• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.655-661
• /
• 2020

SGM (Semi Global Matching) can be used to find all the conjugate points between stereo images. Therefore, it enables high-density DSM (Digital Surface Model) production from high-resolution satellite images. However, water, shadows, and occlusion areas cause mismatching of the surrounding points in this method. Particularly, in buildings with large-parallax and elongated-shapes such as a Korean style apartment, it is difficult to reconstruct the 3D building even if the SGM method is applied to a high-resolution 50cm satellite image. This study proposed and performed the SGM technique with a classified image and an edge image from the IKONOS-2 satellite stereo-image with a 1m resolution to produce DSM. It was compared with the DSMs from the general SGM and the high-density ABM (Area Based Matching) matching of ERDAS software. The results of the apartment DSM by the proposed method were the best in the test area. As a result, despite the image having a resolution of 1m, the outline of the building DSM could be expressed more clearly than the existing method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.435-444
• /
• 2019

Recently, DL (Deep Learning) has been rapidly applied in various fields. In particular, classification and object recognition from images are major tasks in computer vision. Most of the DL utilizing imagery is primarily based on the CNN (Convolutional Neural Network) and improving performance of the DL model is main issue. While most CNNs are involve with images for training data, this paper aims to classify and recognize objects using DSM (Digital Surface Model), and slope and aspect information derived from the DSM instead of images. The DSM data sets used in the experiment were established by DGPF (German Society for Photogrammetry, Remote Sensing and Geoinformatics) and provided by ISPRS (International Society for Photogrammetry and Remote Sensing). The CNN-based SegNet model, that is evaluated as having excellent efficiency and performance, was used to train the data sets. In addition, this paper proposed a scheme for training data generation efficiently from the limited number of data. The results demonstrated DSM and derived data could be feasible for semantic classification with desirable accuracy using DL.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.405-416
• /
• 2019

Due to the development of information and communication technology, the production and processing speed of data is getting faster. To classify objects using machine learning, which is a field of artificial intelligence, data required for training can be easily collected due to the development of internet and geospatial information technology. In the field of geospatial information, machine learning is also being applied to classify or recognize objects using images and point clouds. In this study, the problem of manually constructing training data using existing digital map version 1.0 was improved, and the technique of classifying roads, buildings and vegetation using image and point clouds were proposed. Through experiments, it was possible to classify roads, buildings, and vegetation that could clearly distinguish colors when using true ortho-image with only RGB (Red, Green, Blue) bands. However, if the colors of the objects to be classified are similar, it was possible to identify the limitations of poor classification of the objects. To improve the limitations, random forest and support vector machine techniques were applied after band fusion of true ortho-image and normalized digital surface model, and roads, buildings, and vegetation were classified with more than 85% accuracy.

• Journal of The Geomorphological Association of Korea
• /
• v.17 no.1
• /
• pp.1-14
• /
• 2010

This paper deals with the classification and distribution of geomorphic surfaces and analysis on effects of geomorphic processes on the landforms in the inaccessable DMZ (Demilitarized Zone) to Wonsan Bay of East Sea coast of Chugaryeong Rift Valley, Central Korea. DEM (Digital Elevation Model) and Landsat images are used for the above anlaysis. The geomorphic surfaces are classified by TPI (Topographical Position Index) for the analysis of the convexity and concavity calculated using topographical elements such as elevation, steepness, and relief. In the Chugayreong Valley, 10 geomorphic surfaces are classified as steep valley, shallow valley, upland drainage, U-shaped valley, plain, open slope, upper slope, local ridge, midslope ridge, and high ridge. Zonal Statistics presents average characteristics of geomorphological processes of surfaces by the relationships between bedrock and relief, surface and relief, and between surface and NDVI. So, these analysis can help to understand geomorphological process such as dissection of lava plateau and watershed divide evolution.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.5 no.1
• /
• pp.43-48
• /
• 1987

The terrain is classified by the parameters-gradient, curuature, bump frequency and the ratio of the surface area to the corresponding planar area- that indicate the quantitative measurement of the terrain roughness, and the terrain is fitted to the polynomial function. According to the terrain roughness, the flat terrain, the gently undulating terrain, the rough terrain are classified The flat terrain, the gently undulating terrain and the rough terrain are fitted to the plane function, the 3th or 5th polynomial function and the 5th polynomial function, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.49-49
• /
• 2018

라오스의 Houay Pano 유역은 상업적 조림으로 인해 2011년부터 2013년까지 급속한 토지이용 변화를 겪어왔다. 본 연구는 이러한 토지이용변화가 박테리아 거동에 어떠한 영향을 주는지 이해하기 위해 Soil and Water Assessment Tool (SWAT) 모형을 활용한 박테리아 거동 모델링을 수행하였다. SWAT 모형은 수치 표고 모델, 토양 특성, 토지 이용 등의 정보를 종합하여, 유역 내수량 및 수질의 변화를 모의할 수 있는 모형으로, 본 연구는 대표적인 분원성 지표 세균 (Fecal Indicator Bacteria)인 대장균 (Escheichia coli, E. coli)을 대상으로 모델링을 수행하였다. SWAT 모형은 지표면 위 박테리아를 1)식물 위, 2)토양 용액상, 3)토양 입자상으로 구분하여 모의한다. 각 상태로 분할된 박테리아는 소멸 (die-off), 씻김 (wash-off), 침투, 표면 유출을 통한 수계로의 이동 등의 단계를 통하여 유역 내에서 거동한다. 본 연구는 서로 다른 기후의 영향을 배제하기 위해 각 토지이용 시나리오를 (2011, 2012, 2013) 실제 기후 조건과 동일 기후(2011-2013 평균) 조건으로 분류하여 분석하였다. 실제 기후 조건에서 SWAT 모형은 표면 유출, 토사 유출, E. coli 거동에 대해 2011년부터 2012년까지 감소, 2012년부터 2013년까지 증가로 모두 동일한 양상을 모의하였다. 이는 강수량의 양상과 동일한 것으로, 강수량이 표면 유출의 양을 결정하고, 달라진 표면 유출에 따라 토사 유출과 E. coli 거동이 결정되기 때문이다. 하지만 동일 기후 조건에서는, E. coli 거동 동인인 표면 유출과 토사 유출이 비교적 일정해짐에 따라, 각 상태로 분할된 박테리아의 초기 부하량값이 E. coli 거동을 결정하는 주된 요인임을 확인 할 수 있었다. 따라서 초기 부하량 분할에 활용되는 엽면적 지수 (Leaf Area Index)와 분배계수 (BACTKDDB)의 정확도가 요구된다. 추가적으로 본 연구는 박테리아의 유입원인 비료 모델링과, LAI를 활용한 박테리아 초기 부하량 산정, 토양 특성 변수와 토지 이용 변수의 분리, 지하수를 통한 박테리아 거동 등을 중심으로 SWAT 모형의 한계점과 개선점을 제시하였으며, 본 연구 결과는 토지이용변화가 박테리아 거동에 주는 영향을 모형적으로 이해하고, 또한 추후 박테리아 모델링 개발에 도움을 줄 것으로 예상된다.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.294-301
• /
• 2022

In this study, a multi-layer cascade (MLC) electrical array configuration method for thermoelectric generator consisting of plural number of thermoelectric modules (TEMs) was proposed to reduce mismatch loss caused by temperature maldistribution on the surfaces of the TEMs. To validate the effect of MLC on the mismatch loss reduction, a numerical model capable of reflecting multi-physics phenomena occuring in the TEMs was developed. MLC can be employed by placing a group of TEMs experiencing relatively low temperature differences in an electric layer with more electrical branches while locating a group of TEMs experiencing relatively high temperature differences in an electric layer with less electrical branches. The TEMs were classified using the temperature distribution obtained by the numerical model. A MLC with an optimal electrical branch ratio showed a 96.5% of electric power generation compared to an ideal case.