• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.315-320
• /
• 2017

Estimating the correct pose of augmented objects on the real camera view efficiently is one of the most important questions in image tracking area. In computer vision, Homography is used for camera pose estimation in augmented reality system with markerless. To estimating Homography, several algorithm like SURF features which extracted from images are used. Based on extracted features, Homography is estimated. For this purpose, RANSAC algorithm is well used to estimate homography and DCS-RANSAC algorithm is researched which apply constraints dynamically based on Constraint Satisfaction Problem to improve performance. In DCS-RANSAC, however, the dataset is based on pattern of feature distribution of images manually, so this algorithm cannot classify the input image, pattern of feature distribution is not recognized in DCS-RANSAC algorithm, which lead to reduce it's performance. To improve this problem, we suggest the KCS-RANSAC algorithm using K-means clustering in CS-RANSAC to cluster the images automatically based on pattern of feature distribution and apply constraints to each image groups. The suggested algorithm cluster the images automatically and apply the constraints to each clustered image groups. The experiment result shows that our KCS-RANSAC algorithm outperformed the DCS-RANSAC algorithm in terms of speed, accuracy, and inlier rate.

• Spatial Information Research
• /
• v.20 no.4
• /
• pp.69-82
• /
• 2012

The purpose of this study was to identify structural properties of C.B.D and to provide direction that required for the plan and its development by analyzing land use patterns and its characteristics in the center of the city. In this study, the future planning elements and detailed land use of Seoul was analyzed, in regard to the spatial structural hierarchy and the function of downtown, by investigation of its current urban spatial structure. First, the characteristic of the land-use for merchandising facilities is that it is developed from west to east along the Jong-ro, Myungdong and Namdaemun, it shows high rate of the facilities along the horizontal axis. The large market area on this district would be the reason to the high rate of mechandising facilities. Second, the characteristic of the land-use for business facilities is that it is highly rated on the area passing through the Sejong-ro and Seoul station. The analysis result of our investigation is that the projects executed by Seoul city such as 'downtown maintenance planning' and 'downtown recreation program' strengthened functions of business and merchandising and promoted downtown shopping, leisure, tourism functions resulting activation of nearby market place and evaluated as maintaing the centrality of downtown Seoul well.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.860-867
• /
• 2003

In this paper, an efficient core point detection method using orientation pattern labeling is proposed in fingerprint image. The core point, which is one of the singular points in fingerprint image, is used as the reference point in the most fingerprint recognizing system. Therefore, the detection of the core point is the most essential step of the fingerprint recognizing system, it can affect in the whole system performance. The proposed method could detect the position of the core point by applying the labeling method for the directional pattern which is come from the distribution of the ridges in fingerprint image and applying detailed algorithms for the decision of the core point's position. The simulation result of proposed method is better than the result of Poincare index method and the sine map method in executing time and detecting rate. Especially, the Poincare index method can't detect the core point in the detection of the arch type and the sine map method takes too much times for executing. But the proposed method can overcome these problems.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.38 no.3
• /
• pp.35-43
• /
• 2001

A method is newly presented to synthesize the modal impedances satisfying the desired coupling factor of a reflective (or hack ward) coupled-line. The synthesis is achieved by optimal perturbations of repeating null points of lobes inherent to the solution of the first order nonlinear differential equation for coupling. It is based on the synthesis method of nonlinear source distribution functions for the prescribed space factor pattern in the one-dimensional array antenna. Here, the conventional synthesis method for the even distribution function is extended to the odd case. Resulting modal impedances will have continuously varying profiles. The design procedure of asymmetrical and symmetrical couplers corresponding to the even and odd distribution functions, is examplified to show the generalization and the simplicity of the proposed method.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.885-892
• /
• 2004

Weibull distribution Iincluding Rayleigh and Exponential distribution is a typical model to estimate the effort distribution which is committed to the software testing phase. This model does not represent standpoint that many efforts are committed actually at the test beginning point. Moreover, it does not properly represent the various distribution form of actual test effort. To solve these problems, this paper proposes the Sigmoid model. The sigmoid function to be applicable in neural network transformed into the function which properly represents the test effort of software in the model. The model was verified to the six test effort data which were got from actual software projects which have various distribution form and verified the suitability. The Sigmoid model nay be selected by the alternative of Weibull model to estimate software test effort because it is superior than the Weibull model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.61-61
• /
• 2019

우리나라는 대부분이 산지(약 65%)로 구성되어 있어 강우 시 그 공간적 분포의 변동성이 매우 큰 편이며, 특히 전형적인 산지지형인 댐 유역의 경우 고도 변화 등에 기인한 지형특성 등에 따라 강우의 형태 및 패턴과 이에 따른 유출변화가 큰 복잡한 특성을 갖는다. 이로 인해 단순히 지점강우들을 공간보간(평균)한 면적강우를 홍수 유출모의 등에 활용할 경우 그 신뢰도가 매우 낮은 경우가 많아, 수문모의에 있어 레이더에 기반을 둔 공간 분포형 강우 등의 도입 검토가 요구된다. 한편, 최근 기상청에서는 보다 정확한 레이더 강수량 추정 값의 제공을 위해 "레이더-AWS 강우강도(Radar-AWS Rainrates, RAR)" 산출 기술을 지속적으로 개선하고 있으며, 이는 지상 우량계 대비 상당한 정확도를 보이고 있다. 본 연구에서는 국내 산지지형을 대표하며, 타 댐 유역에 비해 비교적 수문(수위/유량)관측소와 자료가 많은 용담시험유역에 기상레이더 강수량 추정 값(RAR)을 적용해 산지지형 댐 유역에서 강우의 시공간적 변동성과 이에 따른 홍수량의 정확한 분석을 통해 홍수 시 댐 유입량의 정확한 산정 등에 활용할 목적으로 홍수 유출모의를 수행하고자 한다. 모의에는 최근 5년(2014~2018년)동안 발생한 비교적 독립적인 1~2개(연도별)의 홍수사상을 적용하였으며, 모형은 분포형 강우를 적용할 수 있는 비교적 간단한 모형인 HEC-HMS를 활용하였다. HEC-HMS는 주로 집중형 수문모형(Lumped Hydrologic Model)으로 분류되어 레이더 강우와 같은 분포형 자료의 입력을 주로 적용치는 않고 있지만, HEC-GeoHMS와 ModClark 방법을 활용하면 격자단위의 분포형 강우를 적용할 수 있는 형태의 모델 구축이 가능하다. 모의 결과는 기존 유역평균 강우를 적용한 방법과 비교를 통해 그 개선점을 검토하고자 하며, 이를 통하여 산지지역 댐 유역의 홍수특성을 보다 더 정확하게 분석해보고자 한다. 한편, ModClark을 적용한 홍수 유출모의는 단순히 소유역별 도달시간의 격자별 비율을 고려한 홍수추적으로 그 해석상의 한계가 있어, 최근 개발된 하이브리드 수문모형(Hybrid Hydrologic Model, Distributed-Clark) 등도 동일유역에 대해 도입 적용할 계획에 있다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.3
• /
• pp.319-327
• /
• 2016

Korea faces a wide range of problems in areas such as safety, environment, and traffic due to the rapid economic development and urbanization process. Despite the local governments’ efforts to deal with electronic civil complaints and solve urban problems, civil complaints have been on the increase year by year. In this study, we collected civil complaint data over the last six years from a small and medium-sized city, Jinju-si. In order to conduct a spatial distribution pattern analysis, we indicated the location data on the area through Geocoding after classifying the reasons for civil complaints and then extracted the location data of the civil complaint occurrence spots in order to analyze the correlation between electronic civil complaints and land use. Results demonstrated that electronic civil complaints in Jinju-si were clustered in residential, central commercial, and residential-industrial mixed-use areas—areas where land development had been completed within the city center. After analyzing the civil complaints according to the land use, results revealed that complaints about illegal parking were the highest. Regarding the analysis results of facility distribution within a 50m radius from the civil complaint areas, civil complaints occurred a lot in detached housing areas located within the commercial and residential-industrial mixed-use areas. In the case of residential areas(old downtown), civil complaints were condensed in the areas with many ordinary restaurants. This research explored civil complaints in terms of the urban space and can be expected to be effectively utilized in finding solutions to the civil complaints

• Journal of Korean Society for Geospatial Information Science
• /
• v.9 no.2 s.18
• /
• pp.37-46
• /
• 2001

Spectral pattern recognition techniques are most used in classification of remotely sensed data. Yet, in any real image, adjacent pixels are related, because imaging sensors acquire significant portions of energy from adjacent pixels. And, with the continued improvement in the spatial resolution of remote sensing systems, another spatial pattern recognition approach is must considered. In this study, we aim to show the potentiality of spatial classification methods through comparing the accuracies of spectral classification methods and those of spectral classification methods. By the comparisons between the two methods, classification accuracies of 6 different spatial classification methods are higher than that of spectral classification method by 2-6% or so. Additionally, we can show it statistically through the classification experiments with different band combinations.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.91-98
• /
• 2023

With the increasing flood damage by frequently localized heavy rains, flood prediction research are being conducted to prevent flooding damage in advance. In this paper, we present a machine-learning scheme for developing a flooding depth and location prediction model using real-time rainfall data. This scheme proposes a dataset configuration method using the data as input, which can robustly configure various rainfall distribution patterns and train the model with less memory. These data are composed of two: valid total data and valid local. The one data that has a significant effect on flooding predicted the flooding location well but tended to have different values for predicting specific rainfall patterns. The other data that means the flood area partially affects flooding refers to valid local data. The valid local data was well learned for the fixed point method, but the flooding location was not accurately indicated for the arbitrary point method. Through this study, it is expected that a lot of damage can be prevented by predicting the depth and location of flooding in a real-time manner.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.142-144
• /
• 2004

다양한 지리 관측 기술 및 GPS 그리고 무선통신 기술의 발달로 인해, 해수의 흐름 변화 관측이나 PDA를 장착한 물류 차량 관리와 같이 시간에 따라 이동하는 여러 객체들의 변화를 추적하고 관리하는 것이 용이해지고 있다. 그리고. 이로 인해 지능형 교통 시스템. 물류 차량 관리 시스템 등이 활발히 개발되고 있다. 그러나 개발된 시스템에서 차량 운송 계획 평가 및 테스트를 할 경우 차량의 실제 데이터가 부족하기 때문에 적절한 평가 및 다양한 테스트를 하기 힘들고, 실생활에 알맞은 시스템을 만들기 어려움 점이 있다. 이렇게 부족한 차량 데이터를 보충하기 위해, 대부분의 연구에서는 몇몇의 이동 객체 위치 데이터 생성기를 활용하고 있다. 그러나 기존의 이동 객체 데이터 생성기는 단순히 정규 분포, 가우스 분포. 랜덤 데이터. 도로 정보 등을 고려하여 데이터를 생성하기 때문에. 사용자가 물류 수송 계획 등에 활용하기 위해 의도한 시나리오에 따른 데이터를 생성하지 못하고 있다. 따라서, 이 논문에서는 차량 위치 데이터 생성기에 사용자가 지정한 시나리오를 생성, 저장하는 이동 객체 패턴 제공기를 추가하여. 사용자 지정 시나리오를 지원하는 차량 위치 데이터 생성기를 설계한다 이 논문에서 설계된 차랑 위치 데이터 생성기는 사용자가 원하는 계획대로 차량의 위치 정보를 생성함으로써, 물류 수송 및 도로 건설계획 등을 검토할 때 도움이 될 수 있을 것이다.