• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.1090-1093
• /
• 2019

유리섬유강화복합재료로 제작된 배관/덕트 조인트의 오버레이 자동접합을 할 수 있는 로봇이 개발되고 있으며 로봇의 구성 중 하나인 자동적층장치의 작업 시작 위치와 제자리 회전 오차를 극복할 수 있는 기준선에 대한 실시간 영상처리가 필요하다. 기존의 선 검출 알고리즘들은 연산량이 많아 실시간 처리가 어렵거나 전체 영상에서 잡음에 취약한 단점이 있다. 본 논문은 이러한 FRP 배관 및 덕트 내 색상 실선 인식 알고리즘의 효율적인 실시간 영상처리 방법에 관하여 소개하고 배관 내 라인 제어를 위한 선의 실제 거리를 계산하고 출력하는 방법을 나타내었다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.19 no.3
• /
• pp.180-188
• /
• 1999

The dynamic elastic properties of metal matrix composites were investigated by resonant ultrasound spectroscopy(RUS). The composites used in this study consisted of 2124 aluminum alloy reinforced with different concentrations of SiC particles. RUS can determine the nine independent elastic stiffness($C_{ij}$) for the orthorhombic symmetry on a small specimen simultaneously. The elastic constants were determined as a function of the volume fraction. A concept of effective aspect ratio. which combine the aspect ratio and the orientation of reinforcement. was used to calculate the initial moduli from Mori-Tanaka theory for the input of RUS minimization code. Young's moduli can be obtained from the measured stiffnesses. The results show that the elastic stiffness increases with increment of the particle content. The behavior of elastic stiffness indicates that the particle redistribution induced by the extrusion process enlarges the transversely isotropic symmetry as the fraction of reinforced particles increase. This relationship could be used for determination of the volume fractions of reinforcement as a potential tool of nondestructive material characterization.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.97-98
• /
• 2016

뉴미디어 아트에서 사용자의 몰입(sensor immersion)은 작품의 메타포(Metaphor)를 강화하고, 사용자에게 프레즌스(Presence)를 증대시켜 줄 수 있는 중요한 요인이 된다. 미디어 아트 Invisibly Visible은 3D 영상콘텐츠와 함께 응답형 물리환경을 실제 공간에 제공함으로써 사물인터넷(Internet of Things) 세상에서 사람중심의 행위가 예술작품의 자연스러운 참여형태로 이루어지는 뉴 미디어 아트의 새로운 장이 될 수 있으리라 기대한다.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.724-726
• /
• 2022

딥페이크(deepfake)로 인한 디지털 범죄는 날로 교묘해지면서 사회적으로 큰 파장을 불러일으키고 있다. 이때, 딥러닝 기반 모델의 오류를 발생시키는 적대적 공격(adversarial attack)의 등장으로 딥페이크를 탐지하는 모델의 취약성이 증가하고 있고, 이는 매우 치명적인 결과를 초래한다. 본 연구에서는 2 가지 방법을 통해 적대적 공격에도 영향을 받지 않는 강인한(robust) 모델을 구축하는 것을 목표로 한다. 모델 강화 기법인 적대적 학습(adversarial training)과 영상처리 기반 방어 기법인 크기 변환(resizing), JPEG 압축을 통해 적대적 공격에 대한 강인성을 입증한다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.915-936
• /
• 2017

In this study, current status of Korean hazard mitigation guideline for tunnel operation is summarized. It shows that requirement for CCTV installation has been gradually stricted and needs for tunnel incident detection system in conjunction with the CCTV in tunnels have been highly increased. Despite of this, it is noticed that mathematical algorithm based incident detection system, which are commonly applied in current tunnel operation, show very low detectable rates by less than 50%. The putative major reasons seem to be (1) very weak intensity of illumination (2) dust in tunnel (3) low installation height of CCTV to about 3.5 m, etc. Therefore, an attempt in this study is made to develop an deep-learning based tunnel incident detection system, which is relatively insensitive to very poor visibility conditions. Its theoretical background is given and validating investigation are undertaken focused on the moving vehicles and person out of vehicle in tunnel, which are the official major objects to be detected. Two scenarios are set up: (1) training and prediction in the same tunnel (2) training in a tunnel and prediction in the other tunnel. From the both cases, targeted object detection in prediction mode are achieved to detectable rate to higher than 80% in case of similar time period between training and prediction but it shows a bit low detectable rate to 40% when the prediction times are far from the training time without further training taking place. However, it is believed that the AI based system would be enhanced in its predictability automatically as further training are followed with accumulated CCTV BigData without any revision or calibration of the incident detection system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.96-104
• /
• 2011

A halftoning method is used to obtain a binary image visually similar to a continuous gray-level image through the image output devices employing the limited number of gray-levels. As a halftoning method, the error diffusion method is widely used in various applications because of its low computational complexity and good image quality. However, this method weakens the edge in the process of error diffusion to the neighboring pixels. In this case, degradation of the edge quality and damage of the vivid image is expected. To solve these problems, the proposed method determines the adaptive error filter considering the error information of the present pixel and edge distribution of the neighbor pixels. Compared with the conventional methods for enhancing edges, the proposed method involves relatively a few process resources because of its simple procedure, still considerably improving the edges in the halftone image. To evaluate the objective image quality, the performance of the proposed method is compared with that of the conventional method in terms of the edge correlation and the local average accordance.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.465-480
• /
• 2014

In this study, we analyzed the spatio-temporal variations of satellite imagery for the two heavy rainfall cases (21 September, 2010, 9 August, 2011) occurred in the Korean Peninsula. In general, the possibility of strong convection can be increased when the region with plenty of moisture at the lower layer overlapped with the boundary between dark and bright area in the water vapor imagery. And the merging of convective cells caused by the difference in the moving velocities of two cells resulted in the intensification of convective activity and rainfall intensity. The rainfall intensity is more closely linked with the minimum cloud top temperature than the mean cloud top temperature. Also the spatio-temporal variations of rainfall intensity are impacted by the existence of merging processes. The merging can be predicted by the animation of satellite imagery but earlier detection of convective cells is almost impossible by using the infrared and water vapor imagery.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.212-224
• /
• 2009

Proliferation of high performance internet infrastructures finally allows their users download a single copy of regular movie just within in a couple of seconds. Ease of accesses to the software for downloading consequently leads them insensitive to the ethics or legitimacy of their conduct. Thus, strong legal action is enforced for piracy over nationally through strengthen the copyright law. We in this paper conducted a survey to see whether netizens prefer to download just for the matter of their convenience. Whilst the level of awareness is addressed even in a far-fetched manner in the area of music piracy and computer software piracy, the case of movie is much different in that we even fail to find any survey that has been made for movie piracy. The survey has been made by devising questionnaires for netizens and it was posted web WorldSurvey, which is the most prominent online survey site in Korea. To our surprise, 9 out of 10 respondents expressed they actually resort to illegal downloading for the reason of convenience. We realized one more surprise. More than 95% of netizens conspicuously aware of their downloading behaviors are mischievous and illegal without reservation.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.11
• /
• pp.39-46
• /
• 2012

The development of the computer widens the expressive ways for the nature objects and the scenes. The cutting edge computer graphics technologies effectively create any images we can imagine. Although the computer graphics plays an important role in filming and video production, the status of the domestic contents production industry is not favorable for producing and research all at the same time. In digital composition, the match moving stage, which composites the captured real sequence with computer graphics image, goes through many complicating processes. The camera tracking process is the most important issue in this stage. This comprises the estimation of the 3D trajectory and the optical parameter of the real camera. Because the estimating process is based only on the captured sequence, there are many errors which make the process more difficult. In this paper we propose the method for correcting the tracking data. The proposed method can alleviate the unwanted camera shaking and object bouncing effect in the composited scene.

• The KIPS Transactions:PartC
• /
• v.11C no.7 s.96
• /
• pp.971-980
• /
• 2004

This paper describes the design and implementation of the video conferencing system using public key infrastructure which is used for user authentication and encryption. Public key infrastructure reinforces the authentication process for conference participant, and the symmetric key system blocks malicious access to information and protect conference control information. This paper shows the implementation of the trans portation layer secure protocol in conformity with Korea public key authentication algorithm standard and symmetric encryption algorithm (DES, 3DES and AES) for media stream encryption. In this paper, we deal with two ways of protecting information : transportation layer secure protocol secures user authentication process and the conference control information; while public key-based authentication system protects personal information of users when they connect to the network. When distributing the session keys for encryption, Internet Key Exchange is used for P2P communication, and secure protocol is employed for 1 : N multi-user communication in the way of distributing the public key-based en-cryption key.