• 한국산림과학회지
• /
• 제112권2호
• /
• pp.195-208
• /
• 2023

본 연구는 잣나무와 낙엽송을 대상으로 라이다로부터 취득된 3차원의 Point cloud data (PCD)를 이용하여 딥러닝 기반의 수종 분류 모델을 구축하고 분류정확도를 비교·평가하였다. 수종 분류 모델은 라이다 플랫폼(고정식과 이동식), Farthest point sampling (FPS) 기반의 다운샘플링 강도(1024개, 2048개, 4096개, 8192개), 딥러닝 모델(PointNet, PointNet++) 3가지 조건에 따라 총 16개의 모델을 구축하였다. 분류 정확도 평가 결과, 고정식 라이다는 다운샘플링 강도가 8192개인 PCD 자료에 PointNet++ 모델을 적용하였을 때 카파계수가 93.7%로 가장 높았으며, 이동식 라이다는 다운샘플링 강도가 2048개에 PointNet++을 적용하였을 때 카파계수가 96.9%로 가장 높았다. 또한, 플랫폼과 다운샘플링 강도가 동일한 경우 PointNet++이 PointNet보다 정확도가 높았다. 구축된 16개 모델의 오분류 사례는 첫 번째, 수종 간의 구조적인 특징이 유사한 개체목 두 번째, 경사지 또는 임도 주변에 위치하여 편심생장한 개체목 세 번째, 개체목 분할 시 수관부가 수직으로 분할된 개체목에 대해 발생하였다.

• 로봇학회논문지
• /
• 제10권1호
• /
• pp.9-15
• /
• 2015

We present a robust power transmission lines detection method based on vanishing point estimation. Vanishing point estimation can be helpful to detect power transmission lines because parallel lines converge on the vanishing point in a projected 2D image. However, it is not easy to estimate the vanishing point correctly in an image with complex background. Thus, we first propose a vanishing point estimation method on power transmission lines by using a probabilistic voting procedure based on intersection points of line segments. In images obtained by our system, power transmission lines are located in a fan-shaped area centered on this estimated vanishing point, and therefore we select the line segments that converge to the estimated vanishing point as candidate line segments for power transmission lines only in this fan-shaped area. Finally, we detect the power transmission lines from these candidate line segments. Experimental results show that the proposed method is robust to noise and efficient to detect power transmission lines.

• 한국환경과학회지
• /
• 제31권6호
• /
• pp.461-470
• /
• 2022

When an agricultural soil dam collapses, the extent of inundation and the rate of diffusion vary depending on where the collapse occurs in the dam body. In this study, a dam collapse scenario was established and a two-dimensional numerical model FLO-2D was used to closely examine the inundation pattern of the downstream residential area according to the dam collapse point. The results were presented as a flood risk map showing the changes and patterns of the extent of inundation spread. The flood level and the time to reach the maximum water level vary depending on the point of collapse, and the inundation of the downstream area proceeds rapidly in the order of the midpoint, left point, and right point collapse. In the left collapse point, the submergence appeared about 0.5 hour slower than the middle point, and the right collapse point appeared about 1 hour slower than the middle point. Since the relative damage pattern is different depending on the dam collapse point, insurance and disaster countermeasures will have to be established differently.

• Journal of applied mathematics & informatics
• /
• 제28권3_4호
• /
• pp.877-882
• /
• 2010

In this paper, a third-order three-point boundary value problem on time scales is considered. We establish criteria for the existence of a solution and a positive solution by using the Leray-Schauder fixed point theorem. An example is also given to illustrate our results.

• Kyungpook Mathematical Journal
• /
• 제56권3호
• /
• pp.807-817
• /
• 2016

The aim of this paper is to introduce the notion of ${\epsilon}$-compatible maps and obtain some common fixed point theorems. Also, our results generalize some well known fixed point theorems.

• Journal of the Optical Society of Korea
• /
• 제20권5호
• /
• pp.633-640
• /
• 2016

In a dual lens stereoscopic camera, a convergence point determines the stereopsis effects of a video. When a user zooms an object, a convergence point is fixed since it is not coupled with a zoom function. Due to the fixed convergence point, it is possible for a zoom to cause the excessive binocular disparity resulting in visual discomfort. In this paper, to solve this problem, we build the relational model including all phenomena possible to arise and propose the adjustment methods of a convergence point by the positions of a focus, an object and a convergence point. We also evaluate the experiments measuring a binocular disparity and the subjective test to investigate the visual comfort. The results show that one of the proposed methods produced more comfortable 3D images to viewers than the others.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2010-2014
• /
• 2005

Object detection and parameter estimation in point cloud data is a relevant subject to robotics, reverse engineering, computer vision, and sport mechanics. In this paper a software is presented for fully-automatic object detection and parameter estimation in unordered, incomplete and error-contaminated point cloud with a large number of data points. The software consists of three algorithmic modules each for object identification, point segmentation, and model fitting. The newly developed algorithms for orthogonal distance fitting (ODF) play a fundamental role in each of the three modules. The ODF algorithms estimate the model parameters by minimizing the square sum of the shortest distances between the model feature and the measurement points. Curvature analysis of the local quadric surfaces fitted to small patches of point cloud provides the necessary seed information for automatic model selection, point segmentation, and model fitting. The performance of the software on a variety of point cloud data will be demonstrated live.

• 산업경영시스템학회지
• /
• 제32권1호
• /
• pp.11-19
• /
• 2009

A number of trend test methods, i.e., Military Handbook test and Laplace test etc., have been applied to investigate recurrent failures trend in repairable systems. Existing methods provide information about only existence of trend in the system. In this paper, we propose a new change-point test based on the Schwarz Information Criterion(SIC). The change-point approach is more informative than other trend test methods in that it provides the number of change-points and the location of change-points if it exists, as well as the existence of change-point for recurrent failures. The change-point test is applied to nine 300MW generating units operated in East China. We confirm that the change-point test has a potential for establishing optimal preventive maintenance policy by detecting change-point of failure rate.

• Spatial Information Research
• /
• 제6권1호
• /
• pp.11-23
• /
• 1998

GIS 분야에서 지도 일반화는 공간자료의 상세도를 결정하여 효과적으로 자료를 가시화(Visualixation)하거나 자료의 해상력을 변화시켜 변환하는 기능을 수행한다. 최근까지 지도 일반화는 선사상 (Line Features)에 집중되었고, 수치지도를 구성하고 있는 정보량과 그 중요성에 비하여 점사상 (Point Features)에 대한 연구는 상대적으로 미미하였다. 이러한 맥락에서 본 연구는 점사상에 대한 구체적인 일반화 방안을 모색하는데 목적을 둔다. 특히 점사상의 일반화에서 원자료의 기하학적 특성을 파악하는데 가장 중요하게 고려한 요소로 점사상의 분포패턴을 선정하였다. 즉 'Grieg-Smith방법'을 활용한 방격분석 (Quadrat Analysis)과 최근린분석 (Nearest-Neighbour Analysis)를 통해 점사상이 갖고 있는 분포패턴의 특성을 찾아낸 다음, 이를 변형시키지 않도록 일반화의 기준거리(Threshold)를 설정하여 점사상을 제거하는 방법을 통해 점사상의 일반화를 시도하였다. 따라서 이 연구에서 제시한 점사상의 일반화 방안은 원래 점사상이 갖고 있는 기하학적 특성을 최대한 유지한다.

• 대한한의학회지
• /
• 제15권2호
• /
• pp.241-252
• /
• 1994

It is known that the pattern of combustion temperature can be classified into preheating, heating. retaining and cooling periods. In this experiment. the authors have studied the heating mechanism by the density of moxa material during the heating and retaining periods. The starting point. the point at which it begins to reach the maximum gradient temperature. the ending point of the heating period. and the ending point of the retaining period were measured in order to get effective stmulation by repetition of moxa-combustion. For the experiment. samples of 300mg. 400mg, and 500mg of moxa material were molded into conical molds with each 10mm in diameter and height resulting in the volume of $0.26cm^3$. The following results were obtained: The $300mg/0.26cm^3$ denstiy sample reached al1 points tested faster than the samples of $400mg/0.26cm^3$ and $500mg/0.26cm^3$ It dose not reveal any statistical differences between $400mg/0.26cm^3$ and $500mg/0.26cm^3$ in the ending point. the point at which it begins to reach the maximum gradient temperature of the heating period or the ending point of the reataining period The only difference shown was in the starting point of the heating period. According to the above results. it is concluded that the lower density moxa material reached each point of the the respective period faster than the high density moxa material.