• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권12호
• /
• pp.509-516
• /
• 2022

3차원 공간에서 물체들의 정확한 자세 예측은 실내외 환경에서 장면 이해, 로봇의 물체 조작, 자율 주행, 증강 현실 등과 같은 많은 응용 분야들에서 폭넓게 활용되는 중요한 시각 인식 기술이다. 물체들의 자세 예측을 위한 과거 연구들은 대부분 각 인식 대상 물체마다 정확한 3차원 CAD 모델을 요구한다는 한계점이 있었다. 이러한 과거 연구들과는 달리, 본 논문에서는 3차원 CAD 모델이 없어도 RGB 컬러 영상들만 이용해서 미지 물체들의 자세를 예측해낼 수 있는 새로운 신경망 모델을 제안한다. 제안 모델은 적응형 깊이 추정기인 AdaBins를 이용하여 스스로 미지 물체 자세 예측에 필요한 각 물체의 깊이 지도를 효과적으로 추정해낼 수 있다. 벤치마크 데이터 집합들을 이용한 다양한 실험들을 통해, 본 논문에서 제안한 모델의 유용성과 성능을 평가한다.

• Journal of Information Technology Applications and Management
• /
• 제29권6호
• /
• pp.135-144
• /
• 2022

In this study, we transformed 4680 type lithium-ion batteries to 3-dimensional CAD models and present a methodology to detect defects using Radon inverse transformation. Transparency was applied to the model to make it look like a CT image when viewed from the front. One normal and three defect models were created and analyzed. The models were saved as image files while rotating at a certain angle. Then, we used the Radon inverse transformation to reconstruct the original 3D geometry from the image files. Finally, we successfully found defects in the defect models for three cases.

• 한국생산제조학회지
• /
• 제24권2호
• /
• pp.166-171
• /
• 2015

In this study, an automation tool was developed for rapid evaluation of machine tool spindle designs with automated three-dimensional finite element analysis (3D FEA) using solid elements. The tool performs FEA with the minimum data of point coordinates to define the section of the spindle shaft and bearing positions. Using object-oriented programming techniques, the tool was implemented in the programming environment of a CAD system to make use of its objects. Its modules were constructed with the objects to generate the geometric model and then to convert it into the FE model of 3D solid elements at the workbenches of the CAD system using the point data. Graphic user interfaces were developed to allow users to interact with the tool. This tool is helpful for identification of a near optimal design of the spindle based on, for example, stiffness with multiple design changes and then FEAs.

• 대한치과기공학회지
• /
• 제41권2호
• /
• pp.81-86
• /
• 2019

Purpose: The purpose of the present study was to compare the internal fit of two different temporary restorations fabricated by dental CAD/CAM system and to evaluate clinical effectiveness. Methods: Composite resin tooth of the maxillary first molar was prepared as occlusal reduction(2.0mm), axial reduction(1mm offset), vertical angle(6 degree) and chamfer margin for a temporary crown and duplicated epoxy die was fabricated. The epoxy dies were used to fabricate provisional restorations by CAD/CAM milling technique or 3D-printing technique. The inner data from all crowns were superimposed on the master die file in the 'best-fit alignment' method using 3D analysis software. Statistical analysis was performed using a Wilcoxon's rank sum test for differences between groups. Results: It showed that the internal RMS(Root Mean Square) values of the additive group were significantly larger than those of other group. No significant differences in internal discrepancies were observed in the temporary crowns among the 2 groups with different manufacturing method. Conclusion: All the groups had the internal fit within the clinical acceptable range (< $50{\mu}m$). The continuous research in the future to be applied clinically for the adaptation of additive manufacturing technique are needed.

• International Journal of CAD/CAM
• /
• 제3권1_2호
• /
• pp.97-109
• /
• 2003

A large scale polygon models are often used to approximately represent 3D CAD models in Digital Engineering environment such as DMU (Digital Mockups) and network based collaborative design. However, they are not suitable for distribution on the network and for interactive rendering. We introduce a new coding system based on subdivision schemes called S-CODE system. In this system, it is possible to highly compress the model with sufficient accuracy and to view the model efficiently in a level of detail (LOD) fashion. The method is based on subdivision surface fitting by which a subdivision surface and curves which approximate a face of a CAD model are generated. We also apply a subdivision method to analytic surfaces such as conical and cylindrical surfaces. A prototype system is developed and used for evaluation with reasonably complicated data. The results show that the method is useful as a CAD data coding system.

• 한국산학기술학회논문지
• /
• 제20권3호
• /
• pp.16-22
• /
• 2019

로봇을 적용한 자동화 생산 라인에서 로봇 셋업 시 시뮬레이션을 통한 Off-Line Programming(OLP)과 로봇 캘리브레이션은 작업 시간을 단축하고 양산 전부터 생산 품질을 관리하기 위해 필수적이다. 본 연구에서는 상용 3D 스캐너를 사용하여 생산 라인의 CAD 데이터와 현장의 3차원 측정 스캔 데이터를 정합하는 로봇 캘리브레이션 방법을 개발하였다. 제안한 방법은 Iterative Closest Point(ICP) 알고리즘을 통해 두 개의 3차원 점군 데이터를 정합하여 로봇을 교정한다. 정합은 3단계로 수행한다. 먼저 CAD 데이터로부터 3개의 평면으로 연결된 꼭짓점을 특징점으로 추출한다. 추출한 특징점 주변에 위치한 스캔 점군데이터로부터 평면을 재구성하여 대응하는 특징점을 생성한다. 마지막으로 ICP 알고리즘을 통해 추출한 특징점들 간의 거리를 최소화하여 위치 변환 행렬을 계산한다. 자동차 차체 조립라인의 스팟용접 로봇 설치에 제안한 방법을 적용한 결과 스팟용접에서 일반적으로 요구하는 정밀도 1.5mm 수준으로 로봇의 위치 및 자세를 캘리브레이션 할 수 있었으며, 기존에 레이저 트래커를 사용하면 로봇 한 대당 5시간 이상 소요되던 셋업 시간은 40분 이내로 단축할 수 있었다. 개발한 시스템을 사용하면 차체 스팟 용접에 필요한 정밀도를 유지하면서 자동차 차체 조립 라인의 OLP 작업시간을 단축하여, 로봇 정밀 티칭 시간을 단축하여, 생산제품의 품질 향상 및 불량률을 최소화할 수 있다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.848-853
• /
• 2005

3D geometric modeling of an object of interest has been intensively investigated in many fields including CAD/CAM and computer graphics. Traditionally, CAD and geometric modeling tools are widely used to create geometric models that have nearly the same shape of 3D real objects or satisfy designers intent. Recently, with the help of the reverse engineering (RE) technology, we can easily acquire 3D point data from the objects and create 3D geometric models that perfectly fit the scanned data more easily and fast. In this paper, we present 3D geometric model generation based on a stereo vision system (SVS) using random pattern projection. A triangular mesh is considered as the resulting geometric model. In order to obtain reasonable results with the SVS-based geometric model generation, we deal with many steps including camera calibration, stereo matching, scanning from multiple views, noise handling, registration, and triangular mesh generation. To acquire reliable stere matching, we project random patterns onto the object. With experiments using various random patterns, we propose several tips helpful for the quality of the results. Some examples are given to show their usefulness.

• 한국의류산업학회지
• /
• 제10권5호
• /
• pp.652-659
• /
• 2008

This study was designed to testify the possibility and devise the method to manipulate the 3D body scan data to produce rounded-belt pattern adaptable to hip-type variation of women in their 20's. The results of this research were as follows : Firstly, based on drop-value distribution of hip and waist girth, 151 subjects were classified into three hip-types; Type 1 (15.23%) was 'cylinder type', showing lowest drop-value, Type 2 (69.54%) was 'average type' and Type3 (15.23%) was 'hourglass type' showing highest drop-value. Secondly, using CAD program, design lines for round shape belt were set on the surface of 3D scan data of representative subject of each type. And divided 3D surfaces were flattened onto the plane by the internal tools of CAD program. The measure, 'lifting value of round belt pattern', implying the level of curve ratio of pattern was higher in back than front. This result might be linked to the fact that the hip part is more protruded than the abdomen part. And the measures also showed highest values in Type 3(hourglass type) and lowest in Type 1(cylinder type), meaning that the pattern of Type 3 showed more rounded shape than that of Type 1. This finding implied that round belt for body type having high drop-value should be shaped more curved. Thirdly, difference ratios of outline length and area between 3D curves(body surface) and 2D plane(pattern) were 4.5% and 1.3%, respectively. This result demonstrated and solidified the feasibility of designing digital garment pattern from 3D body scan data.

• 한국정밀공학회지
• /
• 제13권3호
• /
• pp.158-164
• /
• 1996

In this paper, the CNC cutting planning module for product with three dimensional solid shape is realized to develop a smart CAD/CAM system which performs systematically from the shape design of procuct by the B-Rep solid modeler to the CNC cutting of product by a machining center. The three dimensional solid shape of product can be easily designed and constructed by the Euler operators and Boolean operators of the solid modeler. And the various functions such as the automatic generation of tool path for the rough and finish cutting processes, the automatic elimination of overcut, the automatic generation of CNC code for the machining center and do on, are established. Especially, the overcut-free tool paths are obtained by splitting the CL solid which is composed of the offset surfaces of the solid shape of product.

• 대한치과보철학회지
• /
• 제60권2호
• /
• pp.222-230
• /
• 2022

디지털 기술은 점차 그 영역을 넓혀 치의학의 여러 분야에 큰 영향을 미치고 있다. 최근 디지털 치의학에서는 다양한 삼차원적(3D) 이미지 데이터를 하나로 중첩시켜 진단 및 보철물 제작에 활용하는 것의 중요성이 대두되고 있다. 안면 스캔, 구내 스캔, 하악 운동 기록(mandibular movement recording) 등의 데이터를 통합하면 가상 환자 모델을 구성할 수 있다. 가상 환자(Virtual patient)란 구내 및 구외 연조직, 잔존 치열, 동적 교합 등 디지털 3D 진단 데이터를 통합하여 형성되며 이를 통해 보철 치료의 결과 등을 가상으로 시뮬레이션을 시행할 수 있다. 본 증례에서의 환자는 37세 여성 및 55세 여성 환자로 각각 기존 보철물의 외형이 틀어진 것 같다는 주소와 근관치료 후 전치부 보철물의 재제작을 주소로 내원하였다. 각 환자에서 3D 안면 스캔을 채득하였으며, ARCUS Digma 2 (KaVo Dental GmbH, Biberach an der Riss, Germany)를 통해 환자의 하악 운동을 기록하였다. 수집한 데이터를 computer-aided design (CAD) 소프트웨어(Exocad dental CAD; exocad GmbH, Darmstadt, Germany) 상에서 하나로 통합하여 가상 교합기에 옮겨 디지털 가상 환자를 형성하였다. 이를 통해 임시 고정성 보철물을 디자인하고 수복하여 평가하였으며, 최종수복물로 옮겨 심미적, 기능적으로 만족할 만한 결과를 보였기에 이를 보고하고자 한다.