• Journal of Korea Multimedia Society
• /
• v.17 no.7
• /
• pp.818-828
• /
• 2014

After emerging of Microsoft Kinect, the interest in three-dimensional (3D) depth image was significantly increased. Depth image data of an object can be converted to 3D coordinates by simple arithmetic calculation and then can be reconstructed as a 3D model on computer. However, because the surface coordinates can be acquired only from the front area facing Kinect, total solid which has a closed surface cannot be reconstructed. In this paper, 3D registration method for multiple Kinects was suggested, in which surface information from each Kinect was simultaneously collected and registered in real time to build 3D total solid. To unify relative coordinate system used by each Kinect, 3D perspective transform was adopted. Also, to detect control points which are necessary to generate transformation matrix, 3D randomized Hough transform was used. Once transform matrices were generated, real time 3D reconstruction of various objects was possible. To verify the usefulness of suggested method, human arms were 3D reconstructed and the volumes of them were measured by using four Kinects. This volume measuring system was developed to monitor the level of lymphedema of patients after cancer treatment and the measurement difference with medical CT was lower than 5%, expected CT reconstruction error.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.969-970
• /
• 2008

• 한국정보컨버전스학회:학술대회논문집
• /
• 2008.06a
• /
• pp.145-150
• /
• 2008

This thesis explores the problem of reconstructing a three-dimensional(3D) scene given a set of images or image sequences of the scene. It describes efficient methods for the 3D reconstruction of static and dynamic scenes from stereo images, stereo image sequences, and images captured from multiple viewpoints. Novel methods for image-based and volumetric modelling approaches to 3D reconstruction are presented, with an emphasis on the development of efficient algorithm which produce high quality and accurate reconstructions. For image-based 3D reconstruction a novel energy minimisation scheme, Iterated Dynamic Programming, is presented for the efficient computation of strong local minima of discontinuity preserving energyy functions. Coupled with a novel morphological decomposition method and subregioning schemes for the efficient computation of a narrowband matching cost volume. the minimisation framework is applied to solve problems in stereo matching, stereo-temporal reconstruction, motion estimation, 2D image registration and 3D image registration. This thesis establishes Iterated Dynamic Programming as an efficient and effective energy minimisation scheme suitable for computer vision problems which involve finding correspondences across images. For 3D reconstruction from multiple view images with arbitrary camera placement, a novel volumetric modelling technique, Embedded Voxel Colouring, is presented that efficiently embeds all reconstructions of a 3D scene into a single output in a single scan of the volumetric space under exact visibility. An adaptive thresholding framework is also introduced for the computation of the optimal set of thresholds to obtain high quality 3D reconstructions. This thesis establishes the Embedded Voxel Colouring framework as a fast, efficient and effective method for 3D reconstruction from multiple view images.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.456-463
• /
• 2003

This paper presents a texture mapping method of a 3D scanned model with 2D images from different views. The texture mapping process consists of two steps Registration of the 3D facet model to the images by interactive points matching, and 3D texture mapping of the image pieces to the corresponding facets. In this paper. some implem entation issues and illustrative examples are described.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.765-774
• /
• 2019

In this paper, we propose a point cloud matching algorithm for multiple RGB-D cameras. In general, computer vision is concerned with the problem of precisely estimating camera position. Existing 3D model generation methods require a large number of cameras or expensive 3D cameras. In addition, the conventional method of obtaining the camera external parameters through the two-dimensional image has a large estimation error. In this paper, we propose a method to obtain coordinate transformation parameters with an error within a valid range by using depth image and function optimization method to generate omni-directional three-dimensional model using 8 low-cost RGB-D cameras.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.35 no.2
• /
• pp.192-205
• /
• 2011

This study analyzed the registration of patent and utility models by fashion firms in Korea. A total of 2,291 registration cases of IPC A41B-H from the period of 1996 to 2009 were collected by KIPRIS of the Korean Intellectual Property Organization (KIPO). All cases were analyzed by year to review the longitudinal trend and 481 cases of IPC A41B (shirts, underwear, baby linen, and handkerchiefs) and 1088 cases of IPC A41D (outerwear, protective garments, and accessories) were analyzed by content (provided benefit type and developing method), by detailed product items and the characteristics of the applicant. The results of this study were as follows: 1) Registration of IPC 41 increased steeply by the year (especially since 2006) and the patent registrations increased more than those in the utility model. 2) Analyzing the application content of A41B on the basis of benefit showed that 75% were to provide new functions and the rest were for health. In terms of the developing method, 83% of benefit provided by the application were by design development, 11.2% were by material, and the rest was by process, In the cases of IPC A41D, 23.6% were for safety and protection. In terms of the developing method, the process and material development were more frequently adopted than in the cases of A41B. 3) The major product types of A41B were socks, underwear, and infant wear, whereas gloves and parts of clothing were major items in A41D. 4) In terms of the characteristics of the applicant, registration by firms was greater for patents than for utility models and registration by foreigners increased in 2006 due to the complete opening of the retail market. 5) Fifteen universities registered for a total 57 cases and major applications were for IT related clothing or high-tech protective items.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.652-658
• /
• 2021

When acquiring a point cloud using a 3D scanner, a registration process of making the acquired data based on each local coordinate into one data with a unified world coordinate system is required. Its process is difficult to obtain a satisfactory result with only one execution, and it is repeated several times to increase the registration precision. The criterion for determining the registration accuracy is an important factor. The previous methods for determining the accuracy of registration have a limitation in that the judgment may be ambiguous in some cases, and different results may be produced each time depending on the characteristics of the point cloud. Therefore, to calculate the accuracy of registration more precisely, I propose a method using the average distance value of the point group for the entire points rather than the corresponding points used in the registration. When this method is used, it is possible to determine the registration accuracy more reliably than the conventional methods.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.64-74
• /
• 2019

Although a non-rigid registration has high demands in clinical practice, it has a high computational complexity and it is very difficult for ensuring the accuracy and robustness of registration. This study proposes a method of applying a non-rigid registration to 3D magnetic resonance images of brain in an unsupervised learning environment by using a deep-learning network. A feature vector between two images is produced through the network by receiving both images from two different patients as inputs and it transforms the target image to match the source image by creating a displacement vector field. The network is designed based on a U-Net shape so that feature vectors that consider all global and local differences between two images can be constructed when performing the registration. As a regularization term is added to a loss function, a transformation result similar to that of a real brain movement can be obtained after the application of trilinear interpolation. This method enables a non-rigid registration with a single-pass deformation by only receiving two arbitrary images as inputs through an unsupervised learning. Therefore, it can perform faster than other non-learning-based registration methods that require iterative optimization processes. Our experiment was performed with 3D magnetic resonance images of 50 human brains, and the measurement result of the dice similarity coefficient confirmed an approximately 16% similarity improvement by using our method after the registration. It also showed a similar performance compared with the non-learning-based method, with about 10,000 times speed increase. The proposed method can be used for non-rigid registration of various kinds of medical image data.

• Journal of Mechanical Science and Technology
• /
• v.19 no.12
• /
• pp.2213-2223
• /
• 2005

In order to reconstruct a full 3D human model in reverse engineering (RE), a 3D scanner needs to be placed arbitrarily around the target model to capture all part of the scanned surface. Then, acquired multiple scans must be registered and merged since each scanned data set taken from different position is just given in its own local co-ordinate system. The goal of the registration is to create a single model by aligning all individual scans. It usually consists of two sub-steps: rough and fine registration. The fine registration process can only be performed after an initial position is approximated through the rough registration. Hence an automated rough registration process is crucial to realize a completely automatic RE system. In this paper an automated rough registration method for aligning multiple scans of complex human face is presented. The proposed method automatically aligns the meshes of different scans with the information of features that are extracted from the estimated principal curvatures of triangular meshes of the human face. Then the roughly aligned scanned data sets are further precisely enhanced with a fine registration step with the recently popular Iterative Closest Point (ICP) algorithm. Some typical examples are presented and discussed to validate the proposed system.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.3
• /
• pp.342-357
• /
• 2014

The present study analyzes the relationship between research and development (R&D) inputs and performance of a national technology innovation R&D program using successive binary Logistic regression models based on a typical R&D logic model. In particular, this study focuses on to answer the following three main questions; (1) "To what extent, do the R&D inputs have an effect on the performance creation?"; (2) "Is an obvious relationship verified between the immediate predecessor and its successor performance?"; and (3) "Is there a difference in the performance creation between R&D government subsidy recipient types and between R&D collaboration types?" Methodologically, binary Logistic regression models are established successively considering the "Success-Failure" binary data characteristic regarding the performance creation. An empirical analysis is presented analyzing the sample n = 2,178 R&D projects completed. This study's major findings are as follows. First, the R&D inputs have a statistically significant relationship only with the short-term, technical output, "Patent Registration." Second, strong dependencies are identified between the immediate predecessor and its successor performance. Third, the success probability of the performance creation is statistically significantly different between the R&D types aforementioned. Specifically, compared with "Large Company", "Small and Medium-Sized Enterprise (SMS)" shows a greater success probability of "Sales" and "New Employment." Meanwhile, "R&D Collaboration" achieves a larger success probability of "Patent Registration" and "Sales."