• 비파괴검사학회지
• /
• 제22권1호
• /
• pp.9-13
• /
• 2002

수중에서 사용후 핵연료 제원측정 시험의 효율성을 높이고 측정오차를 줄이기 위하여 수중 영상측정방법을 개발하였다. 이 시스템의 모의 핵연료봉 직경 및 길이 측정치는 실제값 기준으로 할 때, 각각 $-0.24{\pm}0.03mm,\;0.34{\pm}0.06mm$이고 측정 최대오차는 각각 -0.3mm 및 0.4mm이내였다. 실제 사용후핵연료에 대한 수중 제원측정결과 고리원자력 2호기에서 2주기 동안 연소한 핵연료 집합체 J44의 핵연료봉 직경은 설계치 기준으로 할 때 핵연료봉 상 하단부 직경은 2.0%, 중앙부의 직경은 3.0% 정도 감소하였으나 핵연료봉의 길이는 0.4% 정도 신장하였다. 고리원자력 1호기에서 3주기 동안 연소한 핵연료 집합체 F02의 핵연료봉의 직경 및 길이는 핵연료 집합체 J44의 결과와 비슷한 경향을 나타내었다.

• 드라이브 ㆍ 컨트롤
• /
• 제20권2호
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• Clinics in Shoulder and Elbow
• /
• 제23권2호
• /
• pp.71-79
• /
• 2020

Background: The glenoid version of the shoulder joint correlates with the stability of the glenohumeral joint and the clinical results of total shoulder arthroplasty. We sought to analyze and compare the glenoid version measured by traditional axial two-dimensional (2D) computed tomography (CT) and three-dimensional (3D) reconstructed images at different levels. Methods: A total of 30 cases, including 15 male and 15 female patients, who underwent 3D shoulder CT imaging was randomly selected and matched by sex consecutively at one hospital. The angular difference between the scapular body axis and 2D CT slice axis was measured. The glenoid version was assessed at three levels (midpoint, upper one-third, and center of the lower circle of the glenoid) using Friedman's method in the axial plane with 2D CT images and at the same level of three different transverse planes using a 3D reconstructed image. Results: The mean difference between the scapular body axis on the 3D reconstructed image and the 2D CT slice axis was 38.4°. At the level of the midpoint of the glenoid, the measurements were 1.7°±4.9° on the 2D CT images and -1.8°±4.1° in the 3D reconstructed image. At the level of the center of the lower circle, the measurements were 2.7°±5.2° on the 2D CT images and -0.5°±4.8° in the 3D reconstructed image. A statistically significant difference was found between the 2D CT and 3D reconstructed images at all three levels. Conclusions: The glenoid version is measured differently between axial 2D CT and 3D reconstructed images at three levels. Use of 3D reconstructed imaging can provide a more accurate glenoid version profile relative to 2D CT. The glenoid version is measured differently at different levels.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.772-779
• /
• 2006

The new model proposed in this paper is the hidden Markov mesh model or the 2D HMM with the causality of top-down and left-right direction. With the addition of the causality constraint, two algorithms for the evaluation of a model and the maximum likelihood estimation of model parameters have been developed theoretically which are based on the forward-backward algorithm. It is a more natural extension of the 1D HMM than other 2D models. The proposed method will provide a useful way of modeling highly variable image patterns such as offline cursive characters.

• 한국광학회지
• /
• 제24권3호
• /
• pp.120-124
• /
• 2013

본 논문에서는 임의의 모양, 크기, 및 초점 거리를 가지는 렌즈들의 불규칙한 배열을 통과하여 저장되는 영상으로부터 원본 2차원 객체의 모양을 복원하는 방법을 제시한다. 제안된 방법에서는 먼저 단일 물체점의 위치를 바꾸어가며 불규칙 렌즈 배열을 통한 촬영을 수행하여 각 물체점 위치에 대한 불규칙 렌즈 배열 영상들을 확보한다. 이와 같은 각 물체점별 불규칙 렌즈 배열 영상들을 임의의 모양을 가지는 2차원 물체에 대한 불규칙 렌즈 배열 영상과 비교하여 유사도를 산출함으로써 임의의 모양을 가지는 2차원 물체를 복원한다. 실험 결과를 통하여 원본 물체를 인식할 수 있는 수준으로 물체의 복원이 가능함을 확인하였다. 추후 보다 높은 해상도의 복원과 3차원 물체로의 확장을 위한 추가 연구가 필요함도 확인하였다.

• 한국정보통신학회논문지
• /
• 제16권3호
• /
• pp.591-597
• /
• 2012

신체 주요 장기들에 대한 영상의 중요성이 커져감에 따라 향상된 의료 장비들이 등장하였으며, 획득된 영상에 대한 개선된 화질과 활용성에 기대가 높아지고 있다. 최근 향상된 영상분석 연구를 위해 MATLAB을 이용한 영상 처리의 빈도가 커져가는 것에 기인하여 MATLAB을 이용하여 폐혈관을 분할하였다. 본 논문은 3단계로 폐 영역 분할, 폐 혈관 분할과 3차원 연결성 검사로 수행된다. 분할된 폐 영역에서 문턱치 값을 사용하여 혈관을 분할하고, 2차원 정제 과정인 혈관 두께 분류를 수행한 후 3차원 정제 과정으로 3차원 연결성 검사를 적용하였다. MATLAB을 통한 영상 처리로 의료영상 처리의 다양성 측면과 신뢰성 향상에 기여하였고 흉부 CT 영상을 이용한 관련 연구의 기반이 되리라 판단된다.

• 대한전자공학회논문지
• /
• 제22권1호
• /
• pp.1-6
• /
• 1985

Defocussed된 정지화상은 그 PSF(point spread fufction)이 rectangular 혹은 Gaussian등의 2차함수가 되며 이것과 입력화상과의 convolution으로 모델링 할 수 있음이. 알려져 있다. 그런데 이를 TV카메라의 주사선을 이용한 analog 방식으로 개선코자 할 경우에는 매 수평주사선에 관한한 1차원적인 처리가 가능하며 이 defocussed된 화상은 원래의 화상과 일정한 폭을 가진 펄스와의 수평방향으로 convolution된 결과로 해석 할 수 있음을 밝혔다. 또한 TV 카메라의 analog compound high pass filter를 사용한 복구 실험으로써 현저히 개선된 사진을 얻을 수 있있다.

• Journal of the Optical Society of Korea
• /
• 제16권2호
• /
• pp.115-120
• /
• 2012

In this paper, we present a method to automatically quantify the three-dimensional (3D) volume of red blood cells (RBCs) using off-axis digital holographic microscopy. The RBCs digital holograms are recorded via a CCD camera using an off-axis interferometry setup. The RBCs' phase image is reconstructed from the recorded off-axis digital hologram by a computational reconstruction algorithm. The watershed segmentation algorithm is applied to the reconstructed phase image to remove background parts and obtain clear targets in the phase image with many single RBCs. After segmenting the reconstructed RBCs' phase image, all single RBCs are extracted, and the 3D volume of each single RBC is then measured with the surface area and the phase values of the corresponding RBC. In order to demonstrate the feasibility of the proposed method to automatically calculate the 3D volume of RBC, two typical shapes of RBCs, i.e., stomatocyte/discocyte, are tested via experiments. Statistical distributions of 3D volume for each class of RBC are generated by using our algorithm. Statistical hypothesis testing is conducted to investigate the difference between the statistical distributions for the two typical shapes of RBCs. Our experimental results illustrate that our study opens the possibility of automated quantitative analysis of 3D volume in various types of RBCs.

• 한국지능시스템학회논문지
• /
• 제22권6호
• /
• pp.748-753
• /
• 2012

본 논문에서는 최적 pRBFNNs 패턴분류기 기반 3차원 스캐너를 이용한 얼굴인식 알고리즘을 설계한다. 일반적으로 2차원 영상을 이용한 얼굴인식 시스템은 사진의 명암도를 이용하여 얼굴의 특징을 추출하게 된다. 그렇기 때문에 빛이나 조명, 또는 얼굴 포즈와 같은 환경 변화들은 시스템의 성능을 저하시킨다. 따라서 본 논문에서 제안된 얼굴인식 알고리즘은 2차원 얼굴인식 시스템의 한계를 극복하기 위하여 3차원 스캐너를 사용하여 설계한다. 먼저 3차원 스캐너를 이용하여 얼굴 형상을 스캔하고 스캔된 얼굴 형상은 포즈 보상 과정을 통하여 정면으로 변환된다. 그 후에 Point Signature 기법을 사용하여 얼굴의 깊이 정보를 추출하고 마지막으로 고차원 패턴인식 문제에 대한 해결을 위하여 최적화된 pRBFNNs (Polynomial-based Radial Basis Function Neural Networks) 모델을 사용하여 인식성능을 확인한다.

• 국토계획
• /
• 제54권2호
• /
• pp.93-108
• /
• 2019

This study examines the relationship between three-dimensional urban built environment and urban surface temperature using LANDSAT 8 satellite image data in Seoul city. The image was divided into 600m×600m grid units as an unit of analysis. Due to the high level of spatial dependency in surface temperature, this study uses spatial statistics to take into account spatial auto-correlation. The spatial error model shows the best goodness of fit. The analysis results show that the three-dimensional built environment and transport environment as well as natural environment have statistically significant associations with surface temperature. First, natural environment variables such as green space, streams and river, and average elevation show statistically significant negative association with surface temperature. Second, the building area shows a positive association with surface temperature. In addition, while sky view factor (SVF) has a positive association with surface temperature, surface roughness (SR) shows a negative association with it. Third, transportation related variables such as road density, railway density, and traffic volume show positive associations with surface temperature. Moreover, this study finds that SVF and SR have different effects on surface temperature in regard to the levels of total floor areas in built environment. The results indicate that interactions between floor area ratio (FAR) and three-dimensional built environmental variables such as SVF and SR should be considered to reduce urban surface temperature.