• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1061-1066
• /
• 2013

In the steel industry, the detection of tiny defects including its 3D characteristics on steel surfaces is very important from the point of view of quality control. A multi-spectral photometric stereo method is an attractive scheme because the shape of the defect can be obtained based on the images which are acquired at the same time by using a multi-channel camera. Moreover, the calculation time required for this scheme can be greatly reduced for real-time application with the aid of a GPU (Graphic Processing Unit). Although a more reliable shape reconstruction of defects can be possible when the numbers of available images are increased, it is not an easy task to construct a camera system which has more than 3 channels in the visible light range. In this paper, a new 6-channel camera system, which can distinguish the vertical/horizontal linearly polarized lights of RGB light sources, was developed by adopting two 3-CCD cameras and two polarized lenses based on the fact that the polarized light is preserved on the steel surface. The photometric stereo scheme with 6 images was accelerated by using a GPU, and the performance of the proposed system was validated through experiments.

• 전자공학회논문지
• /
• 제49권11호
• /
• pp.47-55
• /
• 2012

본 논문에서는 객체의 모션 블러(motion blur)를 포함하고 있는 다중시점(multi-view) 영상을 이용하여 객체의 3차원 형상 복원시 영상을 효과적으로 디블러링(deblurring)하여 3차원 형상 복원의 정확도를 높이는 기법을 제안한다. 다중시점 영상의 디블러링 수행시 다중시점 영상 간의 기하학적 상관관계를 고려하여 보다 정확히 PSF (point spread function)를 구함으로써 결과적으로 보다 정확한 3차원 형상 복원을 수행할 있다. 제안하는 기법은 각각의 입력 영상에서 초기 2D PSF를 독립적으로 구한 후, 3차원 PSF의 후보를 각 입력 영상의 카메라 행렬에 의해 투영했을 때 이들에 전역적으로 가장 잘 부합하는 3D PSF를 탐색한다. 3D PSF는 방향과 밀도 성분으로 구성되며 이는 결국 3차원 공간에서의 물체의 움직임 궤적과 동일하다. 추정된 3D PSF는 각 영상으로 다시 투영되어 각 영상의 2D PSF로 추정되고, 이에 의해 각 영상의 디블러링을 수행한다. 본 논문에서 제안하는 기법을 이용하여 다중시점 영상 디블러링과 3차원 형상 복원을 수행한 결과, 단일 영상만을 이용하여 복원할 경우에 비하여 디블러링과 3차원 형상 복원 모두 현저히 개선된 결과를 확인할 수 있다.

• Journal of International Society for Simulation Surgery
• /
• 제2권1호
• /
• pp.13-16
• /
• 2015

Purpose We conducted a study on the reconstruction of the head's shape in 3D using the ToF depth sensor. A time-of-flight camera (ToF camera) is a range imaging camera system that resolves distance based on the known speed of light, measuring the time-of-flight of a light signal between the camera and the subject for each point of the image. The above method is the safest way of measuring the head shape of plagiocephaly patients in 3D. The texture, appearance and size of the head were reconstructed from the measured data and we used the SDF method for a precise reconstruction. Materials and Methods To generate a precise model, mesh was generated by using Marching cube and SDF. Results The ground truth was determined by measuring 10 people of experiment participants for 3 times repetitively and the created 3D model of the same part from this experiment was measured as well. Measurement of actual head circumference and the reconstructed model were made according to the layer 3 standard and measurement errors were also calculated. As a result, we were able to gain exact results with an average error of 0.9 cm, standard deviation of 0.9, min: 0.2 and max: 1.4. Conclusion The suggested method was able to complete the 3D model by minimizing errors. This model is very effective in terms of quantitative and objective evaluation. However, measurement range somewhat lacks 3D information for the manufacture of protective helmets, as measurements were made according to the layer 3 standard. As a result, measurement range will need to be widened to facilitate production of more precise and perfectively protective helmets by conducting scans on all head circumferences in the future.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.77-77
• /
• 2000

The shape of small or curved object is usually reconstructed using a single camera by moving its lens position to find a sequence of the focused images. Most conventional methods have used a window with fixed shape to test the focus measure, which resulted in a deterioration of accuracy. To solve this problem, this paper proposes a new approach of using a shape adaptive window. It estimates the shape of the object at every step and applies the same shape of window to calculate the focus measure. Focus measure is based on the variance of the pixels inside the window. This paper includes the experimental results.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.408-415
• /
• 2022

본 논문에서는 효율적인 feature map 추출 네트워크를 이용한 2D 이미지에서의 3D 포인트 클라우드 재구축 기법을 제안한다. 본 논문에서 제안한 기법의 독창성은 다음과 같다. 첫 번째로, 메모리 측면에서 기존 기법보다 약 27% 더 효율적인 새로운 feature map 추출 네트워크를 사용한다. 제안하는 네트워크는 딥러닝 네트워크의 중간까지 크기 축소를 수행하지 않아, 3D 포인트 클라우드 재구축에 필요한 중요한 정보가 유실되지 않았다. 축소되지 않은 이미지 크기로 인해 발생하는 메모리 증가 문제는 채널의 개수를 줄이고 딥러닝 네트워크의 깊이를 얕게 효율적으로 구성하여 해결하였다. 두 번째로, 2D 이미지의 고해상도 feature를 보존하여 정확도를 기존 기법보다 향상시킬 수 있도록 하였다. 축소되지 않은 이미지로부터 추출한 feature map은 기존의 방법보다 자세한 정보가 담겨있어 3D 포인트 클라우드의 재구축 정확도를 향상시킬 수 있다. 세 번째로, 촬영 정보를 필요로 하지 않는 divergence loss를 사용한다. 2D 이미지뿐만 아니라 촬영 각도가 학습에 필요하다는 사항은 그만큼 데이터셋이 자세한 정보를 담고 있어야 하며 데이터셋의 구축을 어렵게 만드는 단점이다. 본 논문에서는 추가적인 촬영 정보 없이 무작위성을 통해 정보의 다양성을 늘려 3D 포인트 클라우드의 재구축 정확도가 높아질 수 있도록 하였다. 제안하는 기법의 성능을 객관적으로 평가하기 위해 ShapeNet 데이터셋을 이용하여 비교 논문들과 같은 방법으로 실험한 결과, 본 논문에서 제안하는 기법의 CD 값이 5.87, EMD 값이 5.81 FLOPs 값이 2.9G로 산출되었다. 한편, CD, EMD 수치가 낮을수록, 재구축한 3D 포인트 클라우드가 원본에 근접하는 정확도가 향상된 결과를 나타낸다. 또한, FLOPs 수치가 낮을수록 딥러닝 네트워크에 필요한 메모리가 적게 소요되는 결과를 나타낸다. 따라서, 제안하는 기법의 CD, EMD, FLOPs 성능평가 결과가 다른 논문의 기법들보다 메모리 측면에서 약 27%, 정확도 측면에서 약 6.3% 향상된 결과를 나타내어 객관적인 성능이 입증되었다.

• Journal of Computational Design and Engineering
• /
• 제3권4호
• /
• pp.322-329
• /
• 2016

The advent of high-performance terrestrial laser scanners has made it possible to capture dense point-clouds of engineering facilities. 3D shape acquisition from engineering facilities is useful for supporting maintenance and repair tasks. In this paper, we discuss methods to reconstruct box shapes and polygonal prisms from large-scale point-clouds. Since many faces may be partly occluded by other objects in engineering plants, we estimate possible box shapes and polygonal prisms and verify their compatibility with measured point-clouds. We evaluate our method using actual point-clouds of engineering plants.

• 지적과 국토정보
• /
• 제51권1호
• /
• pp.111-124
• /
• 2021

최근, 2019년 4월 15일에 있었던 노트르담 대성당 화재로 문화재 복원 및 재현에 대해 2008년 숭례문 화재사건 이후 관심이 다시 한 번 집중되고 있다. 특히, 기존에 활용되던 LiDAR 및 광파기 측량 등을 활용한 문화재 실측을 다양한 3차원 재현 기술을 활용하여 복원 및 재현하려는 연구가 활발히 진행되고 있다. 본 연구는 운주사의 와형석조여래불을 대상으로 최근 4차 산업혁명 시대에서 핵심기술로 자리매김한 UAV(Unmanned Aerial Vehicle)의 무인항공영상와 기존에 사진측량에 활용되던 근접영상(CRP) 및 지상 LiDAR 스캐닝을 활용하여 데이터를 획득하고, 이들을 3가지 융합모델로 SfM기반의 3차원 재현을 실시, 모델의 재현도 및 정확도를 비교·분석하였다. 아울러, 3가지의 모델 중 가장 우수한 융합모델을 활용하여 11세기 초 고려시대의 불교 천문학적 고증이 녹아있는 와형석조여래불을 실세계 좌표기반으로 북극성과의 연관성을 확인한다. 본 연구를 통해 문화재의 단순한 외형적인 3차원 재현뿐 아니라 문화재에 담긴 역사적 고증을 확인함으로써 문화재의 종류 및 형태에 따라 고증까지 함께 재현하는 방안을 모색하였다.

• 한국의류학회지
• /
• 제33권3호
• /
• pp.401-409
• /
• 2009

The shape of crotch area is very important to develop functional clothing as well as other ergonomic goods such as chair or saddle etc. However, it is inevitable that 3D scanned image of crotch would have missing part due to its folded shape including overlapping legs nearby. Therefore, the objectives of this research was to compare reconstruction methods of missing parts at crotch using seven dummies of real men's replicas. Two reconstruction methods adopted were kinds of 'fill- hole' in Rapidform 2004, one was 'smooth' and the other was 'curvature'. Each restored image was compared with the original shape of the dummies. As results, the average distance was 0.66mm between original and 'smooth' treated images and 0.59mm between original and 'curvature' treated, which was not statistically different. Average area of restored crotch region was $8740.04cm^2$ by 'smooth' method and $8405.02cm^2$ by 'curvature' method which is close to the original area of $8413.76cm^2$. Statistical difference was found between images of original and 'smooth' ones$(p=0.04^*)$. However, there was no difference between original and 'curvature' treated images, which indicates that 'curvature' method is more useful to fill the hole compared with 'smooth' method.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1385-1395
• /
• 2019

In this paper, we propose a method to fabricate a patient-specific breast implant using MRI images and 3D scan data. Existing breast implants for breast reconstruction surgery are primarily fabricated products for shaping, and among the limited types of implants, products similar to the patient's breast have been used. In fact, the larger the difference between the shape of the breast and the implant, the more frequent the postoperative side effects and the lower the satisfaction. Previous researches on the fabrication of patient-specific breast implants have used limited information based on only MRI images or on only 3D scan data. In this paper, we propose an algorithm for the fabrication of patient-specific breast implants that combines MRI images with 3D scan data, considering anatomical suitability for external shape, volume, and pectoral muscle. Experimental results show that we can produce precise breast implants using the proposed algorithm.

• 한국CDE학회논문집
• /
• 제15권4호
• /
• pp.297-305
• /
• 2010

Medical image acquisition techniques such as CT and MRI have disadvantages in that the numerous time and efforts are needed. Furthermore, a great amount of radiation exposure is an inherent proberty of the CT imaging technique, a number of side-effects are expected from such method. To improve such conventional methods, a number of novel methods that can obtain 3D medical images from a few X-ray images, such as algebraic reconstruction technique (ART), have been developed. Such methods deform a generic model of the internal body part and fit them into the X-ray images to obtain the 3D model; the initial shape, therefore, affects the entire fitting process in a great deal. From this fact, we propose a novel method that can generate a 3D vertebraic generic model based on the statistical database of CT scans in this study. Moreover, we also discuss a method to generate patient-tailored generic model using the facts obtained from the statistical analysis. To do so, the mesh topologies of CT-scanned 3D vertebra models are modified to be identical to each other, and the database is constructed based on them. Furthermore, from the results of a statistical analysis on the database, the tendency of shape distribution is characterized, and the modeling parameters are extracted. By using these modeling parameters for generating the patient-tailored generic model, the computational speed and accuracy of ART can greatly be improved. Furthermore, although this study only includes an application to the C1 (Atlas) vertebra, the entire framework of our method can be applied to other body parts generally. Therefore, it is expected that the proposed method can benefit the various medical imaging applications.