• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.451-462
• /
• 2009

The spread of satellite image increases various services using it. Especially, 3D visualization services of the whole earth such as $Google\;Earth^{TM}$ and $Virtual\;Earth^{TM}$ or 3D GIS services for several cities provide realistic geometry information of buildings and terrain of wide areas. These service can be used in the various fields such as urban planning, improvement of roads, entertainment, military simulation and emergency response. The research about extracting the building and terrain information effectively from the high-resolution satellite image is required. In this paper, presents a system for effective extraction of the building model from a single high-resolution satellite image, after examine requirements for building model extraction. The proposed system utilizes geometric features of satellite image and the geometric relationship among the building, the shadow of the building, the positions of the sun and the satellite to minimize user interaction. Finally, after extracting the 3D building, the fact that effective extraction of the model from single high-resolution satellite will be show.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.26 no.3
• /
• pp.52-65
• /
• 1998

It has been recognized that the cityscate identity is a very important factor in a modern city. It is necessary to have a variable view to urban comunities for understanding the cityscape identity. We have investigated the contents of archaic texts such as the geography for tracing a cityscape identity to its origin in a city. Because it has been written about politics, economics and culture of a specific area in the geography based on deep interest to the city, we can look into the early image of the cityscape closely after searching of archaic texts. It is also significant to stdy with archaic texts of geography since these studies have a correlatio to the understand of an area and the keeping of historical conscious which are fundamental of cityscape identity. We have studieds on the area of Cheongju from the middle of Chosun dynasty to the end of this kingdom, since that many geographies were described those days. It was selected "Go-Reo-Sa" and "Se-Jong-Sil-Lok" Geography, "Sin-Jeung-Dong-Guk-Y대-Ji-Seung-Lam" "Dae-Dong-Ji-Ji" "Dong-Guk- Yeo-Ji-Ji", "Jeug-Bo-Mun-Heon-Bi-Go Yeo-Ji-Go", and "Taek-Li-Ji", as archaic texts of geography because these texts described in detail about city and gave a clue to speculate an image of city. The major results are as follows; 1) It was described about the cityscape in those archaic texts are metaphysical image, existing and usable elements of cityscape, lost resources of cityscape. 2) The metaphysical images are neither objective nor consistent in the each archaic texts. But the metaphysical image of old city suggests good insight for the application to the modern city image. 3) It is necessary to the careful onsideration about the existing elements. 4) There are variable programs about the lost resources of the cityscape, in accordance with the possibility of the restoraton. 5) The physical and visible factors and non-physical and invisible factors are equally important elements of the cityscape identity. Our research suggests that it is necessary to understand in detail how those factors of cityscape identity have changed with the changes of the times, and how those factors affect the modern cityscape identity.

• Korean Journal of Environment and Ecology
• /
• v.19 no.4
• /
• pp.375-384
• /
• 2005

This study was conducted selecting 44 places with a block unit subject to urban area in Gangnam-gu, to analyze a temperature change according to land use and green structure. In this study, it was used the broad-wide urban temperature, supported by Landset TM and ETM+ satellite image 6scene(1999${\~}$2002). The result of the research, the land use pattern has slightly influence on a temperature change of urban area. The result from correlation analysis between temperature and the factors affected by land cover type, such as building-to-land ratio(A correlation coefficient is 0.368${\~}$0.709) have positive correlation and green area ratio(a correlation coefficient is -0.551${\~}$-0.860) have negative correlation. The result from correlation analysis between temperature and green capacity of the land, crown projection area ratio, each factor have negative correlation with temperature, as showing that a correlation coefficient of green capacity of the land is -0.577(June 2006)${\~}$-0.882(June 1999) and crown projection area ratio's is -0.549(June 2001)${\~}$-0.817(June 1999). The result of the regression analysis for establishing urban area temperature change prediction model showed that green capacity of the land of the explanation variable was accepted.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.3
• /
• pp.27-35
• /
• 2018

In the mandatory application of the CPTED, only negative parts of urban parks and vegetation were reflected. Therefore, this study tries to present the positive effects of urban parks and vegetation. The purpose of this study is to demonstrate the effects of urban parks and vegetation on crime occurrence and to suggest the planning implications of this to CPTED based on theory related to crime, environmental psychology, and crime occurrence analysis. This study used the crime occurrence data of Seoul, NDVI, population, distance from urban park, floating population, and the like. This study collected data from the Statistics Korea, the local government, and Landsat 8 satellite images provided by the USGS and created data of environmental variables and social variables by district using ArcGIS and statistical program. Literature analysis, correlation analysis, regression analysis, and geographically weighted regression were used to determine the relationship between crime occurrence and environmental variables, and to discuss its implication. It was found that crime occurrence has a relationship with the total population (${\beta}=.663$), the number of amusement facilities (${\beta}=.447$) and the area of a police station jurisdiction (${\beta}=.395$). This confirms that a crime rate is low when the floating population is large (${\beta}=-.241$) and vegetation vitality is high (NDVI, ${\beta}=-.281$). Vegetation vitality (NDVI) is effective in lowering violence through psychological stabilization, strengthening territoriality and improving regional image. The implications for the allocation of urban park and vegetation, program and management plan of urban park and vegetation to reduce crime occurrence have therefore been presented.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2748-2760
• /
• 2018

This paper proposes an audio event classification method based on convolutional neural networks (CNNs). CNN has great advantages of distinguishing complex shapes of image. Proposed system uses the features of audio sound as an input image of CNN. Mel scale filter bank features are extracted from each frame, then the features are concatenated over 40 consecutive frames and as a result, the concatenated frames are regarded as an input image. The output layer of CNN generates probabilities of audio event (e.g. dogs bark, siren, forest). The event probabilities for all images in an audio segment are accumulated, then the audio event having the highest accumulated probability is determined to be the classification result. This proposed method classified thirty audio events with the accuracy of 81.5% for the UrbanSound8K, BBC Sound FX, DCASE2016, and FREESOUND dataset.

• Korean Institute of Interior Design Journal
• /
• v.27 no.1
• /
• pp.132-139
• /
• 2018

The high-rise and high-density apartment complexes are built on a large scale and occupy a large portion of the city. The facade of the apartment has a great influence on the cityscape. In particular, the lower part of apartment design gives people to important impressions. For the harmonious landscape of the city, the color plan emphasizes its importance as an influential visual design element that forms the urban landscape. In specialized apartment design, especially finishing material on lower-parts of apartment which is recognized by pedestrian is more important planning factor. Also, finishing material which is one of the primary design elements is important for making the entire image about the building with color. Nowadays stone is mostly used for specialized design on lower-level in apartments. Stone makes luxurious image and harmonious landscape as a nature material. But when planning for design, only general stone graphic or pictures is used without specific plan, after construction, there is a big difference between a plan and the actual color and image. Thus based on exact understanding of stone, I analyzed current state of expression for stone which is used for lower-parts of apartments in Daegu. By this, the purpose of this study is to present detailed data to offer the basis for planning specialized design of lower-parts of apartment.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.1
• /
• pp.32-43
• /
• 2009

The purpose of this study is to suggest the visual landscape plan for Shinan province with ecological landscape resources, which is comprised of more than 1,000 islands. The plan was done by the order of image plan, landscape structure plan and detained landscape plan. The image of Shinan province was elicited as 'nature', 'complexity' and 'connectivity', by the aspects of planning, cognitive and strategic sides. The landscape zones are planned, such as leisure zone, rural & marine ecological zone and marine tourism zone, and the landscape axes are also set, such as marine axis, ecological axis and circular axis. Especially to conserve the ecological resources, some conservation zones are proposed and design guidelines for each landscape type are also provided, which are not commonly included in the urban landscape plan. Consequently, the landscape plan and ecological environmental plan were complementary to each other. In the detailed landscape plan, more specific plans and design guidelines are suggested for coastal scenery, village and forest scenery, historical and cultural landscape management and promotion. To improve the visual landscape in terms of planning and administrative aspects, the visual landscape plan has become increasingly important for the local governments. The establishment of visual landscape plan may hopefully help to make Shinan province more beautiful and attractive. The landscape plan and ecological environment plan should be integrated, and the further discussion and research are necessary.

• Korean Journal of Remote Sensing
• /
• v.25 no.3
• /
• pp.271-285
• /
• 2009

Multi-temporal satellite imagery can be changed into a transform image that emphasizes the changed area only through the application of various change detection techniques. From the transform image, an automated change detection model calculates the optimal threshold value for classifying the changed and unchanged areas. However, the model can cause undesirable results when the histogram of the transform image is unbalanced. This is because the model uses a single threshold value in which the sign is either positive or negative and its value is constant (e.g. -1, 1), regardless of the imbalance between changed pixels. This paper proposes an advanced method that can improve accuracy by applying separate threshold values according to the increased or decreased range of the changed pixels. It applies multiple threshold values based on the cumulative producer's and user's accuracies in the automated binary change detection model, and the analyst can automatically extract more accurate optimal threshold values. Multi-temporal IKONOS satellite imagery for the Daejeon area was used to test the proposed method. A total of 16 transformation results were applied to the two study sites, and optimal threshold values were determined using accuracy assessment curves. The experiment showed that the accuracy of most transform images is improved by applying multiple threshold values. The proposed method is expected to be used in various study fields, such as detection of illegal urban building, detection of the damaged area in a disaster, etc.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.37-44
• /
• 2019

In this study, we propose the automatic extraction method of Rescue Requests from Drone Images. A central object is extracted from each image by using central object extraction method[7] before classification. A central object in an images are defined as a set of regions that is lined around center of the image and has significant texture distribution against its surrounding. In this case of artificial objects, edge of straight line is often found, and texture is regular and directive. However, natural object's case is not. Such characteristics are extracted using Edge direction histogram energy and texture Gabor energy. The Edge direction histogram energy calculated based on the direction of only non-circular edges. The texture Gabor energy is calculated based on the 24-dimension Gebor filter bank. Maximum and minimum energy along direction in Gabor filter dictionary is selected. Finally, the extracted rescue requestor object areas using the dominant features of the objects. Through experiments, we obtain accuracy of more than 75% for extraction method using each features.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.