• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.316-319
• /
• 2013

이안식 일체형 입체카메라는 줌인 시 고정된 컨버전스 포인트로 인해 촬영된 영상 시청할 때 어지러움을 유발하는 시각적 불편이 발생할 수 있다. 본 논문에서는 이안식 일체형 입체카메라에서 줌인 시 발생되는 시각적 불편을 방지하기 위해 제안된 컨버전스 포인트를 조정하는 기법을 실사로 촬영하고 각 기법 및 케이스별로 스테레오 분석을 실시한다. 이를 위해 포커스, 피사체 및 컨버전스 포인트의 위치에 따른 케이스와 각각의 간격 거리, 그리고 4가지 기법을 적용한 영상을 제작하여 스테레오 분석을 실시한다. 이로써 컨버전스 포인트를 조정하여 시각적 불편을 최소화하는 기법을 제안하고 제시한 깁법의 우수성을 입증한다.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.483-486
• /
• 2010

단일 카메라를 통하여 실시간으로 입력되는 객체의 추적은 환경의 제약을 많이 받는다. 입력되는 영상에서의 움직임이 있는 객체는 단일하여야 하며, 동시에 많은 움직임이 발생하면 추적하고자 하는 객체를 구분하기 어려워진다. 본 논문에서는 동일공간을 감시하는 두 대의 카메라가 서로 데이터를 주고 받으며 추적하고자 하는 특정객체를 오류 없이 추적할 수 있는 방법을 제시하였다. 실시간 객체 추적은 입력되는 영상에서 객체의 위치를 가장 빠르게 검색하기 위한 고속탐색 알고리즘이 필요하다. 본 논문은 실시간영상에서 객체의 움직임을 추출하고 추적을 위하여 각각 위치가 다른 두 대의 카메라가 상호 협력하면서 객체 추적에 대한 연산을 현저하게 줄일 수 있었다. 또한 객체의 움직임이 많은 공간에서도 추적하고자 하는 특정객체를 잃어버리지 않고 추적하였다. 실험결과, 제안한 방법은 97% 이상의 높은 객체 추적율을 보였다.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.3
• /
• pp.209-211
• /
• 2005

A tail-on-detector (TOD) view has been used to see the symphysis pubis or sacrococcyx in skeletal scintigraphy, but it is inconvenient to acquire because a patient must sit or lean on a detector. The TOD views are still frequently performed in training hospitals in Korea, although it is becoming almost impossible to sit on a camera in this age of dual-headed cameras. The authors show cases with lateral views obtained in supine position that were acquired for the same reason; they are easier and more useful than the TOD views.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.70.1-70
• /
• 2001

Recently, research of visual control is getting more essential in robotic application, and acquiring 3D informations from the 2D images is becoming more important with development of vision system. For this application, we propose the effective way of controlling stereo vision tracking system for target tracking and calculating distance between target and camera. In this paper we address improved controller using dual-loop visual servo which is more effective compared with using single-loop visual servo for stereo vision tracking system. The speed and the accuracy for realizing a real time tracking are important. However, the vision processing speed is too slow to track object in real time by using only vision feedback data. So we use another feedback data from controller parts which offer state feedback ...

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.448-451
• /
• 2014

이안식 일체형 입체카메라는 줌인 시 고정된 컨버전스 포인트로 인해 촬영된 영상 시청할 때 어지러움을 유발하는 시각적 불편이 발생할 수 있다. 본 논문에서는 이안식 일체형 입체카메라에서 줌인 시 발생되는 시각적 불편을 최소화하기 위해 컨버전스 포인트 조정기법을 제안한다. 그리고 거리와 케이스에 따라 각 기법을 적용한 입체영상을 제작하고 피실험자를 통해 주관평가를 실시한다. 이 결과를 통해 제안된 컨버전스 포인트 이동기법의 비교를 통해 제시된 기법의 우수성을 입증한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.358-362
• /
• 2014

이안식 일체형 입체카메라는 줌인 시 고정된 컨버전스 포인트로 인해 촬영된 영상 시청할 때 어지러움을 유발하는 시각적 불편이 발생할 수 있다. 본 논문에서는 이안식 일체형 입체카메라에서 줌인 시 발생되는 시각적 불편과 거리감의 변동을 방지하기 위해 3DCG환경에서 컨버전스 포인트 이동값에 대한 실험을 한다. 거리별 컨버전스 포인트 이동에 따른 입체영상을 시청하고 평가하는 주관 평가를 실시하여 시각적 불편을 최소화하는 컨버전스 포인트 조정기법을 제안할 수 있는 근거를 마련하고자 한다.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.74.1-74.1
• /
• 2019

We present an ongoing imaging survey of the host galaxies of hard X-ray-selected active galactic nuclei (AGNs) observed with the Hubble Space Telescope (HST). The snapshot images are taken with the Advanced Camera for Surveys through an HST gap-filler program. The sample, selected from the 70-month Swift-BAT X-ray source catalog, represents an unbiased and uniform AGN population, which will enable us to test the AGN unification model and explore the physical connection between host galaxies and central supermassive black holes. We also plan to investigate the AGN triggering mechanism by examining merger signatures and searching for dual nuclei. We present the pipeline for imaging analysis and the current status of the survey.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.4
• /
• pp.6-15
• /
• 2022

In this study, a traffic light recognition algorithm was implemented and validated for low-speed special purpose vehicles in an urban environment. Real-time image data using a camera and YOLO algorithm were applied. Two methods were presented to increase the accuracy of the traffic light recognition algorithm, and it was confirmed that the second method had the higher accuracy according to the traffic light type. In addition, it was confirmed that the optimal YOLO algorithm was YOLO v5m, which has over 98% mAP values and higher efficiency. In the future, it is thought that the traffic light recognition algorithm can be used as a dual system to secure the platform safety in the traffic information error of C-ITS.

• Tribology and Lubricants
• /
• v.33 no.2
• /
• pp.52-58
• /
• 2017

An ultra-high precise ejection process is essential in a dispensing system for fabricating various precision parts such as a semiconductor, LED, and camera module. The size of such parts has been decreasing, which implies that a precise ejecting technique is required. A phosphor-containing liquid is ejected via a dispenser using dual piezoelectric actuators that are used for generating a high-speed dispensing mechanism. The rod and nozzle continuously contact in high speed to eject the liquid. However, the high-strength filler or phosphor in the liquid causes wear on the surfaces of the rod and nozzle during the dispensing process. As a result, the ejection reliability decreases as the wear on the surfaces increases. Therefore, it is necessary to estimate the wear characteristics of the rod and nozzle via an experiment and FE analysis. Reliability rests up to 1,000 cycles are conducted under relatively severe conditions. The flow rate and surfaces roughness of the rod and nozzle are measured in each ejection cycle. The surface images and wear volume are obtained before and after the tests and the ejection reliability is confirmed by measuring the flow rate of the liquid. The experimental results show that the ejection reliability is maintained up to 1,000k cycles; these results are validated by the simulation results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.