• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.507-510
• /
• 2003

In this paper, optical sensor system using PSD(Position Sensitive Detection) is proposed to obtain the three dimensional position of moving markers attached to human body. To find the coordinates of an moving marrer with stereo vision system, two different sight rays of an moving marker are required. Usually, those are acquired with two optical sensors synchronized at the same time. PSD sensor is used to measure the position of an incidence light in real-time. To get the three-dimension position of light source on moving markers, a conventional camera calibration method are used. In this research, we realized a low cost motion capture system. The proposed system shows high three-dimension measurement accuracy and fast sampling frequency.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.60-63
• /
• 2020

With the advent of deep learning, a lot of attempts have been made in computer vision to substitute deep learning models for conventional algorithms. Among them, image classification, object detection, and image restoration have received a lot of attention from researchers. However, most of the contributions were refined in one of the fields only. We propose a new paradigm of model structure. End-to-end model which we will introduce classifies noise of an image and restores accordingly. Through this, the model enhances universality and efficiency. Our proposed model is an 'One-For-All' model which classifies weather condition in an image and returns clean image accordingly. By separating weather conditions, restoration model became more compact as well as effective in reducing raindrops, snowflakes, or haze in an image which degrade the quality of the image.

• 한국환경복원기술학회지
• /
• 제15권1호
• /
• pp.107-117
• /
• 2012

We estimated the potential area roof greening in Gyeonggi-do that will mitigate the heat island effect. The estimation was based on building age, roof shape, and building use which were recorded in the building register from "Sewoomteo, the Building Administration System in the Ministry of Land, Transport and Maritime Affairs. The estimated potential roof greening area in Gyeonggi-do was approximately $102.5km^2$ assuming that the buildings for residence, public, education(school), office, shopping mall are appropriate for roof greening. The area occupied by apartment buildings over six-story was 76.3% of the potential roof greening area 10.2% for individual houses, 5.9% for under five-story apartment buildings, and 3.7% for school buildings. The result indicated that it is residential buildings that we need to pay attention for roof greening, especially high-rise buildings over six-story. Greening of the whole estimated area, $102.5km^2$, in Gyeonggi-do will result in the increase of green space per capita by $8.74m^2$. This is 1.65 times greater than the area of current urban parks, and 1.97 times greater than the total area of neighborhood parks, children's parks, and pocket parks. Greening of the estimated roof area will increase green coverage of urban area by twice, adding to current green coverage of the urban areas, 11.3%, in 10 major cities. In particular, the effect of roof greening would be remarkable in inceasing the green space of Anyang City, Gwangmyeong City, and Guri City where neighborhood park area falls short.

• 대한장애인치과학회지
• /
• 제10권2호
• /
• pp.84-88
• /
• 2014

1. 순측접근법은 치수치료를 순측으로 시행한 후 변색된 순측의 치질을 확대하여 삭제하고 레진으로 순면전체를 수복함으로써 치수치료와 동시에 심미성을 회복할 수 있다. 2. 순측으로 치수치료를 시행하므로 시야가 확보에 유리하고 기구조작이 용이해 행동조절이 잘 되지 않는 어린이에게 추천된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권11호
• /
• pp.953-960
• /
• 2007

TFT-LCD(Thin Flat Transistor Liquid Crystal Display) 패널의 불량(Mura)을 정확히 검출하기 위해서는 패널 영상에 포함된 왜곡을 반드시 보정해야 한다. 일반적인 컴퓨터 비젼 시스템의 촬상영상에 대한 왜곡 보정 알고리즘은 이미 알려져 있지만, 패널 영상에만 독특하게 나타나는 비네팅(Vignetting) 효과는 패널 고유의 특성으로 인한 배경 불균일성(Background Non-uniformity)과 결합되어 기존의 알고리즘을 바로 적용하기 어려운 문제점이 있다. 영상 복원 결과의 정확도를 높이기 위해서는 비네팅 효과를 영상 배경과 분리하여 적절히 보정해주어야만 한다. 따라서, 본 논문에서는 주성분분석(Principle Component Anlaysis)을 통해 비네팅 효과를 분석하고 이를 보정하는 새로운 알고리즘을 제안한다. 불량이 포함된 175개의 영상을 대상으로 복원 실험을 수행한 결과, 왜곡 영상에 포함된 불량들의 평균 밝기 오차는 37% 에서 11% 로 내려갔으며 불량에 대한 판정 실패율도 14.8%에서 2.2%로 떨어졌음을 확인하였다.

• 한국환경복원기술학회지
• /
• 제13권5호
• /
• pp.90-105
• /
• 2010

Because of various stresses with rapid change of social structure, the number of the disabled increase steadily. So, the interest of touch garden which the disabled interact with nature and communicate with the non-disabled is more in demand. This study carried out a survey for landuse, facilities, therapeutic garden in creating touch gardens targeting the disabled using them. The results are as follows: At first, the appropriate natural facilities can lead return visit of the disabled. The second, general facilities for information and barrier-free are insufficient. The third, the disabled demand more places for sense of touch and vision, and, also they demand more places for feeling various living things and sense of the season. And the last, the disabled have no experience in therapeutic gardens, but they have consensus for creating special places for the disabled. This study carried out a survey for specially designated user such as the disabled, but through it, it is expected to establish developed design guidelines for creating touch gardens and therapeutic gardens.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.740-753
• /
• 2023

Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

• 한국IT서비스학회지
• /
• 제22권5호
• /
• pp.87-98
• /
• 2023

Traditionally, tooth restoration has been carried out by replicating teeth using plaster-based materials. However, recent technological advances have simplified the production process through the introduction of computer-aided design(CAD) systems. Nevertheless, dental restoration varies among individuals, and the skill level of dental technicians significantly influences the accuracy of the manufacturing process. To address this challenge, this paper proposes an approach to designing personalized tooth restorations using Generative Adversarial Network(GAN), a widely adopted technique in computer vision. The primary objective of this model is to create customized dental prosthesis for each patient by utilizing 3D data of the specific teeth to be treated and their corresponding opposite tooth. To achieve this, the 3D dental data is converted into a depth map format and used as input data for the GAN model. The proposed model leverages the network architecture of Pixel2Style2Pixel, which has demonstrated superior performance compared to existing models for image conversion and dental prosthesis generation. Furthermore, this approach holds promising potential for future advancements in dental and implant production.

• 한국환경과학회:학술대회논문집
• /
• 한국환경과학회 2002년도 The 10th Anniversary of KENSS International Workshop
• /
• pp.29-44
• /
• 2002

Wetlands provide vital habitats for fish and wildlife while offering numerous other benefits. As in some other countries, however, Taiwan has witnessed the loss of a significant portion of its coastal wetlands due to large-scale reclamation projects along the coast. Most of the wetlands that still remain are seriously being threatened by both human activities and natural changes, such as drainage for agricultural production, filling for industrial development, discharge of wastes and drought. The administrative performance of the existing authorities and legislation in Taiwan has mostly been ineffective in protecting these precious, sensitive areas. This paper introduces the distribution of wetlands in Taiwan and highlights their invaluable functions and potential economic value. It also discussed the recent activities, both initiated by the government and the NGOs, to protect wetlands in Taiwan. Based on the above discussion, the paper identifies the wide-range of current problems related to their management and proposes the vision should have to save wetlands for the future. It argues that establishing clear policies and effective institutional mechanisms on wetland protection and conservation, classifying the wetlands for better management, and fully promoting public awareness and consciousness of the importance of the wetlands will not only be beneficial but will also address the urgent need to safeguard the wetlands in Taiwan. Additionally, the paper recognizes that international cooperation and collaboration on wetland restoration is essential and most challenging.

• 한국산학기술학회논문지
• /
• 제15권12호
• /
• pp.7324-7330
• /
• 2014

미약한 광원 및 조명이 존재하는 환경에서 획득된 저조도 영상에는 많은 색 왜곡이 발생한다. 이러한 색 왜곡은 해당 비전 시스템의 성능 저하를 발생시킬 수 있는 원인이 된다. 따라서 저조도 영상의 원래 색을 찾는 과정은 비전 시스템의 성능 향상을 위한 중요한 과정이다. 이를 위해 본 논문에서는 저조도 영상을 대상으로 한 이색도 반사 모델 기반의 색 복원 기법을 제안한다. 제안한 기법은 이색도 반사 모델을 기반으로 저조도 영상을 확산 반사와 정반사의 영향을 받는 영역으로 구분한다. 이후 각 영역에 미치는 조명 효과를 제거하기 위하여 grey world 기법과 MSRCR 기법을 적용한다. 마지막으로, 두 기법을 적용하여 생성된 결과 영상에 대해 위치별 가중치를 이용하여 두 영상을 조합하여 최종 결과 영상을 생성한다. 본 논문에서는 성능 평가를 위하여 저조도 합성 영상을 사용하였고, 유클리드 거리 및 각 오차를 성능 평가 요소로 활용하였다. 또한 기존에 연구되었던 다양한 기법과의 성능 비교를 수행하여 성능 평가의 객관성을 확보하였다. 다양한 영상 셋을 이용한 실험에서 제안한 기법은 기존의 기법들에 비해 두 성능 평가요소 관점에서 GTD 영상에 가까운 색 복원이 가능함을 보였다.