• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.4
• /
• pp.158-168
• /
• 2000

Vehicle driving simulators can provide engineers with benefits on the development and modification of vehicle models. One of the most important factors to realistic simulations is the fidelity given by a motion system and a real-time visual image generation system. Virtual reality technology has been widely used to achieve high fidelity. In this paper the virtual environment including a visual system like a head-mounted display is developed for a vehicle driving simulator system by employing the virtual reality technique. virtual vehicle and environment models are constructed using the object-oriented analysis and design approach. Accordint to the object model a three dimensional graphic model is developed with CAD tools such as Rhino and Pro/E. For the real-time image generation the optimized IRIS Performer 3D graphics library is embedded with the multi-thread methodology. Compared with the single loop apprach the proposed methodology yields an acceptable image generation speed 20 frames/sec for the simulator.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.2
• /
• pp.1-8
• /
• 2015

Tracking of an object in 3D space performed in real-time is a significant task in different domains from autonomous robots to smart vehicles. In traditional methods, specific data acquisition equipments such as radars, lasers etc, are used. Contemporary computer technology development accelerates image processing, and it results in three-dimensional stereo vision to be used for localizing and object tracking in space. This paper describes a system for tracking three dimensional motion of an object using color information in real time. We create stereo images using pair of a simple web camera, raw data of an object positions are collected under realistic noisy conditions. The system has been tested using OpenCV and Matlab and the results of the experiments are presented here.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1013-1014
• /
• 2008

In this paper, we propose a new method of generating 3D face by using single frontal face image and 3D generic face model. By using active appearance model (AAM), the control points among facial feature points were localized in the 2D input face image. Then, the transform parameters of 3D generic face model were found to minimize the error between the 2D control points and the corresponding 2D points projected from 3D facial model. Finally, by using the obtained model parameters, 3D face was generated. We applied this 3D face to 3D game framework and found that the proposed method could make a realistic 3D face of game user.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.164.3-164
• /
• 2001

In this paper, we present a method for obtaining the actual modeling data through reconstructing a 3D data from an image and a method of estimating the geometrical information and the camera location of architectural objects from a photograph containing a virtual environment are introduced. Our approach combines both geometry-based and image-based modeling techniques. The modeling system is effective and robust because it exploits constrains that are characteristic of architectural scenes. Our approach can recover models for use in either geometry-based rendering systems. We present results that demonstrate out approach´s ability to create realistic renderings of architectural scenes from viewpoints far from the original photographs.

• Journal of Korea Multimedia Society
• /
• v.18 no.3
• /
• pp.349-358
• /
• 2015

Simulating color appearance of makeup effect is an important issue in computer graphics as well as cosmetic industry. Most of previous works on makeup simulation are simple color blending to mimic the cosmetic effects. Some of previous works employed Kubelka-Munk model to accurately simulate the layering effect of cosmetics. However, the simulation limited on single point, and the rest of area are still computed by simple color blending utilizing the color of the single point simulation. This paper presents an image-based method to compute the color appearance effect of makeup application using per-pixel Kubelka-Munk model. Unlike the previous methods, it is possible to compute per-pixel application thickness as well as optical property of cosmetics. The computed thickness pattern can be used in makeup simulation for a more realistic makeup simulation.

• Journal of the Korean Society of Costume
• /
• v.54 no.4
• /
• pp.113-127
• /
• 2004

This study examined the trend of pattern which appeared throughout men's clothing fashion magazine from 1999 to 2002 and the influence which the demographic characteristic have on the sensibility dimension of pattern and the preference degree of kinds of pattern. The results of study were as follows. 1) The pattern which was used most frequently on recent men's clothing was a length stripe, and the representation technique which was used most frequently on recent men's clothing was the technique of a geometric expression. 2) The pattern which men and women preferred most out of ten kinds of patterns-length stripe, width stripe, oblique stripe, check, square, waterdrop, paisley, flower of style shape, flower of realistic shape, flower of shape-was a length stripe. 3) The sensibility dimension of pattern image was composed of fascination, dignity, daring, gentleness, and reality. 4) Because sensitivity dimension and kinds of pattern were significant according to the distinction of sex, vocation, academic career, income, this study can conclude the demographic characteristic have an influence on sensitivity dimension and kinds of pattern.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.85-88
• /
• 2002

Until recently, there have been fundamental changes in many fields of industries. Especially, the mass-production is being changed into mass-customization. In order to construct a 3D e-catalog system far the utilization of mass-customization, there are several matters to consider. Setting realistic 3D image should be effective fur providing the customers with the product information with reality and raising their interest. This study explains the whole process to convert CAD data formed from the production activities into VRML data used in virtual reality environment. Examples are given and discussed to validate the proposed activity.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1183-1187
• /
• 2003

Five new satellite image interpretation modules are developed. The modules are for: 1) construction of a realistic color image, 2) feature recognition by intensity filtering, 3) removal of spurious spots by next -neighbor count comparison, 4) deviation-amplification filtering, and 5) feature recognition by spectral distribution pattern. The modules were applied to a set of IKONOS images of 8 x 8 km area of the city of Daejeon, Korea, to recognize the distribution of various features such as water resources, playgrounds, forests, etc.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.479-481
• /
• 2023

Generative Adversarial Networks (GANs) have facilitated substantial improvement in single-image super-resolution (SR) by enabling the generation of photo-realistic images. However, the high memory requirements of GAN-based SRs (mainly generators) lead to reduced performance and increased energy consumption, making it difficult to implement them onto resource-constricted devices. In this study, we propose an efficient and compressed architecture for the SR-GAN (generator) model using the model compression technique Knowledge Distillation. Our approach involves the transmission of knowledge from a heavy network to a lightweight one, which reduces the storage requirement of the model by 58% with also an increase in their performance. Experimental results on various benchmarks indicate that our proposed compressed model enhances performance with an increase in PSNR, SSIM, and image quality respectively for x4 super-resolution tasks.