditions during starlight and one-half moonlight) while using two types of NVGs (green P43 and white P45 phosphor screens). The pilots were asked to answer a questionnaire about their preference for NVG display color. The findings showed a significant difference between screen color preference and pilots' experience with the green-phosphor-based NVGs (43.5% vs. 23.1% for white screens). However, there was no relationship between screen color preference and luminance level. Previous NVG experience seems to play an important role in shaping a user's individual preference for a certain phosphor screen color, although green and white phosphor screens both provide satisfactory visibility. Nevertheless, when deciding, it is advisable to experiment with both colors and select the one that suits the user's preferences and needs. Lewkowicz R, Dereń-Szumełda J. Phosphor screens color preferences depending on night vision experience and luminance level. Aerosp Med Hum Perform. 2024; 95(10):749-757.

The Effects of the Virtual Background on French as a Second Foreign Language Vocabulary Learning

The purpose of this research was to investigate how the use of green screen technology affects vocabulary acquisition in LOTE (languages other than English) learners, particularly Chinese students learning French as a second foreign language. Two groups (a control group and an experimental group) with a total of 58 students participated in the study. Data were collected through in-class and delayed vocabulary tests, learning questionnaire, and semi-structured interviews. The study results demonstrate significant benefits in terms of providing an authentic learning experience, improving understanding, increasing motivation, and facilitating interaction. The results also confirm the technology’s effectiveness in enhancing both immediate and long-term vocabulary retention. The effectiveness is particularly evident for location-related words, as the technology provides visual context that facilitates recall of these words, which may not have easily retrievable mental images compared to more concrete words with tangible references. Further research can also be undertaken to compare the impact of virtual background on vocabulary retention with other immersive technologies. Nevertheless, virtual backgrounds are likely to be a cost-effective and accessible tool that can already offer promising improvements in learning outcomes and can be easily implemented with existing software like Zoom (5.2.0 or higher) and Tencent Meeting (1.3.0 or higher).

Improving Teaching and Learning in Higher Education through Machine Learning: Proof of Concept’ of AI’s Ability to Assess the Use of Key Microskills

Advances in artificial intelligence (AI), including intelligent machines, are opening new possibilities to support teaching and learning in higher education. This research has found a ‘proof of concept’ in the application of machine learning in the assessment of educators’ use of four key microskills, drawn from an internationally established framework. The analysis of teaching videos where these microskills were demonstrated multiple times in front of a green screen or in a space formed the data set. Multiple videos of this nature were recorded to allow for increased analysis and deconstruction of the video components to enable the application of machine learning. The results showed how AI can be used to support the collaborative and reflective practice of educators in a time when online teaching has become the norm. Having achieved a ‘proof of concept’, this research has laid the groundwork to allow for the whole framework of ten microskills to be applied in this way thus adding a new dimension to its use. Providing such critical information that is not currently available in such a systematic and personalised way to educators in the higher education sector can also support the validity of formative assessment practices.

Integrating Depth-Based and Deep Learning Techniques for Real-Time Video Matting without Green Screens

Virtual production, a filmmaking technique that seamlessly merges virtual and real cinematography, has revolutionized the film and television industry. However, traditional virtual production requires the setup of green screens, which can be both costly and cumbersome. We have developed a green screen-free virtual production system that incorporates a 3D tracker for camera tracking, enabling the compositing of virtual and real-world images from a moving camera with varying perspectives. To address the core issue of video matting in virtual production, we introduce a novel Boundary-Selective Fusion (BSF) technique that combines the alpha mattes generated by deep learning-based and depth-based approaches, leveraging their complementary strengths. Experimental results demonstrate that this combined alpha matte is more accurate and robust than those produced by either method alone. Overall, the proposed BSF technique is competitive with state-of-the-art video matting methods, particularly in scenarios involving humans holding objects or other complex settings. The proposed system enables real-time previewing of composite footage during filmmaking, reducing the costs associated with green screen setups and simplifying the compositing process of virtual and real images.

A Hybrid Image Augmentation Technique for User- and Environment-Independent Hand Gesture Recognition Based on Deep Learning

This research stems from the increasing use of hand gestures in various applications, such as sign language recognition to electronic device control. The focus is the importance of accuracy and robustness in recognizing hand gestures to avoid misinterpretation and instruction errors. However, many experiments on hand gesture recognition are conducted in limited laboratory environments, which do not fully reflect the everyday use of hand gestures. Therefore, the importance of an ideal background in hand gesture recognition, involving only the signer without any distracting background, is highlighted. In the real world, the use of hand gestures involves various unique environmental conditions, including differences in background colors, varying lighting conditions, and different hand gesture positions. However, the datasets available to train hand gesture recognition models often lack sufficient variability, thereby hindering the development of accurate and adaptable systems. This research aims to develop a robust hand gesture recognition model capable of operating effectively in diverse real-world environments. By leveraging deep learning-based image augmentation techniques, the study seeks to enhance the accuracy of hand gesture recognition by simulating various environmental conditions. Through data duplication and augmentation methods, including background, geometric, and lighting adjustments, the diversity of the primary dataset is expanded to improve the effectiveness of model training. It is important to note that the utilization of the green screen technique, combined with geometric and lighting augmentation, significantly contributes to the model’s ability to recognize hand gestures accurately. The research results show a significant improvement in accuracy, especially with implementing the proposed green screen technique, underscoring its effectiveness in adapting to various environmental contexts. Additionally, the study emphasizes the importance of adjusting augmentation techniques to the dataset’s characteristics for optimal performance. These findings provide valuable insights into the practical application of hand gesture recognition technology and pave the way for further research in tailoring techniques to datasets with varying complexities and environmental variations.

Transitioning from green screens to green scenes: Exploring how short videos influence Gen Z’s choice of eco-conscious travel destinations

The digital era has brought immense attention to the tourism industry through the pervasive influence of social media. Social media content profoundly shapes travel aspirations among the Chinese Generation Z, mainly through short videos. This study aims to unravel the intricate dynamics between short videos and Gen Z’s travel preferences, shedding light on their motivations, environmental consciousness, and adoption of sustainable tourism practices. Three regression models were applied in this study to shed light on this correlation. The initial model examines factors influencing the general travel intentions of Chinese Gen Z. The subsequent model delves into determinants affecting the adoption of responsible tourism practices among Gen Z. Then, the last model identifies factors contributing to tourism-related environmental awareness among this population. Through empirical analysis conducted via a structured questionnaire administered to 506 Chinese Gen Z individuals, this study’s findings confirm that well-crafted short videos significantly impact the travel intentions of Chinese youth, thereby fostering responsible tourism practices and increasing environmental consciousness. This highlights the pivotal role of argumentation quality and source credibility in shaping Gen Z’s travel intentions, underscoring the importance of credibility in promoting responsible tourism practices and environmental awareness. Furthermore, this study analysis reveals that females exhibit greater susceptibility to the influence of short video content on travel decisions than males. In conclusion, this study emphasizes the critical role of integrating short video content into marketing strategies within the tourism sector, particularly in the Gen Z demographic.

Us, Them, Right, Wrong: How TikTok's Green Screen, Duet, and Stitch help shape political discourse

As TikTok exploded in popularity following the initial lockdowns of the COVID-19 pandemic in March 2020, use from individual users skyrocketed. During this time, political content became largely ubiquitous across the app. Politics play out daily on TikTok, as individuals craft messages within the technological affordances and sociocultural dynamics of the app. This study expands on research regarding civic engagement in digital public spheres by examining and describing how TikTok shapes political expression and discourse through three technological affordances on the app: the Green Screen, the Stitch, and the Duet. While these affordances are often hailed as features that bolster user creativity through increased possible interactions, our analysis found these increased possible interactions to be highly specific, and also limited in conjunction with politics. On political TikTok, these affordances function more as political commentary than conversation, lending to an overall volatile environment.

Exploration of Easy Ways to use Green Screen in Making Learning Videos in Information Technology Education Study Programs

Exploration of Easy Ways to use Green Screen in Making Learning Videos in Information Technology Education Study Programs

Implementing chroma key compositing with a green screen to improve the learning experience of remote students during synchronous hybrid lectures

Implementing chroma key compositing with a green screen to improve the learning experience of remote students during synchronous hybrid lectures

Green filming in Poland. An interplay between necessity, environmental responsibility and green incentives

The objective of this paper is to explore the sustainable management approach in film production by examining tangible green film policy solutions in Poland. Specifically, the article contributes to mapping the green film ecosystem in Poland. First, it points to different green screen practices, showing actions that promote an environmentally sustainable approach to film production. Second, it examines the challenges associated with implementing green film production in Poland, considering the conditions necessary for transforming film production into an ecological production framework.

PHILOSOPHICAL AND RELIGIOUS TEACHINGS OF CHINA AS THE BASIS OF ART AND ARCHITECTURE

The social life of China, its culture and art were determined by the local religion of Taoism, and the main postulates were laid out in the treatise "Daodejing" ("The Book of Tao and De", 6th century AD). Accordingly, a person with the whole way of life became a participant in the cycle of phenomena in nature, and therefore felt that he was not the main creation of God, as it was in Christianity, but only one of the components of the universe.
 Unlike Christianity, the phenomenon of Buddhism consists in the absence of a "logos" – the deity at the heart of the religion, since initially the image of the Buddha was interpreted as the image of a person who has achieved enlightenment. In Buddhism, there was no thesis about the value of human existence, which was interpreted as one-moment and changeable.
 Now let's trace how the specific philosophical and religious teachings of China influenced art and architecture.
 This is clearly visible both in secular buildings and in the temples of the three religions. The phenomenon of the transformation of the borrowed religion of Buddhism on local soil can be illustrated by the example of the unique cave temple complex of Dunhuang, the creation of which lasted over a thousand years, from the 4th to the 14th century. On the example of the wall paintings of sanctuaries, it is possible to trace how the borrowed subjects and techniques were gradually diversified and improved under the influence of local painting techniques. Moreover, scenes of secular life, portraits of benefactors, as well as a pantheon of Taoist deities were gradually added to the purely Buddhist subjects (fetian – the Chinese version of the heavenly apsaras, lords of Fuxi and NЯwa, etc.).
 The principles of feng shui and established hierarchy were also maintained in secular architecture and landscape design. So, all the main facades were oriented to the south, and the screens acted as barriers for evil spirits (in the gardens, such a function was performed by "natural screens" – "green screens", when one natural picture covered the other and it was impossible to view the entire garden at the same time. Chinese garden became the personification of the harmony of the world, therefore each landscape picture was carefully thought out. It was believed that gazebos – small pavilions in the garden became a place where a person encountered the laws of perfect harmony of nature. 
 An analysis of the relationship between traditional Chinese architecture and art and traditional philosophical and religious teachings proves that architecture and art were subject to the principles of feng shui and local "religious syncretism".

A17Digital patient simulation versus patient actors – what do participants prefer?

Nottinghamshire Healthcare Medical Education delivers simulation-based learning to over 500 medical students and junior doctors each year. The scenarios for these sessions are co-produced and delivered with a simulated patient actor. In January 2023, we introduced a new type of simulation allowing participants to interact with a digital patient. The AVATr digital patient received good feedback delivered remotely [1], but we intended to use it face to face. Our aim was to find out whether participants found the digital patient more or less useful than the patient actor. A secondary aim was to explore if the digital patient was helpful in preparing for simulation with a patient actor. The digital patient simulation was delivered in the morning of a full-day session to a cohort of F2 doctors. Participants sat on a chair in front of a green screen with a go-pro filming them. Participants were able to see themselves in a third-person perspective on a TV screen and interact with a digital patient. The digital patient was controlled by a facilitator who chose responses from a grid depending on what had been asked and how it had been asked. The participants experienced two scenarios – one around assessing psychosis and one on adult self-harm. The participants also had a simulation later that day with a patient actor. We collected qualitative and quantitative feedback via digital forms and analysed the results. Ninety-two participants attended the sessions between January 2023 and March 2023. 70% of participants Agreed or Strongly agreed that the virtual patient was useful, compared to 100% for the patient actor. If facilitator familiarity with technology was adjusted for 68% of participants, Agreed or Strongly agreed the digital patient was useful. Eighty-six per cent of participants believed that digital patient simulation helped them prepare for the patient actor simulation. Total numbers in Clustered bar graph comparing Likert-scale responses to the statements The Virtual Patient was useful and The Patient Actor was useful We found that whilst participants overwhelming preferred simulation with a patient actor to simulation with a digital patient, the digital patient played a role in helping prepare participants for simulation with a patient actor. Authors confirm that all relevant ethical standards for research conduct and dissemination have been met. The submitting author confirms that relevant ethical approval was granted, if applicable.

Green screen gets a magenta makeover from Netflix

Green screen gets a magenta makeover from Netflix

Content Production and the Contemporary Film and Television Industry: A Study of the LED Screen Virtual Production Studio

<p>自2019 年《曼達洛人》（The Mandalorian ）影集採用LED 幕取代藍、綠幕的製作方式，已為影視產業帶來新的變革。因此，本研究試圖探討LED幕虛擬製作室對當代影視產業、影視內容產製與視覺美學之影響。研究方法採用文獻分析法與深度訪談法，研究結果首先得出採用LED 幕虛擬製作室時，後期製作必須在前期階段就展開，且要在拍攝前完成虛實景物預覽等工作，此「後期前製化」改變了產製流程。其次，LED 幕虛擬製作室目前以製作廣告、MV 類型為多，建議未來可以開發電影或影集來擴展製作內容與國際競爭力。最後在視覺美學方面，多種數位科技的深度混合可讓演員進入虛擬空間演出時，感知到周遭環境的真實性，進而創造擬真性的虛實影像，以引發觀者沈浸在感知真實性之美學體驗。</p> <p> </p><p>The use of LED screens instead of blue and green screens for production in The Mandalorian television series since 2019 has brought about a revolution in the film and television industry. This study aims to explore the impact of LED screen virtual production studios on the contemporary film and television industry, content production, and visual aesthetics. The study employed literature analysis and in-depth interviews as research methodologies. Findings indicate that, firstly, the adoption of LED screen virtual production studios requires the post-production process to be initiated during the pre-production stage, and the preview of virtual and real scenery must be completed before shooting, resulting in a change in the production process. Secondly, LED screen virtual production studios are currently primarily used for producing advertisements and music videos. The study suggests that, in the future, the studio can be employed for creating films or television series in order to expand the range of content production and increase international competitiveness. Finally, the deep integration of various digital technologies in visual aesthetics allows performers to perceive the realism of their surroundings while performing in the virtual space, thereby creating a realistic virtual image to immerse viewers in an aesthetically pleasing experience of perceptual realism.</p> <p> </p>

Background Replacement in Video Conferencing

Article Background Replacement in Video Conferencing Kiran Shahi *, and Yongmin Li 1 Department of Computer Science, Brunel University London, Uxbridge, UB8 3PH, United Kingdom * Correspondence: 2144420@alumni.brunel.ac.uk Received: 17 March 2023 Accepted: 24 April 2023 Abstract: Background replacement is one of the most used features in video conferencing applications by many people, perhaps mainly for privacy protection, but also for other purposes such as branding, marketing and promoting professionalism. However, the existing applications in video conference tools have serious limitations. Most applications tend to generate strong artefacts (while there is a slight change in the perspective of the background), or require green screens to avoid such artefacts, which results in an unnatural background or even exposes the original background to other users in the video conference. In this work, we aim to study the relationship between the foreground and background in real-time videos. Three different methods are presented and evaluated, including the baseline U-Net, the lightweight U-Net MobileNet, and the U-Net MobileNet&ConvLSTM models. The above models are trained on public datasets for image segmentation. Experimental results show that both the lightweight U-Net MobileNet and the U-Net MobileNet& ConvLSTM models achieve superior performance as compared to the baseline U-Net model.

Analytical assessment of street-level tree canopy in Austrian cities: Identification of re-naturalisation potentials of the urban fabric

Climate change-related impacts such as heat stress, extreme weather events, and their consequences are particularly felt within densely built-up urban areas. Urban re-naturalisation is recognised as a promising cost-effective strategy for improving urban resilience to these environmental and societal issues. In this respect, the present contribution focuses on a comprehensive city-wide assessment of street-level urban tree canopy to detect the existing vegetation gaps and identify re-naturalisation potentials within the urban fabric for the three largest cities in Austria (Vienna, Graz, and Linz). The study relies on QGIS and R software environments to carry out spatial data analytics on georeferenced tree cadastre data and the global map of Local Climate Zones (LCZ) to compute spatial density maps and urban structure parameters. The results suggest a rather random distribution of tree clusters and highly fragmented instances within the city. This fragmentation is predominantly observed within central densely built urban fabric for all three cities, with the absence of street trees in peripheral urbanised areas being more prominent in Graz and Linz. The computed percentage of potentially disconnected areas in terms of the tree canopy for Vienna, Graz, and Linz amounts to 45%, 54%, and 37%, respectively. The analysis of urban structure revealed a homogeneous densely built-up character over central districts and a dominantly heterogeneous character across non-central and peripheral districts with a more openly built fabric (this heterogeneity is, generally more prominent in the case of Graz and Linz). In general, there are numerous opportunities for urban re-naturalisation, focusing on urban trees within such openly arranged buildings. Due to the evident physical constraints of the urban space within central districts, the consideration of building-level greening (e.g. green roofs, green facades) may be a better approach to urban re-naturalisation in these cases. Given the further constraints imposed by the abundance of historic buildings, such measures may not be feasible in every event. Hence, this calls for consideration of novel, innovative and emerging greening systems with the proposition of movable vertical green screens and vertical gardens.

Pembuatan Video Company Profile Fakultas Teknik Dan Komputer Universitas Harapan Medan Menggunakan Metode Chroma Key

The development of technology and information is increasingly rapid, it also has an impact on promotional media which increasingly have many ways of promoting goods or services. One of them is making a company profile video for the Faculty of Engineering and Computers Harapan Medan University, which does not yet have a company profile video as a promotional medium. Making a company profile video using the croma key method aims to introduce the institution to the wider community, convey what is on campus 3, Harapan Medan University and explain what rooms and facilities are on campus 3, Harapan Medan University. Therefore, in this study, a company profile video of the Faculty of Engineering and Computers Harapan Medan University will be made using a green screen effect using adobe illustrator, adobe after effects, and adobe premiere based on multimedia in the form of animated characters as the main characters. The method used in this study is the chroma key method because it combines animation with the original video. The results of this study will make it easier to introduce the Faculty of Engineering and Computers Harapan Medan University. By conducting a study using a questionnaire, researchers can get results from a company profile video that has been made for the Faculty of Engineering and Computers.
 

Effects of green infrastructure on the dispersion of PM2.5 and human exposure on urban roads

Urban green infrastructure (GI) has been widely demonstrated to effectively improve air quality in the built environment. However, due to the lack of comparative studies of the effects of different GI forms on PM2.5 dispersion, optimal GI designs suitable for different urban road types currently remain unclear. In this study, we adopted different roadside GI types in Hangzhou city as case studies and used the ENVI-met model to compare the effects of the different GI forms on PM2.5 dispersion and human exposure to PM2.5. The results indicated that 1) In open roads, the concave-shaped GI type could effectively reduce PM2.5 aggregation and human exposure on motorways, and the all-tree GI type performed the best in terms of sidewalk PM2.5 purification. 2) In street canyons, green roof and green screen were highly conducive to PM2.5 concentration reduction under commuter exposure compared with traditional green solutions. 3) There were trade-offs in the GI-PM2.5 interaction. GI types which can reduce pedestrian exposure tend to increase exposure in motorways. The same GI type deployed along the two different road types could yield completely opposite dispersion effects. Novel GI types had better environmental performance and relatively high economic cost. All decision-making should be based on the trade-offs between the advantages and disadvantages of GI. Our study also highlights the importance of comprehensive consideration of GI and road types and local wind conditions in future urban road planning and GI applications.

Thermal performance of indirect green façade in composite climate of India

Many experimental and theoretical studies have shown that green facades can increase the thermal efficiency of a building's façade. Previous field research has focused on humid subtropical and tropical climates and the Mediterranean climate. There has been no research directed at the Indian climates. Moreover, the studies have evaluated microclimate and inside surface or ambient temperatures; however, whether its application creates a comfortable environment is yet to be found. A real-time study was performed to assess the effect of indirect green facade systems on the glazed facade to evaluate thermal comfort in India's composite climate (Hot semi-arid climate Bsh). Two glazed facades were examined: one with a green screen of Bengal clock vine and the other bare to serve as the base case. The temperatures on the southwest-oriented green façades were up to 8.1°C lower than the respective temperatures of the uncovered façade. In summer, the nighttime temperatures for the vegetated façade were up to 5.1°C higher than those for the base facade. No significant insulating effect in the cold season was observed. The highest reduction was seen between 2 p.m. and 6 p.m., implying the relation with high solar radiation during these hours in the southwest orientation. While the green facade helped lower building temperatures, it also raised relative humidity, making an uncomfortable indoor thermal environment. The study also aimed to find the appropriate distance to install a green façade. Although a green façade controls temperature, the study finds that a proper distance between greenery and the facade surface improves the system's thermal performance. According to the study, installing a green facade with more than 150 mm distance between the greenery system and the façade surface is optimum in New Delhi's composite climate. The study's findings try to fill the gap of the impact of green facades in the Indian climate to see its applicability on a larger scale; however, the results show increased discomfort with higher relative humidity as the climate changes from dry to humid.