• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.546-549
• /
• 1997

3D medical image reconstruction techniques are useful to figure out complex 3D structure from the set of 2D sections but their implementations are difficult due to processor's limitation and their computational complexity. In this paper, we propose a new speed optimization technique or accelerating the volume rendering algorithm. In addition, the whole procedure or reconstructing the medical images are constructed by using Visual C++ 5.0 under PC environment. They include classification, shading and ray-casting.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.443-450
• /
• 2009

Purpose: Conventional image reconstruction uses simplified physical models of projection. However, real physics, for example 3D reconstruction, takes too long time to process all the data in clinic and is unable in a common reconstruction machine because of the large memory for complex physical models. We suggest the realistic distributed memory model of fast-reconstruction using parallel processing on personal computers to enable large-scale technologies. Materials and Methods: The preliminary tests for the possibility on virtual manchines and various performance test on commercial super computer, Tachyon were performed. Expectation maximization algorithm with common 2D projection and realistic 3D line of response were tested. Since the process time was getting slower (max 6 times) after a certain iteration, optimization for compiler was performed to maximize the efficiency of parallelization. Results: Parallel processing of a program on multiple computers was available on Linux with MPICH and NFS. We verified that differences between parallel processed image and single processed image at the same iterations were under the significant digits of floating point number, about 6 bit. Double processors showed good efficiency (1.96 times) of parallel computing. Delay phenomenon was solved by vectorization method using SSE. Conclusion: Through the study, realistic parallel computing system in clinic was established to be able to reconstruct by plenty of memory using the realistic physical models which was impossible to simplify.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.6_1
• /
• pp.507-516
• /
• 2007

Segmentation and organization of the LiDAR (Light Detection and Ranging) data of the Earth's surface are difficult tasks because the captured LiDAR data are composed of irregularly distributed point clouds with lack of semantic information. The reason for this difficulty in processing LiDAR data is that the data provide huge amount of the spatial coordinates without topological and/or relational information among the points. This study introduces LiDAR data segmentation technique by utilizing histograms of the LiDAR height image data and analyzing roof shape for 3D reconstruction and visualization of the buildings. One of the advantages in utilizing LiDAR height image data is no registration required because the LiDAR data are geo-referenced and ortho-projected data. In consequence, measurements on the image provide absolute reference coordinates. The LiDAR image allows measurement of the initial building boundaries to estimate locations of the side walls and to form the planar surfaces which represent approximate building footprints. LiDAR points close to each side wall were grouped together then the least-square planar surface fitting with the segmented point clouds was performed to determine precise location of each wall of an building. Finally, roof shape analysis was performed by accumulated slopes along the profiles of the roof top. However, simulated LiDAR data were used for analyzing roof shape because buildings with various shapes of the roof do not exist in the test area. The proposed approach has been tested on the heavily built-up urban residential area. 3D digital vector map produced by digitizing complied aerial photographs was used to evaluate accuracy of the results. Experimental results show efficiency of the proposed methodology for 3D building reconstruction and large scale digital mapping especially for the urban area.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2943-2948
• /
• 2015

Run 3D reconstruction using a single camera, based on the information, we are advancing research on driving assistance apparatus or can be informed how to pass the obstacle existing ahead the driver. As a result depth information falls but it is possible to provide information that can pass through an obstacle on the straight. For 3D reconstruction by measuring the internal parameters, it calculates the Fundamental matrix and matching to find the feature points obtained by executing the triangulation on the basis of this. When the through experiments try to confirm the results, the depth information is present error information in the X and Y axes which can determine whether or not to pass through an obstacle has reliability.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.248-251
• /
• 2007

In this paper, we are propose a method to estimate the 2-D mesh from structured light image for reconstruction of 3-D face image. To acquire the structured light image, we are project structured light on the face using the projector. we are extract the projected cross points from the acquire image. The 2-D mesh image is extracted from the position and angle of cross points. In the extraction processing, the error was fixed to extract the correct 2-D mesh.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.3
• /
• pp.124-130
• /
• 2006

A wavelet-based image compression system allowing both lossless and lossy image compression is proposed in this paper. The proposed algorithm consists of the two stages. The first stage uses the wavelet packet transform and the quad-tree coding scheme for the lossy compression. In the second stage, the residue image taken between the original image and the lossy reconstruction image is coded for the lossless image compression by using the integer wavelet transform and the context based predictive technique with feedback error. The proposed wavelet-based algorithm, allowing an optional lossless reconstruction of a given image, transmits progressively image materials and chooses an appropriate wavelet filter in each stage. The lossy compression result of the proposed algorithm improves up to the maximum 1 dB PSNR performance of the high frequency image, compared to that of JPEG-2000 algorithm and that of S+P algorithm. In addition, the lossless compression result of the proposed algorithm improves up to the maximum 0.39 compression rates of the high frequency image, compared to that of the existing algorithm.

• Journal of IKEEE
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2008

This paper presents a new method for building detection and reconstruction from aerial images. In our approach, we extract the useful building location information from the generated disparity map to obtain the segmentation of interested objects and thus reduce significantly unnecessary line segment extracted in low level feature extraction step. Hypothesis selection is carried out by using undirected graph in which close cycles represent complete rooftops hypotheses, and hypothesis are finally tested to contruct building model. We test the proposed method with synthetic images generated from Avenches dataset of Ascona aerial images. The experiment result shows that the extracted 3D line segments of the buildings can be efficiently used for the task of building detection and reconstruction from aerial images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1749-1752
• /
• 2005

For online high accurate reconstruction of an object from an visual information, a linear reconstruction method for multiple images is popular. Basically this method needs many cameras or many different screen shots from different view points. This method, however, has the benefit of less calculation and is adequate for a real time application by comparing other popular method. In this paper, online reconstruction system using more than three cameras is treated. An evaluation method of cameras' position, and of the number is derived for the linear reconstruction method. To decrease errors that are caused from skew of lens, positional error between corresponding points is taken into consideration on the evaluation. The proposed evaluation method enables estimation of the adequate number of cameras and then of feasible view locations. Additionally, repeating search of epipolar lines enables estimation of the hidden point. Comparing with result of an average error analysis, it was confirmed that the proposed methods works effectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.643-644
• /
• 2012

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.