• 제목/요약/키워드: Scan Model

검색결과 475건 처리시간 0.023초

터널 막장 3차원 지형모델 상에서의 불연속면 자동 매핑을 위한 딥러닝 기법 적용 방안 (Deep Learning Approach for Automatic Discontinuity Mapping on 3D Model of Tunnel Face)

  • 추엔 팜;신휴성
    • 터널과지하공간
    • /
    • 제33권6호
    • /
    • pp.508-518
    • /
    • 2023
  • 이 논문은 LiDAR 스캔 또는 사진측량 기술에 의해 재구성된 3D 디지털 모델을 기반으로 터널 벽면의 불연속면을 자동으로 매핑하는 새로운 접근 방식을 제안한다. 본 제안에서는 U-Net이라 불리는 딥러닝 시맨틱 영역분할 모델을 사용하며, 터널 막장면의 3D 지형 모델에서 불연속면 영역을 식별해 낸다. 제안된 딥러닝 모델은 투영된 RGB 이미지, 면의 깊이 이미지 및 국부적인 면의 표면 속성 이미지(즉, 법선 벡터 및 곡률 이미지)를 포함한 다양한 정보를 종합 학습하여 기본 3차원 이미지에서 불연속면 영역을 효과적으로 분할한다. 이후 영역분할 결과는 면의 깊이 맵과 투영 행렬을 사용하여 3D 모델로 다시 투영시키고, 3D 공간 내에서 불연속면의 위치 및 범위를 정확하게 표현한다. 영역분할 모델의 성능은 영역 분할된 결과를 해당 지면 실측 값과 비교함으로써 평가하였으며, IoU(intersection-over-union) 값이 약 0.8 정도로 나타나 영역분할 결과의 높은 정확성을 확인하였다. 여전히 학습데이터가 제한적 이었음에도 불구하고, 제안 기법은 3D 모델의 점군 데이터를 불연속면의 유사군으로 그룹화하기 위해 전 막장면의 법선 벡터와 클러스터링과 같은 비지도 학습기반 알고리즘에만 의존하던 기존 접근 방식의 한계의 극복 가능성을 보여주었다.

시스템 초기화(Calibration)에 따른 항공레이저측량의 정확도 평가 (The Evaluation of Accuracy for Airborne Laser Surveying via LiDAR System Calibration)

  • 이대희;위광재;김승용;김갑진;이재원
    • 한국측량학회:학술대회논문집
    • /
    • 한국측량학회 2004년도 춘계학술발표회논문집
    • /
    • pp.15-26
    • /
    • 2004
  • The calibration for systematic error in LiDAR is crucial for the accuracy of airborne laser scanning. The main error is the misalignment of platforms between INS(Inertial Navigation System) and Laser scanner For planimetrical calibration of LiDAR, the building is good feature which has great changes in height and continuous flat area in the top. The planimetry error(pitch, roll) is corrected by adjustment of height which is calculated from comparing ground control points(GCP) of building to laser scanning data. We can know scale correction of laser range by the comparison of LiDAR data and GCP is arranged at the end of scan angle where maximize the height error. The area for scale calibration have to be large flat and have almost same elevation. At 1000m for average flying height, The Accuracy of laser scanning data using LiDAR is within 110cm in height and ${\pm}$50cm in planmetry so we can use laser scanning data for generating 3D terrain surface, expecically digital surface model(DSM) which is difficult to measure by aerial photogrammetry in forest, coast, urban area of high buildings

  • PDF

Application of 3D Simulation Surgery to Orthognathic Aurgery : A Preliminary Case Study

  • Lim, Jung-Hwan;Kim, Hyun-Young;Jung, Young-Soo;Jung, Hwi-Dong
    • Journal of International Society for Simulation Surgery
    • /
    • 제1권1호
    • /
    • pp.23-26
    • /
    • 2014
  • The aim of this report is to evaluate accuracy using3D surgical simulationand digitally printedwafer in orthognathic surgery. 22-year-old female was diagnosed with mandibular prognathism and apertognathia based on 3D diagnosis using CT. Digital dentition images were taken by laser scanning from dental cast, and each STL images were integrated into one virtual skull using simulation software. Digitalized intermediate wafer was manufactured using CAD/CAM software and 3D printer, and used to move maxillary segment in real patient. Constructed virtual skull from 1 month postoperative CT scan was superimposedinto simulated virtual model to reveal accuracy. Almost maxillo-mandibular landmarks were placed in simulated position within 1 mm differences except right coronoid process. Thus 3D diagnosis, surgical simulation, and digitalized wafer could be useful method to orthognathic surgery in terms of accuracy.

3D 스캔을 이용한 콘센트 커버의 역설계 및 금형 개발 (Reverse engineering of concentric plug cover by 3D scanning and development of injection mold)

  • 김동욱;최영락;신상은;김세환;최계광;한성렬
    • Design & Manufacturing
    • /
    • 제9권1호
    • /
    • pp.18-22
    • /
    • 2015
  • Mold making and product manufacturing process was made by a die through a number of stages. Thereby, it takes a long period of time from the manufacture of mold until passed the products to consumers. However, it is not possible to meet the diverse desires purchasing of consumer. We made a 3D CAD Model aligned with product scan data using reverse engineering. Utilizing thereafter flow analysis to derive the optimal mold conditions, by applying the condition, and devised a mold fabrication process that is much shorter than the conventional process for fabricating a mold. In this study, the outlet cover to the product, it describes a process, as a result, it was confirmed that the number of steps can be shortened much more than the conventional process.

  • PDF

Detection of Second-Layer Corrosion in Aging Aircraft

  • Kim, Noh-Yu;Yang, Seun-Yong
    • 비파괴검사학회지
    • /
    • 제29권6호
    • /
    • pp.591-602
    • /
    • 2009
  • The Compton backscatter technique has been applied to lap-joint in aircraft structure in order to determine mass loss due to exfoliative corrosion of the aluminum alloy sheet skin. The mass loss of each layer has been estimated from Compton backscatter A-scan including the aluminum sheet, the corrosion layer, and the sealant. A Compton backscattering imaging system has been also developed to obtain a cross-sectional profile of corroded lap-splices of aging aircraft using a specially designed slit-type camera. The camera is to focus on a small scattering volume inside the material from which the backscattered photons are collected by a collimated scintillator detector for interpretation of material characteristics. The cross section of the layered structure is scanned by moving the scattering volume through the thickness direction of the specimen. The theoretical model of the Compton scattering based on Boltzmann transport theory is presented for quantitative characterization of exfoliative corrosion through deconvolution procedure using a nonlinear least-square error minimization method. It produces practical information such as location and width of planar corrosion in layered structures of aircraft, which generally cannot be detected by conventional NDE techniques such as the ultrasonic method.

성인여성의 하반신 체형분석 및 부츠 컷 청바지의 가상 외관평가 (Analysis on Lower Body Type and 3D Virtual Appearance Evaluation of Boots cut Jeans for Women)

  • 최진;도월희
    • 대한가정학회지
    • /
    • 제46권2호
    • /
    • pp.73-83
    • /
    • 2008
  • The focus of this research was concerned with studying lower body type for Korean adult females. information from the measuring values based on research on the physical standard of the nation(2004) were summarized, in addition a factor of the need for appropriate fit in boots cut jean wear, basic lower body part applying to each item had to be taken into consideration to enhance sizing suitability. The body type are classified into three kinds by means of factor analysis and cluster analysis. Type 1 referred to the fat lower body, having thick rounding waist. compared to other body parts, and long leg according to its proportion. Type 2 represented medium stature but with a large skeleton structure of lower body. Type 3 represented a the long lower body having slender rounding waist. This study was attempted to evaluate the fitness of boots cut jeans pattern for women using 3D Clothes Modeling Software.

성인 남성 머리와 얼굴 부위의 형태분류와 3차원적 분석 (Classification of Head Shape and 3-dimensional analysis for Korean Men)

  • 최영림;김재승;남윤자
    • 한국의류산업학회지
    • /
    • 제12권6호
    • /
    • pp.812-820
    • /
    • 2010
  • The objectives of this study were to classify the head shapes of Korean men and to suggest computer tomography as a new body measurement method. The 23 head measurement items of 760 men, aged more than 18 in Sizekorea 2004 database were used to analyze, measured by using statistical methods. Factor analysis, cluster analysis and duncan test were performed using these data. Through factor analysis, 5 factors were extracted upon factor scores and those factors comprised 70.91% for the total variances. The head and face shapes were categorized as 5 types-triangle, round, oval, long, rectangle. We decided for the type 1(triangle) to standard head shape since this type was the most observed. 21 participants were measured using computed tomography(CT). The measured data of skin and skeleton and the standard head shapes were illustrated.

추적레이다의 표적 탐지 및 추적 기술 동향 (Target Acquisition and Tracking of Tracking Radar)

  • 신한섭;최지환;김대오;김태형
    • 항공우주산업기술동향
    • /
    • 제7권1호
    • /
    • pp.113-118
    • /
    • 2009
  • 추적레이다는 안테나로부터 폭이 매우 좁은 펄스를 표적에 위치시켜 표적에서 돌아오는 신호를 수신하여 표적의 위치 (거리, 각도, 속도 등)를 추적하는 장비이다. 추적레이다가 특정한 표적을 탐지하고 추적하기에 앞서 표적과 주변 환경의 특성을 예측하기 위해 잡음 신호와 표적 신호의 수학적 모델이 필요하다. 본 논문에서는 일반적으로 적용되는 잡음 신호와 표적 신호의 모델에 대한 이론적인 내용을 소개하였고, 이와 더불어 표적의 탐지와 추적을 위한 거리 추적, 각도 추적 및 도플러 주파수 추적에 대한 일반적인 기법들을 기술하였다.

  • PDF

폴리곤 기반 역공학 시스템의 구멍메움에 관한 연구 (A Study on Filling Polygonal Holes in a Polygon-based Reverse Engineering System)

  • 전용태;박광현;노형민;최영
    • 한국정밀공학회지
    • /
    • 제21권4호
    • /
    • pp.140-147
    • /
    • 2004
  • In reverse engineering, the whole surfaces of the three-dimensional product are measured using 3D positional scanners. The raw triangle meshes constructed from a scanned point set are not well fitted for direct use in the downstream engineering or graphic activities. No object can be fully described by a single scan. Although multiple scans are usually taken and aligned to achieve a complete model, a set of scanned points does not entirely wrap the whole object. This is because some surfaces may be inaccessible to the scanner, so some portion of the scanned surface may be missing. This paper discusses the algorithms of a hole-filling that are crucial to refine the triangle meshes. In this paper, the holes are filled with flat triangles first by subdivision operation and then smoothed with neighboring triangles. This process continues until it converges to a certain user-defined iteration number. Examples are given and discussed to validate the system.

DBSCAN 기반의 제조 공정 데이터 불량 위치의 검출 (Detection of the Defected Regions in Manufacturing Process Data using DBSCAN)

  • 최은석;김정훈;아지즈 나스리디노프;이상현;강정태;류관희
    • 한국콘텐츠학회논문지
    • /
    • 제17권7호
    • /
    • pp.182-192
    • /
    • 2017
  • 제조 산업은 국가 경제 성장의 원동력으로 그 중요성이 부각되고 있다. 이에 따라 제조 공정상에서 생성되는 제조 데이터 분석의 중요성 또한 조명 받고 있다. 본 논문에서는 PCB(Printed Circuit Board) 제조 공정에서 발생한 로그 데이터를 분석하여 PCB 상에서 빈번하게 발생하는 고장 영역에 대해서 작업자가 고장 영역을 직접 눈으로 볼 수 있도록 시각화하는 방법을 제안한다. 우선 고장 영역을 파악하기 위해서 PCB 공정 데이터 집합에 K-means, DB-SCAN 클러스터링 알고리즘을 적용하여 군집화 하였고, 두 알고리즘 중 더 정확한 고장 영역을 도출하는지 비교하였다. 또한 MVC(Model-View-Controller) 구조 시스템을 개발하여 실제 PCB 이미지 상에 클러스터링 결과를 출력하는 것으로 실제 고장영역을 눈으로 확인할 수 있도록 시각화하였다.