• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.800-806
• /
• 2006

최근, 컴퓨터 사이언스 분야에서 모자이크에 대한 다양한 연구들이 이뤄지고 있지만, 세부 묘사를 유지하려는 관점에서의 접근은 부족한 편이다. 본 논문은 원 영상의 세부 묘사를 유지하는 타일 모자이크 방법을 제안한다. 이 방법은 타일간의 빈 공간을 제거하기 위한 겹쳐진 타일의 사용을 통해 구현된다. 본 논문에서 제시한 방법은 다음 세 단계로 구성된다. 첫째, 에지 회피 기법이 적용된 무게중심 보로노이 다이어그램(CVD:Centroidal Voronoi Diagram)을 통해 메인 타일의 위치를 얻는다. 둘째, 메인 타일들의 위치에 딜로니 삼각형화(Delaunay Triangulation)를 적용해 서브 타일의 위치를 계산한다. 셋째, 타일간의 관계를 고려해 타일의 크기와 방향성을 구한다. 위의 과정을 통해 타일 간의 빈 공간이 최소화되어 세부 묘사가 강화된 모자이크 영상을 얻는다.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2004.04a
• /
• pp.333-340
• /
• 2004

This paper deals with geometric nonlinear analyses using a new meshfree technique which improves the numerical integration accuracy. The new method called the Petrov-Galerkin natural element method (PGNEM) is based on the Voronoi diagram and the Delaunay triangulation which is based on the same concept used for conventional natural element method called the Bubnov-Galerkin natural element method (BGNEM). But, unlike BGNEM, the test shape function is differently chosen from the trial shape function. In the linear static analysis, it is ensured that the numerical integration error of the PGNEM is remarkably reduced. In this paper, the PGNEM is applied to large deformation problems, and the accuracy of the proposed numerical technique is verified through the several examples.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.146-149
• /
• 2002

It is reported that the mechanical properties of vertebral trabecular bone depend on the density and the mass of bones. Osteoporosis is a systemic skeletal disease caused by low bone mass and microstructure deterioration of trabecular bone. Silva and Gibson (1997) studied the treatment of age-related bone loss using drug therapy. Vertebroplasty is a minimally invasive surgery for the treatment of osteoporosis vertebrae. This procedure includes puncturing vertebrae and filling with Polymethylmethacrylate (PMMA). However, the relative effect of drug therapy and bone cement for osteoporosis treatment is not reported yet. In this study, several 2D models of human vertebral trabecular bone are analyzed by finite element method. The mechanical behaviors of the vertebral trabecular bone treated by the drug therapy and the bone cement are compared. This study shows that bone cement treatment is more effective strategy than drug therapy to prevent the degradation of bone strength.

• Journal of Communications and Networks
• /
• v.7 no.4
• /
• pp.417-428
• /
• 2005

The Voronoi diagram (VD) is the most suitable mechanism to find the nearest neighbor (NN) for mobile clients. In NN query processing, it is important to reduce the query response time, since a late query response may contain out-of-date information. In this paper, we study the issue of location dependent information services (LDISs) using a VD. To begin our study, we first introduce a broadcast-based spatial query processing methods designed to support NN query processing. In further sections, we introduce a generic method for location-dependent sequential prefetching and caching. The performance of this scheme is studied in different simulated environments. The core contribution of this research resides in our analytical proof and experimental results.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.37 no.12
• /
• pp.847-853
• /
• 1988

A method of three-demensional finite element mesh generation is presented in this paper. This method is based on the Delaunay's triangulation whose dual is Voronoi's diagram. A set of points is given on the boundary surface of the concerning domain and the initial tetrahedra are generated by the given set of points. Then, the quality of every tetrahedron is investigated and the interior points are generated near the tetrahedra which are inferior in quality and the tetrahedra of good quality can be controlled by the density of the initial boundary points. Regions with different material constant can be refined in tetrahedra respectively. To confirm the effectiveness of this algorithm,the total volume of tetrahedra was compared to the true volume and this mesh generator was applied to a three-dimensional electostatic problem.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.73-75
• /
• 2005

최근에 이동 객체의 위치 정보를 활용한 위치기반서비스(Location-based Services : LBS)에 대한 관심이 급증하고 있고, 다양한 서비스들이 연구되고 있다. 기존의 이동 객체에 대한 위치 의존 질의(Location-dependent Query)들은 단순히 대상 객체와의 거리만을 고려하였고, 스카이라인 질의(Skyline Query)는 질의의 위치와 무관한 대상 객체의 정적인 속성만을 고려하였다. 이동 객체에 대한 스카이라인 질의는 스카이라인 질의의 다중 속성과 이동 객체의 동적인 속성인 대상 객체와의 거리를 고려해야 하기 때문에 이동 객체의 위치 변경에 따른 연속적인 질의가 발생한다. 이 논문에서는 이동 객체의 연속적인 스카이라인 질의를 효율적으로 처리하기 위한 Voronoi Diagram(VD)기반의 스카이라인 영역(Skyline Region)정의와 효율적인 영역 결정 기법을 제안한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.53-60
• /
• 2010

We propose a motion planning method for autonomous mobile robots. In order to minimize traveling time, a smooth path and a time optimal velocity profile should be generated under kinematic and dynamic constraints. In this paper, we develop an effective and practical method to generate a good solution with lower computation time. The initial path is obtained from voronoi diagram by Dijkstra's algorithm. Then the path is improved by changing the graph and path simultaneously. We apply the dynamic programming algorithm into the stage of improvement. Simulation results are presented to verify the performance of the proposed method.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.335-342
• /
• 2001

본 논문은 보로노이 공간분류를 활용하여 원격탐사 영상인식을 위한 다층 신경망 분류기를제안한다. 제안된 다층 신경망 분류기는 보로노이 다각형 영역으로 클래스를 구분하며, 초평면 방정식의 계수를 오류 역전과 학습 초기의 연결 강도, 임계치 그리고 은닉층의 노드 수로 결정한다. 제안된 방법은 오류역전과 학습 알고리즘에서 임의로 정해주던 초기 정보를 사전 분석에 의해 공학적으로 결정함으로써 느린 수렴 속도와 학습실패 등의 단점을 피할 수 있는 장점이 있다. 보로노이 다이어그램에 대한 경계선의 초평면 방정식은 훈련집합의 클래스별 평균값을 구하여 Mathematica 패키지로 계산하였다. 제안된 다층 신경망에 의한 영상분류기의 인식능력을 평가하기 위하여 원격탐사 영상인식에서 자주 활용되는 최소거리 분류 방법과 최대우도 분류 방법으로 처리해서 비교한 결과, 최소거리 분류 방법은 실험화상에 대해 81.4%, 최대우도 부류기에 의한 분류는 87.8%, 제안한 방법은 92.2% 정확성을 가진 분류결과를 나타냈다.

• International Journal of CAD/CAM
• /
• v.2 no.1
• /
• pp.45-54
• /
• 2002

Given a set of three generator circles in a plane, we want to find a circumcircle of these generators. This problem is a part of well-known Apollonius' $10^{th}$ Problem and is frequently encountered in various geometric computations such as the Voronoi diagram for circles. It turns out that this seemingly trivial problem is not at all easy to solve in a general setting. In addition, there can be several degenerate configurations of the generators. For example, there may not exist any circumcircle, or there could be one or two circumcircle(s) depending on the generator configuration. Sometimes, a circumcircle itself may degenerate to a line. We show that the problem can be reduced to a point location problem among the regions bounded by two lines and two transformed circles via $M{\ddot{o}}bius$ transformations in a complex space. The presented algorithm is simple and the required computation is negligible. In addition, several degenerate cases are all incorporated into a unified framework.

• Korean Journal of Computational Design and Engineering
• /
• v.22 no.2
• /
• pp.110-117
• /
• 2017

Delaunay refinement algorithm is a classical method to generate quality triangular meshes when point cloud and/or constrained edges are given in two- or three-dimensional space. It computes the Delaunay triangulation for given points and edges to obtain an initial solution, and update the triangulation by inserting steiner points one by one to get an improved quality triangulation. This process repeats until it satisfies given quality criteria. The efficiency of the algorithm depends on the criteria and point insertion method. In this paper, we propose a method to accelerate the Delaunay refinement algorithm by applying geometric hashing technique called bucketing when inserting a new steiner point so that it can localize necessary computation. We have tested the proposed method with a few types of data sets, and the experimental result shows strong linear time behavior.