• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2381-2398
• /
• 2024

The construction of virtual indoor spaces is crucial for the development of metaverses, virtual production, and other 3D content domains. Traditional methods for creating these spaces are often cost-prohibitive and labor-intensive. To address these challenges, we present a pipeline for generating digital twins of real indoor environments from RGB-D camera-scanned data. Our pipeline synergizes space structure estimation, 3D object detection, and the inpainting of missing areas, utilizing deep learning technologies to automate the creation process. Specifically, we apply deep learning models for object recognition and area inpainting, significantly enhancing the accuracy and efficiency of virtual space construction. Our approach minimizes manual labor and reduces costs, paving the way for the creation of metaverse spaces that closely mimic real-world environments. Experimental results demonstrate the effectiveness of our deep learning applications in overcoming traditional obstacles in digital twin creation, offering high-fidelity digital replicas of indoor spaces. This advancement opens for immersive and realistic virtual content creation, showcasing the potential of deep learning in the field of virtual space construction.

• Structural Engineering and Mechanics
• /
• v.7 no.2
• /
• pp.159-180
• /
• 1999

The present paper shows a new non-tensorial approach to derive basic equations for various structural analyses. It can be used directly in numerical computation procedures. The aim of the paper is, however, to show that the approach serves as an excellent tool for analytical purposes also, working as a link between analytical and numerical techniques. The paper gives a method to derive, at first, expressions for strains in general beam and shell analyses, and secondly, the governing equilibrium equations. The approach is based on the utilization of local fixed Cartesian coordinate systems. Applying these, all the definitions required are the simple basic ones, well-known from the analyses in common global coordinates. In addition, the familiar principle of virtual work has been adopted. The method will be, apparently, most powerful in teaching the theories of curved beam and shell structures for students not familiar with tensor analysis. The final results obtained have no novelty value in themselves, but the procedure developed opens through its systematic and graphic progress a new standpoint to theoretical considerations.

• ETRI Journal
• /
• v.35 no.5
• /
• pp.911-914
• /
• 2013

This letter presents Progression-Preserving Projection, a dimension reduction technique that finds a linear projection that maps a high-dimensional sensor dataset into a two- or three-dimensional subspace with a particularly useful property for visual exploration. As a demonstration of its effectiveness as a visual exploration and diagnostic means, we empirically evaluate the proposed technique over a dataset acquired from our own virtual-reality-enhanced ball-intercepting training system designed to promote the upper extremity movement skills of individuals recovering from stroke-related hemiparesis.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.450-459
• /
• 2014

In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider tree-growing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local self-similarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease.

• Structural Engineering and Mechanics
• /
• v.67 no.3
• /
• pp.291-300
• /
• 2018

In this work, a new trigonometry theory of shear deformation is developed for the static analysis of thick isotropic beams. The number of variables used in this theory is identical to that required in the theory of Euler-Bernoulli, sine function is used in the displacement field in terms of the coordinates of the thickness to represent the effects of shear deformation. The advantage of this theory is that shear stresses can be obtained directly from the relationships constitute, while respecting the boundary conditions at the free surface level of the beam. Therefore, this theory avoids the use of shear correction coefficients. The differential equilibrium equations are obtained using the principle of virtual works. A thick isotropic beam is considered, whose numerical study to show the effectiveness of this theory.

• Structural Engineering and Mechanics
• /
• v.63 no.5
• /
• pp.683-689
• /
• 2017

In this paper, a hyperbolic shear deformation theory is presented for bending analysis of functionally graded beams. This theory used in displacement field in terms of thickness co-ordinate to represent the shear deformation effects and does not require shear correction factor, and gives rise to transverse shear stress variation such that the transverse shear stresses vary parabolically across the thickness satisfying shear stress free surface conditions. The governing equations are derived by employing the virtual work principle and the physical neutral surface concept. A simply supported functionally graded beam subjected to uniformly distributed loads and sinusoidal loads are consider for detail numerical study. The accuracy of the present solutions is verified by comparing the obtained results with available published ones.

• Advances in robotics research
• /
• v.2 no.1
• /
• pp.1-11
• /
• 2018

To monitor the environment and determine the source of a pollutant gradient using a multiple robot swarm, we propose a hybrid algorithm that combines two bio-inspired algorithms mimicking chemotaxis and pheromones of bacteria. The algorithm is implemented in virtual robot agents in a simulator to evaluate their feasibility and efficiency in gradient maps with different sizes. Simulation results show that the chemotaxis controller guided robot agents to the locations with higher pollutant concentrations, while the pheromone marked in a virtual field increased the efficiency of the search by reducing the visiting redundancy. The number of steps required to reach the target point did not increase proportionally as the map size increased, but were less than those in the linear whole-map search method. Furthermore, the robot agents could function with simple sensor composition, minimum information about the map, and low calculation capacity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.417-423
• /
• 2021

Recently, in the Game industries, they are increasing to use of game engines to reduce the development cost of 3D content and software. In particular, Unreal Engine provides a blueprint visual scripting function that enables software production without programming (coding). Although High-end video content can be produced, the problem is that content development is complicated and requires advanced manpower. To solve this problem, we propose an optimized VR game context process. This is because 1) a Blueprint visual script is used, 2) VR games with various interactions can be produced, 3) Non-majors in the software field (or groups) can develop advanced content. In various related industries such as defense, medical care, manufacturing, and construction, we may easily develop any game content without programming with our refined VR rhythm action game development process. We expect to reduce the development cost with the process advantages in the game industries.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2007.08a
• /
• pp.421-424
• /
• 2007

We have succeeded in designing a PHUND (portable head up navigation display), which has a compact system with a MD panel and full color display device using RGB LED sources. The PHUND has been developed as an alternative to conventional built-in type HUD system targeting the high volume aftermarket with an affordable price.