Unreal Game Engine Research Articles

Innovative Strategies of Virtual Reality Technology in Ethnic Dance Inheritance

Abstract In the quest to safeguard and revitalize folk dance heritage, this study explores the transformative potential of virtual reality (VR) technology. We developed an immersive display system using the Unreal game engine, incorporating a dance movement database, virtual reality immersion, and precise inertial motion capture. This innovative approach captivates users with an immersive folk dance experience and boasts a high motion recognition accuracy (99.51%) and an overall accuracy of 96%. Comparative experiments highlight VR’s advantages in making folk dance education more interactive and enjoyable without sacrificing ease of use. Virtual reality emerges as a vital tool in engaging new generations with folk dance, suggesting a vibrant future for intangible cultural heritage preservation.

Desineer: Experimental Space Production in VR Environment

Architecture students and professionals had the opportunity to produce experimental spaces with the power of computer technologies, apart from traditional methods in space production. Technologies such as parametric design, Building Information Modelling (BIM), visual coding, and virtual reality hold new horizons for space production and the architecture itself. Despite all their potentials, they are still mainly used to support the design process or to present a project. The use of these tools is limited only to the effort to produce different and "impressive" forms based on aesthetic concerns. The study aims to examine the different possibilities of space production through digital space experiments. In this context, an experimental Virtual Reality (VR) application named “Desineer” was developed with Unreal game engine. The program has an easy interface where users can directly grab, drag, place and shape mesh objects. The Hands have played an important role in production throughout human history. Desineer eliminates the intermediary tools such as keyboard and mouse, with the help of VR technology, allowing the production of digital space directly by hands. By using the program, experiments were conducted on the manual production of digital space at Dumlupınar University Faculty of Architecture for students to gain new experiences. Within the scope of the study, first, discussions were held on space and the production of it for the students to develop their own ideas and perspectives, albeit fundamentally. Later, poems on different themes belonging to various poets were given to the students. The students read these poems and think about how the poems made them think and feel. Finally, the students produced improvised spaces based on these ideas and emotions using Desineer. It was observed that the workshop contributed students to the development of different perspectives on the production of space.

AI-powered Human Digital Twins in Virtual Therapeutic Sessions

When patients are unwilling to speak openly, therapists miss valuable information and may not be able to provide best possible care. This study investigated the idea of human Digital Twins (DT) of patients and therapists as a novel solution to encourage them to speak openly. We proposed a methodology to create highly realistic human DT using computer vision, 3D scanning, Metahumans tool, and Unreal game engine. Based on this methodology, we created two versions of virtual therapeutic session: a) video-based virtual sessions with real human and b) virtual sessions with DT of patients and therapists. Twelve therapists then were asked to evaluate technology acceptance of each virtual session. Participants reported significantly lower trust to virtual sessions with highly realistic digital human compared to video-based one. Findings from this study may provide insights regarding opportunities and challenges of virtual therapy using highly realistic digital human technologies. This work also contributes to the virtual therapeutic research field by proposing an AI-powered methodology to create human DT of patients and therapists. Further studies are needed to provide more validation of the efficiency of this approach in virtual sessions for mental health support.

Potentials of game engines for wind power digital twin development: an investigation of the Unreal Engine

Digital twin technologies have become popular in wind energy for monitoring and what-if scenario investigation. However, developing a digital representation of the wind is challenging, especially due to the digital twin platform constraints. Game engines might be possible to solve this issue, especially since game engines have been used for product design, testing, prototyping, and also digital twins. Therefore, this study investigates the potential of developing a digital twin of wind power in the Unreal game engine. A case study of two types of wind turbines (Vestas V164-8 and Enercon E-126 7.580) and one location (Esbjerg, Denmark) is chosen for this study. The digital twin includes the environment with historical wind data and the visual representation of the wind turbine with a wind power production model and the estimated production in the given wind conditions of the area. The results show that game engines are viable for building entire digital twins where a realistic graphical user interface is required. Unreal Engine 5 provides the tools for modelling the landscape, surrounding water, and lighting. In addition, the Unreal Engine ecosystem provides vast amounts of content, such as 3D assets and game logic plugins, easing the digital twin development. The results prove that digital twins built in Unreal Engine 5 have great potential development of digital twins and user interfaces for communicating with a digital twin. The developed digital twin allows for further extension to benefit future digital twins utilizing wind turbines.

Development of a Novel Object Detection System Based on Synthetic Data Generated from Unreal Game Engine

This paper presents a novel approach to training a real-world object detection system based on synthetic data utilizing state-of-the-art technologies. Training an object detection system can be challenging and time-consuming as machine learning requires substantial volumes of training data with associated metadata. Synthetic data can solve this by providing unlimited desired training data with automatic generation. However, the main challenge is creating a balanced dataset that closes the reality gap and generalizes well when deployed in the real world. A state-of-the-art game engine, Unreal Engine 4, was used to approach the challenge of generating a photorealistic dataset for deep learning model training. In addition, a comprehensive domain randomized environment was implemented to create a robust dataset that generalizes the training data well. The randomized environment was reinforced by adding high-dynamic-range image scenes. Finally, a modern neural network was used to train the object detection system, providing a robust framework for an adaptive and self-learning model. The final models were deployed in simulation and in the real world to evaluate the training. The results of this study show that it is possible to train a real-world object detection system on synthetic data. However, the models showcase a lot of potential for improvements regarding the stability and confidence of the inference results. In addition, the paper provides valuable insight into how the number of assets and training data influence the resulting model.

A Framework for Personalized Training at Home Based on Motion Capture

As the number of single-person households continues to increase, contents related to exercise at home are increasing. Therefore, this paper proposes a framework for efficient home fitness. The home fitness framework proposed in this paper is based on a method of acquiring expert motion information and providing it to users. To this end, content creation and provision are implemented by using Kinect and Unreal game engine. In addition, it is possible to provide customized home fitness in consideration of the user's athletic ability. The proposed system first captures the expert's motion and stores it. We propose a method that can efficiently store stop motion and dynamic motion storage. In the case of each user, since there is a difference in exercise ability for each individual, an adverse effect may occur if an excessively accurate motion is requested. Therefore, to solve these problems, we present the parts that can be considered for each joint. For the exercise motion provided by the expert, a method was provided that allows the user to adjust the degree of matching for each joint in consideration of user's own exercise ability. That is, joint parts that do not require exact matching could be completely excluded from matching. For parts that would be subject to large changes, a range of errors is specified. As the training progresses, the error range is reduced, and the excluded parts are presented to be matched gradually. Such adjustments are made based on expert feedback. In this way, it was possible to improve the exercise effect gradually. This paper proposes an effective method for personalized home fitness according to the user's athletic ability. This will apply to various fields besides home fitness.

An empirical framework for developing and evaluating a Virtual Assembly Training System in learning factories

ABSTRACT Higher Education Institutions are introducing Virtual-Reality (VR) development courses and divisions focussing on the development of Virtual Environments which are in high demand. Students without a programming background are not familiar with the processes of developing Virtual Assembly Training Systems (VATS), consequently, they learn through trial and error. To address this challenge the development of two similar VATS was observed to propose a framework detailing the workflow, roles, tasks and deliverables undertaken during development. Both VATS are based on the assembly of a top bracket, an elementary railcar component rendered via the HTC Vive Pro. The first VATS was developed by expert developers and the other through project-based learning with five engineering students. The case study was conducted at the Railcar Learning Factory wherein SolidWorks, Sketchup, Blender and Unreal Game Engine were used for CAD modelling and visual scripting. The encountered challenges and best practices evolved into the proposed framework. Findings suggest that engineers without a programming background can develop VATS when capacitated with a blend of asynchronous and synchronous learning. Importantly, Learning Factory Managers should consider the lifecycle of VR prototypes to ensure their usage in the industry. This approach can contribute to generating industry-relevant research output.

Automatically Generating Summary Visualizations from Game Logs

In this paper we describe a system called ViGLS (Visualization of Game Log Summaries) that generates summaries of gameplay sessions from game logs. ViGLS automatically produces visualization of the summarized actions that are extracted based on cognitive models of summarization. ViGLS is implemented using a service-oriented architecture, de-coupling the summarization methods from any particular game engine being used. The camera code libraries used in visualization are based on constraint based camera control approaches and, in our implementation, make use of the scripting layer of the Unreal game engine.

Gamification and Hazard Communication in Virtual Reality: A Qualitative Study

An effective warning attracts attention, elicits knowledge, and enables compliance behavior. Game mechanics, which are directly linked to human desires, stand out as training, evaluation, and improvement tools. Immersive virtual reality (VR) facilitates training without risk to participants, evaluates the impact of an incorrect action/decision, and creates a smart training environment. The present study analyzes the user experience in a gamified virtual environment of risks using the HTC Vive head-mounted display. The game was developed in the Unreal game engine and consisted of a walk-through maze composed of evident dangers and different signaling variables while user action data were recorded. To demonstrate which aspects provide better interaction, experience, perception and memory, three different warning configurations (dynamic, static and smart) and two different levels of danger (low and high) were presented. To properly assess the impact of the experience, we conducted a survey about personality and knowledge before and after using the game. We proceeded with the qualitative approach by using questions in a bipolar laddering assessment that was compared with the recorded data during the game. The findings indicate that when users are engaged in VR, they tend to test the consequences of their actions rather than maintaining safety. The results also reveal that textual signal variables are not accessed when users are faced with the stress factor of time. Progress is needed in implementing new technologies for warnings and advance notifications to improve the evaluation of human behavior in virtual environments of high-risk surroundings.

Dream

When the Covid-19 pandemic closed London, England's theaters, digital studio Marshmallow Laser Feast (MLF) was already working on Dream, a mixed-reality live performance intended to bring together live and online audiences. Co-developed with the Royal Shakespeare Company, the Manchester International Festival, and the Philharmonia Orchestra, Dream's focus on the integration of live performance and immersive technologies has taken on a new significance since the closure of so many performance venues around the world. It was funded by the UK government's Audience of the Future program. Rather than re-create A Midsummer's Night Dream, the team mined the original text for any mention of plants, flowers, trees, or creatures. These references were then used to create a lush, immersive forest world within Epic's Unreal game engine. As with many of MLF's other works, this play revalues the natural world by revealing unseen and unknown presences in the forest to (human) audiences.

A live comparison between Unity and Unreal game engines

A game engine is an ongoing thread that helps us in making and designing beautiful games with the simplest methods and least resources. Game engines support a wide variety of playing platforms that can translate the game designed into a playable game in different platforms like PlayStation, PC, Xbox, Android, IOS and Nintendo. There is a wide variety of game engines that suits every programmer and designer working on engines such as Unity game engine, Unreal game engine and construct game engine. In order to make a game one has to learn how to code in one of these engines. From our results, Unity has everything you need to create games in one place. It has an integrated development framework that creates rich solutions and out-of-box functionality to make games. This paper recommends making a decision one has to look at, such as what platforms one wants to target and how one can plan on monetising their product. Keywords: Game engine, compare engine, Unity game, Unreal game, platforms.

Virtual Reality for Smart Urban Lighting Design: Review, Applications and Opportunities

More and more cities are evolving into smart cities, increasing their attractiveness, energy efficiency, and users’ satisfaction. Lighting systems play an important role in the evolution process, thanks to their ability to affect city life at night along with people’s mood and behaviour. In this scenario, advanced lighting design methods such as virtual reality (VR) became essential to assess lighting systems from different points of view, especially those linked with the city users’ expectations. Initially, the review highlights a list of objective and subjective parameters to be considered for the lighting design of three main city areas/applications: roads, green areas and buildings. Besides, the state-of-art in using VR for outdoor lighting design is established. Finally, the Unreal game engine is used to analyse the ability of VR to take into account the lighting parameters, not yet investigated in current literature and to highlight the VR potential for augmenting lighting design. The results confirm the benefit of using VR in lighting design, even if further investigations are needed to establish its reliability, especially from the photometrical point of view.

Basic elements and characteristics of game engine

Contemporary game engines are invaluable tools for game development. There are many engines available, each of them which excel in certain features. Game Engines is a continuous series that helps us to make and design beautiful games in the simplest and least resource way. Game drives support a wide variety of play platforms that can translate the game into a game that can be played on different platforms such as PlayStation, PC, Xbox, Android, IOS, Nintendo and others. There is a wide range of game engines that suit every programmer and designed to work on Unity Game Engine, Unreal Game Engine and Construct Game Engine. In the research paper, we discuss the basic elements of the game engine and how to make the most useful option among Game Engines depending on your different needs and needs of your game. Keywords: Game engine, game engine element, basics of game engine.

Editorial Issue 28.5

This issue contains six papers. In the first paper, Hui Liang, Jian Chang, and Shujie Deng, from the National Centre for Computer Animation in Bournemouth, UK; Can Chen from Changzhou University, China; Ruo-feng Tong, from Zhejiang University, Hangzhou, China; and Jian J. Zhang, from Bournemouth University, UK, design an immersive storytelling environment that allows multiple players to use naturally interactive hand gestures to manipulate virtual puppetry for assisting narration. A set of multimodal interaction techniques is presented for a hybrid user interface that integrates existing 3D visualization and interaction devices including head-mounted displays and depth motion sensor. In the second paper, Sybren A. Stüvel, Frank van der Stappen, and Arjan Egges, from Universiteit Utrecht, The Netherlands, present an investigation into the accuracy of human observers with regard to the recognition of collisions between virtual characters. They show the result of two user studies, where participants classify scenarios as “colliding” or “not colliding”; a pilot study investigates the perception of static images, whereas the main study expands on this by employing animated videos. In the pilot experiment, they investigated the effect of two variables on the ability to recognise collisions: distance between the character meshes, and visibility of the inter-character gap. In the main experiment, they investigate the angle between the character paths and the severity of the (near) collision. In the third paper, Marios Andreas Kyriakou, from the University of Cyprus; Xueni Pan, from the University of London, UK; and Yiorgos Lambros Chrysanthou, from the University of Cyprus examine attributes of virtual human behavior that may increase the plausibility of a simulated crowd and affect the user's experience in Virtual Reality (VR). Purpose-developed experiments in both Immersive and semi-Immersive VR systems queried the impact of collision and basic interaction between real users and the virtual crowd and their effect on the apparent realism and ease of navigation within VR. Participants' behavior and subjective measurements indicated that facilitating collision avoidance between the user and the virtual crowd makes the virtual characters, the environment, and the whole VR system appear more realistic and lifelike. In the fourth paper, Mihai Polceanu and Cedric Buche, from Florida International University, and Lab-STICC - ENIB, CERV, Plouzané, France, introduce a study of existing approaches that explicitly use mental simulation. Current implementations of the mental simulation paradigm, taken together, computationally address many aspects suggested by cognitive science research. Agents are able to find solutions to nontrivial scenarios in virtual or physical environments. Existing systems also learn new behavior by imitation of others similar to them and model the behavior of different others with the help of specialized models, culminating with the collaboration between agents and humans. Approaches that use self models are able to mentally simulate interaction and to learn about their own physical properties. In the fifth paper, Yuxing Qiu, Lipeng Yang, Shuai Li, and Qing Xia, from Beihang University, Beijing, China; Hong Qin, from Stony Brook University, USA; and Aimin Hao, from Beihang University, Beijing, China, advocate a method for the modeling and enhancement of scale-sensitive fluid details. The core of their method is the coupling of multilayer depth regression analysis and FLIP fluid simulation. First, they capture the depth buffer of the fluid surface from the top of scene. Second, they employ depth peeling to decompose the target fluid volume into multiple layers and conduct time–space analysis over surface layers. Third, they propose a logistic regression-based model to pinpoint the interacting regions, wherein multiple detail-relevant factors are taken into account. Finally, details are enhanced by animating extra diffuse materials and augmenting the air–fluid mixing phenomenon. Abdullah Bulbul, from Yildirim Beyazit Universitesi, Ankara, Turkey, and Rozenn Dahyot, from Trinity College, Dublin, Ireland, propose to automatically populate geo-located virtual cities by harvesting and analyzing online contents shared on social networks and websites. They show how pose and motion paths of agents can be realistically rendered using information gathered from social media. 3D cities are automatically generated using open source information available online. To provide a final rendering of both static and dynamic urban scenes, they use Unreal game engine.

Populating virtual cities using social media

AbstractWe propose to automatically populate geo‐located virtual cities by harvesting and analyzing online contents shared on social networks and websites. We show how pose and motion paths of agents can be realistically rendered using information gathered from social media. 3D cities are automatically generated using open‐source information available online. To provide our final rendering of both static and dynamic urban scenes, we use Unreal game engine.

Virtual Reality Visualisation of a Biologically Realistic Anatomical and Functional Model of the Tadpole Spinal Cord

Virtual Reality Visualisation of a Biologically Realistic Anatomical and Functional Model of the Tadpole Spinal Cord

Virtual Reality Visualisation of a Biologically Realistic Anatomical and Functional Model of the Tadpole Spinal Cord

Virtual Reality Visualisation of a Biologically Realistic Anatomical and Functional Model of the Tadpole Spinal Cord