• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.1453-1456
• /
• 2011

타일로 분할된 항공 라이다 데이터로 부터 데이터마이닝 기법을 이용한 지표면 분류 결과에 따라 건물을 포함하는 타일에 대해 적용할 건물영역 추출 기법을 제안한다. 본 기법은 재귀적 경계점 추출 알고리즘과 경계점 연결을 통해 경계선을 형성하고 경계선을 타일의 외벽과 연결해 건물영역의 외곽을 추출한다. 제안된 기법으로 추출된 건물 영역을 실제 항공사진과 비교하여 제시하고 재귀적 경계점 추출 알고리즘의 실행시간을 단축시키기 위해 사용된 지형정보 인덱스의 실행시간 단축 효과 분석이 제시된다.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.09a
• /
• pp.119-125
• /
• 2010

본 연구에서는 항공 라이다 데이터로부터 지표의 유형을 분류하는 과정에서 필요한 처리시간을 감소시켜 보다 효율적인 지형 분류가 가능하도록 타일 단위의 샘플링을 이용한 지형 분류 기법을 제안하였다. 또한 실험을 통하여 샘플링 정도에 따라 정확도와 시간효율을 비교분석하여 최적의 샘플링 정도를 제시하였다. 본 연구에서 제안한 타일 단위의 샘플링을 이용한 지형 분류기법을 이용해 자연재해내 도시 구조 변화 등의 지형정보의 변화를 탐지하기 위한 모니터링 목적으로 활용할 경우에 지형분류의 정확도 손실을 최소화하면서 빠른 처리가 가능하기 때문에 실시간 서비스가 가능해 질 수 있다.

• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.79-82
• /
• 2010

본 논문에서는 항공 라이다 데이터로부터 지형의 유형을 분류하는 과정에서 지형적 특성에 따라 분류에 사용하는 판정 윈도우의 크기를 가변적으로 조정하여 적용시키는 가변형 판정 윈도우를 이용한 지형 분류 기법을 제안하였다. 또한 실험을 통하여 가변형 판정 윈도우를 이용한 지형 분류 기법의 시간효율과 정확도를 분석하였다. 실험 결과에 따르면 제안된 가변형 판정 윈도우를 이용한 지형 분류 기법은 지형 분류에 사용되는 판정 윈도우의 개수를 줄여 지형 분류의 속도를 향상시켰기 때문에 빠른 분류 속도가 필요한 재해 피해 현황을 파악하기 위한 시스템에 적용 할 수 있을 것으로 기대된다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.8
• /
• pp.251-260
• /
• 2014

3D point data is utilized in various industry domains for its high accuracy to the surface information of an object. It is substantially utilized in geography for terrain scanning and analysis. Generally, 3D point data need to be changed by Gridding which produces a regularly spaced array of z values from irregularly spaced xyz data. But it requires long processing time and high resource cost to interpolate grid coordination. Kriging interpolation in Gridding has attracted because Kriging interpolation has more accuracy than other methods. However it haven't been used frequently since a processing is complex and slow. In this paper, we presented a parallel Gridding algorithm which contains Kriging and an application of grid data structure to fit MapReduce paradigm to this algorithm. Experiment was conducted for 1.6 and 4.3 billions of points from Airborne LiDAR files using our proposed MapReduce structure and the results show that the total execution time is decreased more than three times to the convention sequential program on three heterogenous clusters.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.4
• /
• pp.469-476
• /
• 2009

The new laser scanning technology allows to attain 3D information faster with higher accuracy on surface ground, vegetation and buildings of the earth surface. This acquired information can be used in many areas after modifying them appropriately by users. The contour production for accurate landform is an advanced technology that can reveal the mountain area landscapes hidden by the trees in detail. However, if extremely precise LiDAR data is used in constructing the contour, massive-sized data intricates the contour diagram and could amplify the data size inefficiently. This study illustrates the algorithm producing contour that is filtered in stages for more efficient utilization using the LiDAR contour produced by the detailed landscape data. This filtering stages allow to preserve the original landscape shape and to keep the data size small. Point Filtering determines the produced contour diagram shape and could minimize data size. Thus, in this study we compared experimentally filtered contour with the current digital map(1:5,000).

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.10a
• /
• pp.313-314
• /
• 2008

현재의 조감도 제작방법은 3D-Max, 포토샵과 같은 그래픽 프로그램을 이용하여 편집하는 방법이 일반적이다. 이러한 조감도는 일반적으로 제작과정에서의 특성상 2차원 평면 데이터를 이용하여 모델링하지만 지표면의 3차원 공간데이터를 사용하지 않고 대상지역의 사진 등을 편집하여 사용하기 때문에 주변 시설물을 정확히 반영하지 못하는 문제점을 가지고 있다. 본 연구에서는 다차원데이터를 이용하여 LiDAR 데이터에서 획득한 고정밀의 DEM과 고품질의 항공영상을 이용한 3차원 모델을 제작하여 조망권, 가시권, 지형분석 등을 수행하고, 주변의 모든 대상물을 고려한 효율적인 조감도를 제작하는 것이 본 연구의 목적이다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.6
• /
• pp.579-586
• /
• 2010

Due to the recent development of measuring technology and 3D programs, it has become possible to obtain various spatial data. This study utilizes the 2-dimensional data and 3-dimensional data extraction technology based on the existing empirical and statistical DB. The data obtained from geospatial data technology are integrated with civil engineering BIM to conduct the modeling of the topography of the target region and select the optimum location condition by using the cut and fill balance of the volume of earth. The target area is the land around Tamjin River, Jangheong-gun, Jeolla-do. The 3-dimensional topology linked with 3-dimensional mapping technology by using the orth-image and aerial LiDAR that uses aerial photo of the target area is visualized with Civil3D of AutoDesk. By using Civil3D program, the Thanks to the recent development of measuring technology and 3D programs, target area is analyzed through visualization and related data can be obtained for analysis. The method of using civil engineering BIM enables to obtain various and accurate information about the target area which is helpful for addressing the issues risen from the existing methodology. In this regard, it aims at searching for the alternatives and provides suggestions to utilize the information.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.229-239
• /
• 2019

All vegetation colonies have layered structure. This layer is called 'forest vertical structure.' Nowadays it is considered as an important indicator to estimate forest's vital condition, diversity and environmental effect of forest. So forest vertical structure should be surveyed. However, vertical structure is a kind of inner structure, so forest surveys are generally conducted through field surveys, a traditional forest inventory method which costs plenty of time and budget. Therefore, in this study, we propose a useful method to classify the vertical structure of forests using remote sensing aerial photographs and machine learning capable of mass data mining in order to reduce time and budget for forest vertical structure investigation. We classified it as SVM (Support Vector Machine) using RGB airborne photos and LiDAR (Light Detection and Ranging) DSM (Digital Surface Model) DTM (Digital Terrain Model). Accuracy based on pixel count is 66.22% when compared to field survey results. It is concluded that classification accuracy of layer classification is relatively high for single-layer and multi-layer classification, but it was concluded that it is difficult in multi-layer classification. The results of this study are expected to further develop the field of machine learning research on vegetation structure by collecting various vegetation data and image data in the future.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.2
• /
• pp.59-67
• /
• 2015

When planning for streams, adequate and definite flood control should be in the primary consideration of the planner; likewise, flood control is the basic prerequisite for the recent river restoration taking place nationwide. Planning 'safe' streams and rivers that are predictable and controllable begins from accurate survey data. In this research, we will create streams in 3D terrain models and apply them through hydraulic analysis and restoration using smart geospatial information. This process allows the extraction of more accurate data regarding streams and rivers, which makes possible precise hydraulic analysis that is superior in details to the conventional methods. The study also proposes optimal vertical section interval for efficient data processing on hydraulic analysis, applicable when LiDAR data is utilized on hydraulic analysis of urban streams. The study proposes 3D design plan and various applications for spatially planning and restoring rivers and streams.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.3
• /
• pp.255-262
• /
• 2008

Value of natural environment and the importance of conservation are augmented gradually, and collision of environment conservation and development are caused in various construction industries. In this study, Presented practical use way to ecological road design using vegetation information and high precision 3-dimensional geo-spatial data for minimizing pollution. Also, analyzed freezing danger of road surface in winter and direct ray of light danger through simulation of completed road and surrounding environment. And presented road design support way through view analysis.