• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2375-2378
• /
• 2003

In manufacture of printed circuit boards, one important issue is precisely to measure the three-dimensional shape of the solder paste silk-screened prior to direct surface mounting of chips. This paper presents the 3D shape reconstruction of solder paste using the optical triangulation method based on structured light or slit beam and the measurement algorithm for height, volume. area, and coplanarity on component pads from the 3D range image. Futhermore, statistical process control function is incorporated for process capability analysis.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2015.05a
• /
• pp.17-18
• /
• 2015

In manufacturing industry, image scanning technique has made enormous progress in past decades. 3D models have been also very important to continuously monitor the related spatial information for freeform buildings. The process of shape making of 3D scanning is as follows: mesh surface segmentation, NURBS surface generation, and parametric solid model generation. We will review the process and applying process. Especially in the construction industry, 3D data collection by laser scanning has become an high quality 3D models. Therefore, in this research, we have an effort to review construction of reverse design process for freeform envelope using 3D scanning. The technology enables many 3D shape engineering and design parameterization of reverse engineering in the construction site.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.160-168
• /
• 2022

In this paper, we propose a 3D mesh reconstruction method from a single image using deep learning and a sphere shape transformation method. The proposed method has the following originality that is different from the existing method. First, the position of the vertex of the sphere is modified to be very similar to the 3D point cloud of an object through a deep learning network, unlike the existing method of building edges or faces by connecting nearby points. Because 3D point cloud is used, less memory is required and faster operation is possible because only addition operation is performed between offset value at the vertices of the sphere. Second, the 3D mesh is reconstructed by covering the surface information of the sphere on the modified vertices. Even when the distance between the points of the 3D point cloud created by correcting the position of the vertices of the sphere is not constant, it already has the face information of the sphere called face information of the sphere, which indicates whether the points are connected or not, thereby preventing simplification or loss of expression. can do. In order to evaluate the objective reliability of the proposed method, the experiment was conducted in the same way as in the comparative papers using the ShapeNet dataset, which is an open standard dataset. As a result, the IoU value of the method proposed in this paper was 0.581, and the chamfer distance value was It was calculated as 0.212. The higher the IoU value and the lower the chamfer distance value, the better the results. Therefore, the efficiency of the 3D mesh reconstruction was demonstrated compared to the methods published in other papers.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.294-295
• /
• 2011

본 논문에서는 스마트폰의 카메라와 플래시를 이용한 Shape from Shading 방법으로 3차원 형상 취득을 위한 카메라와 플래시의 보정 기법을 제시한다. 영상에서 관찰되는 화소 값은 카메라의 반응곡선에 의해 비선형적으로 표현되고 렌즈의 왜곡으로 인해 3차원 형상 복원에 오차를 발생 시킨다. 기하학적(geometric) 보정과 방사량(radiometric) 보정, 플래시 보정을 수행함으로써 3차원 형상 복원의 오차를 줄인다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.672-678
• /
• 1993

The bead shape in high frequency electric resistance (HER) pipe welding gives important information ons judging current welding state. In most manufacturing process, the heat input is controlled by skilled operators observing color and bead shape. We proposed the bead shape monitoring system in HERW pipe process by using structured light beam. We reconstructs 3-D shape of bead from the measured data, and compare this shape with real 3-D shape obtained by coordinate-measuring machine. This experiment results show that the proposed system can monitor the bead shape with good accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.469-478
• /
• 2010

This paper proposes the effective shape descriptor for 3D foot pose estimation. To reduce processing time, silhouette-based foot image database is built and meta information which involves the 3D pose of the foot is appended to the database. And we proposed a modified Centroid Contour Distance whose size of the feature space is small and performance of pose estimation is better than the others. In order to analyze performance of the descriptor, we evaluate time and spatial complexity with retrieval accuracy, and then compare with the previous methods. Experimental results show that the proposed descriptor is more effective than the previous methods on feature extraction time and pose estimation accuracy.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.27-37
• /
• 2008

Applications of 3D data increase with advancement of multimedia technique and contents, and it is necessary to manage and to retrieve for 3D data efficiently. In this paper, we propose a new method using the sliced shape which extracts efficiently a feature description for shape-based retrieval of 3D models. Since the feature descriptor of 3D model should be invariant to translation, rotation and scale for its model, normalization of models requires for 3D model retrieval system. This paper uses principal component analysis(PCA) method in order to normalize all the models. The proposed algorithm finds a direction of each axis by the PCA and creates orthogonal n planes in each axis. These planes are orthogonalized with each axis, and are used to extract sliced shape image. Sliced shape image is the 2D plane created by intersecting at between 3D model and these planes. The proposed feature descriptor is a distribution of Euclidean distances from center point of sliced shape image to its outline. A performed evaluation is used for average of the normalize modified retrieval rank(ANMRR) with a standard evaluation from MPEG-7. In our experimental results, we demonstrate that the proposed method is an efficient 3D model retrieval.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.2
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.13-22
• /
• 2023

In this paper, we present a method for estimating full 3D shapes from given 2D silhouette images of human bodies. Because the silhouette only consists of the partial information on the true shape, it is an ill-posed problem. To address the problem, we use the statistical human shape space obtained from the existing large 3D human shape database. The method consists of three steps. First, we extract the boundary pixels and their appropriate normal vectors from the input silhouette images. Then, we initialize the correspondences of each pixel to the vertex of the statistically-deformable 3D human model. Finally, we numerically optimize the parameters of the statistical model to fit best to the given silhouettes. The viability and the robustness of the method is demonstrated with various experiments.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.3
• /
• pp.254-262
• /
• 2015

This paper presents 3D collision deformation modelling methodologies using photogrammetry for reconstruction of vehicle accidents. A vehicle's deformation shape in collision provides important information on how the vehicle collided. So effective measurement(scanning) and construction of a corresponding appropriate model are essential in the analysis of collision deformation shape for obtaining much information related to collision accident. Two measurement methods were used in this study: Indirect-photogrammetry which requires relatively small amount of photos or videos, and direct-photogrammetry which requires large amount of photos directly taken for the purpose of 3D modelling. When the indirect-photogrammetry method, which was mainly used in this study, lacked enough photographic information, already secured 2D numerical deformation data was used as a compensation. This made 3D collision deformation modelling for accident reconstruction analysis possible.