• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.7
• /
• pp.1245-1249
• /
• 2001

In this paper I describe an Effective method by which analyzes the Fault-Tree, with Shannon decomposition. The advantage of this method are: 1) All the minimal outsets can not be preprocessed. 2) The maximum error can be prespecified. 3) s-dependent system also can be analyzed. But disadvantage is that certain subtrees of the decomposition tree can not be determined easily.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.133-134
• /
• 2015

흉부 X-ray 영상에서 몸체 및 관심영역 분할 기법은 의료 X-ray 영상의 화질 개선 알고리즘을 더 효과적으로 적용하기 위해 전처리 단계로 영상의 물체와 배경을 분할하거나 관심영역만을 분할하는 방법이다. 보통 화질 개선 알고리즘을 적용할 때 영상의 밝기 정보나 주파수 정보를 이용하여 영상 디테일과 대비를 개선하는 방법을 사용한다. 영상 전체에 이러한 알고리즘을 적용하는 경우 불필요한 배경 정보가 포함되기 때문에 디테일과 대비가 떨어질 수 있다. 본 논문은 사용자가 보고자 하는 부분의 정보만을 사용하도록 물체를 분할하는 알고리즘을 제안한다. 1 단계로 몸체 분할 알고리즘을 이용하여 배경 성분의 정보를 제외하고 2 단계에서는 몸체의 중심인 폐와 폐사이의 장기 정보만을 볼 때의 관심영역 분할 알고리즘으로 팔이나 목, 복부의 불필요한 정보를 제외하는 방법을 제안한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.223-226
• /
• 2003

When we detect side-view face in color image, we decide a candidate face region using skin-tone color, and confirm to the face by template matching. Cang Wei use a left and a right template of face, calculate to similarity value by hausdorff method, and decide the final side-view face. It has a characteristic that side-view face is wide spreading neck region. To get exactly result, face region is separated vertically by 3 pixel unit, and matched template. In this paper, we assume that a side-view face is a right side-view or a left side-view face. We separate a half of the candidate face region vertically, and regard a left side as left candidate face, a right side as right candidate face by template matching. This method detect faster than Gang Wei method.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.99-110
• /
• 2023

In this paper, we propose a system termed ForestLi that can accurately estimate the diameter at breast height (DBH) and tree height using LiDAR point cloud data. The ForestLi system processes LiDAR point cloud data through the following steps: downsampling, outlier removal, ground segmentation, ground height normalization, stem extraction, individual tree segmentation, and DBH and tree height measurement. A commercial system, such as LiDAR360, for processing LiDAR point cloud data requires the user to directly correct errors in lower vegetation and individual tree segmentation. In contrast, the ForestLi system can automatically remove LiDAR point cloud data that correspond to lower vegetation in order to improve the accuracy of estimating DBH and tree height. This enables the ForestLi system to reduce the total processing time as well as enhance the accuracy of accuracy of measuring DBH and tree height compared to the LiDAR360 system. We performed an empirical study to confirm that the ForestLi system outperforms the LiDAR360 system in terms of the total processing time and accuracy of measuring DBH and tree height.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.3
• /
• pp.317-325
• /
• 2021

Pine wilt disease first appeared in Busan in 1998; it is a serious disease that causes enormous damage to pine trees. The Korean government enacted a special law on the control of pine wilt disease in 2005, which controls and prohibits the movement of pine trees in affected areas. However, existing forecasting and control methods have physical and economic challenges in reducing pine wilt disease that occurs simultaneously and radically in mountainous terrain. In this study, the authors present the use of a deep learning object recognition and prediction method based on visual materials using an unmanned aerial vehicle (UAV) to effectively detect trees suspected of being infected with pine wilt disease. In order to observe pine wilt disease, an orthomosaic was produced using image data acquired through aerial shots. As a result, 198 damaged trees were identified, while 84 damaged trees were identified in field surveys that excluded areas with inaccessible steep slopes and cliffs. Analysis using image segmentation (SegNet) and image detection (YOLOv2) obtained a performance value of 0.57 and 0.77, respectively.

• Proceedings of the KIPE Conference
• /
• 2014.07a
• /
• pp.126-127
• /
• 2014

기존 IPMSM (Interior Permanent Magnet Synchronous Motor) 제어를 위한 LUT (Look Up Table)방식은 입력한 일정 간격의 데이터를 이용한 선형 보간 방법이 주로 사용되었다. 하지만, 이러한 방식은 LUT 구성을 위해 많은 데이터를 요구하므로, DSP 메모리 용량에 LUT 구성의 한계가 존재한다. 또한, 많은 양의 데이터를 관리해야하는 단점을 가지고 있다. 본 논문에서는 이러한 단점을 보완하기 위하여 영역 분할을 이용한 다항식 곡면 적합 LUT 구성을 제안하였다. 다항식 곡면 적합을 이용한 LUT 구성 방법은, 관리해야하는 데이터양을 비약적으로 줄일 수 있는 장점을 가지고 있다. 제안한 방법의 효용성은 실험을 통하여 증명하였다.

• Journal of Korean Society of Forest Science
• /
• v.112 no.2
• /
• pp.195-208
• /
• 2023

This study aimed to use three-dimensional point cloud data (PCD) obtained from Terrestrial Laser Scanning (TLS) and Mobile Laser Scanning (MLS) to evaluate a deep learning-based species classification model for two tree species: Pinus koraiensis and Larix kaempferi. Sixteen models were constructed based on the three conditions: LiDAR platform (TLS and MLS), down-sampling intensity (1024, 2048, 4096, 8192), and deep learning model (PointNet, PointNet++). According to the classification accuracy evaluation, the highest kappa coefficients were 93.7% for TLS and 96.9% for MLS when applied to PCD data from the PointNet++ model, with down-sampling intensities of 8192 and 2048, respectively. Furthermore, PointNet++ was consistently more accurate than PointNet in all scenarios sharing the same platform and down-sampling intensity. Misclassification occurred among individuals of different species with structurally similar characteristics, among individual trees that exhibited eccentric growth due to their location on slopes or around trails, and among some individual trees in which the crown was vertically divided during tree segmentation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.1
• /
• pp.1-8
• /
• 1992

A method analizing contact pressure between plate and elastic half space is presented by using F.E.M. With the method, the pressure intensities at surface nodes of half space cae be directly calculated by using flexibility matrix of half space. The method is originally presented by Y.K. Cheung et al.(3) Insted of Y.K. Cheung's method, which use a conception of equi-contact pressure area around each surface nodes of half space in the noded rectanqular element area. We use the equi-contact pressure area around the Gaussian integration points of half space surface in the noded isoparametric element area. Numarical examples are presented and compared with other's studies.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.122-127
• /
• 2016

This paper propose implementation method of SoC system for efficient depth image segmentation. SoC systems are combined platform in the form of the Software and Hardware IP. In order to perform effectively, the user to determine the operation of the configuration of each part. In this paper, we implemented a segmentation of depth images taken by the infrared sensor at APU of SoC system. The proposed method efficiently implements high performance and low power in SoC system. Proposed method that using software parts of SoC system is capable to use at several depth image processing systems.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1994.04a
• /
• pp.65-72
• /
• 1994

This study presents the application of multi-level substructuring for the effective nonlinear analysis of coupled wall structures. Also, the transition elements with 8 or 12 d. o. f, 5-node plane stress elements and concrete nonlinear model are considered as the basic finite elements of substructuring. In particular, the concept of localized nonlinearity is considered for the probable nonlinear zones of the structure, and the effective bottom-up and top-down process are presented through connectivity trees. The nonlinear analysis based on localized nonlinearity and multi-level substructuring, compared with the complete nonlinear analysis of the structure, gives the greater saving effects in computational efforts and cost.