• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.638-653
• /
• 2022

In this paper, we propose the new method of creating 3D virtual-human reflecting the pattern of clothes worn by the person in the high-resolution whole body front image and the body shape data about the person. To get the pattern of clothes, we proceed Instance Segmentation and clothes parsing using Cascade Mask R-CNN. After, we use Pix2Pix to blur the boundaries and estimate the background color and can get UV-Map of 3D clothes mesh proceeding UV-Map base warping. Also, we get the body shape data using SMPL-X and deform the original clothes and body mesh. With UV-Map of clothes and deformed clothes and body mesh, user finally can see the animation of 3D virtual-human reflecting user's appearance by rendering with the state-of-the game engine, i.e. Unreal Engine.

• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.69-78
• /
• 2020

K/DA is a K-pop virtual idol based on the game character. This study analyzed the creation process, characteristics and existential meaning of virtual idols from the perspective of Pataphysics. K/DA is a character with both characteristics of game character and K-pop girl group. Also, virtual character and real idol share the body through motion capture and augmented reality(AR). As a result, K/DA crosses virtual and reality, and at the same time becomes a pataphysical subject that does not belong to either virtual or reality. K/DA is suggested a third zone where digital subjects will be located in the future.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.473-480
• /
• 2014

As the use of computer has been popularized these days, an active research is in progress to make much more convenient and natural interface compared to the existing user interfaces such as keyboard or mouse. For this reason, there is an increasing interest toward Microsoft's motion sensing module called Kinect, which can perform hand motions and speech recognition system in order to realize communication between people. Kinect uses its built-in sensor to recognize the main joint movements and depth of the body. It can also provide a simple speech recognition through the built-in microphone. In this paper, the goal is to use Kinect's depth value data, skeleton tracking and labeling algorithm to recognize information about the extraction and movement of hand, and replace the role of existing peripherals using a virtual mouse, a virtual keyboard, and a speech recognition.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.2
• /
• pp.1-8
• /
• 2009

This paper introduces a virtual dress up system, according to user's input model and garment image. At first step, we deform the garment image by using skeleton structures and ARAP method. Next step, sampling the boundary points and find their matching vertices which are used for optimizing the boundary fitting. In 2D rendering of the dress up, they have some unrealistic results, so we reconstruct the garment mesh to the 3D mesh. Rendering from the reconstructed 3D mesh, we can get the final dress up result. We present that our system produce a visually plausible and well-fitted virtual dress up results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.731-736
• /
• 2008

In this paper, we propose the movement detection algorithm by using virtual skeleton model. To do this, first, we eliminate error values by using conventioanl method based on RGB color model and eliminate unnecessary values by using the HSI color model. Second, we construct the virtual skeleton model with skeleton information of 10 peoples. After matching this virtual model to original image, we extract the real head silhouette by using the proposed circle searching method. Third, we extract the object by using the mean-shift algorithm and this head information. Finally, we validate the applicability of the proposed method through the various experiments in a complex environments.

• Journal of Korea Game Society
• /
• v.21 no.5
• /
• pp.75-86
• /
• 2021

This study examines the access index to the development of immersive contents suitable for elementary school users. The findings of this study can be used as a correct development guide for companies participating in the production of virtual reality sports room contents, by providing users with an effective content experience of education and physical exercise based on the immersive content of sports, physical education, and convergence learning linked with various sensor technologies. As for the research method, this study selected content developed based on the standardization guide of the supporting institution. Through research using expert advice, interviews with sports managers, and content experience survey, this study derived a content access standard index of the virtual reality sports room. Finally, the study verified the developed contents through advanced development applying the production standard indicators.

• Science of Emotion and Sensibility
• /
• v.5 no.4
• /
• pp.67-75
• /
• 2002

The purpose of this study is to assess the ability of balance control in virtual moving surround stimulation using head mount display (HMD) device and force platform in patients with brain injury. Fifteen patients with stroke (mean age 54.47 yrs) and fifteen healthy normal persons participated. COP parameters were obtained total path distance, frequency of anterior-posterior and medial-lateral component by FFT analysis, weight-spectrum analysis in the two different conditions; (1) during comfortable standing with opened or closed eyes, (2) during virtual moving surround stimulation delivered using HMD with four different moving pattern. Moving patterns consisted of close-far, superior-inferior lilting (pitch) , right-left tilting (roll) and horizontal rotation (yaw) movement. In all parameters, the test-retest reliability was high. Also, the construct validity of virtual moving surround stimulation was excellent (p＜0.05). A posturographic balance assessment system equiped with virtual moving surround stimulation using HMD is considered clinically useful in evaluation of balance control in patients with brain injury.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.1-11
• /
• 2020

Image-based virtual try-on (VTON) is becoming popular for online apparel shopping, mainly because of not requiring 3D information for try-on clothes and target humans. However, existing 2D algorithms, even when utilizing advanced non-rigid deformation algorithms, cannot handle large spatial transformations for complex target human poses. In this study, we propose a 3D clothing reconstruction method using a 3D human body model. The resulting 3D models of try-on clothes can be more easily deformed when applied to rest posed standard human models. Then, the poses and shapes of 3D clothing models can be transferred to the target human models estimated from 2D images. Finally, the deformed clothing models can be rendered and blended with target human representations. Experimental results with the VITON dataset used in the previous works show that the shapes of reconstructed clothing are significantly more natural, compared to the 2D image-based deformation results when human poses and shapes are estimated accurately.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.168-175
• /
• 2009

Stanislavsky's acting system is based on the sensory memory of an incident that an actor has actually experienced, but Michael Chekhov insisted that in relation to the acting technique of actors, they should find the virtual and unreal external stimuli caused by emotion and imagination irrespective of their personal experience. As such, Stanislavsky's acting system and Michael Chekhov's acting technique are very different in terms of the acting method used. In actual acting, however, the acting system and the acting technique should have a close relationship. Any acting performed by an actor cannot be totally psychological or physical because the body and the mind cannot be separated. It is for this reason that all kinds of training should be both psychological and physical training and should not be conducted only mechanically. Acting is the ability of actors to imagine the virtual or fictitious reality and to express their indignation ability onstage. As actors stimulate and train their own fantasy and imagination, they can greatly improve their ability to embody or express the inner world of the characters they are portraying in a play.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.125-132
• /
• 2024

Recently, with immersive virtual reality(IVR) technologies, various services such as education, training, entertainment, industry, healthcare and remote collaboration have been applied. In particular, researches are actively being studied to visualize and interact with virtual humans, research on virtual pets in IVR is also emerging. For interaction with the virtual pet, similar to real-world interaction scenarios, the most important thing is to provide physical contact such as haptic and non-verbal interaction(e.g., gesture). This paper investigates the effects on factors (e.g., shape and texture) of passive haptic feedbacks using mapping physical props corresponding to the virtual pet. Experimental results show significant differences in terms of immersion, co-presence, realism, and friendliness depending on the levels of texture elements when interacting with virtual pets by passive haptic feedback. Additionally, as the main findings of this study by statistical interaction between two variables, we found that there was Uncanny valley effect in terms of friendliness. With our results, we will expect to be able to provide guidelines for creating interactive contents with the virtual pet in immersive VR environments.