• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.197-209
• /
• 2020

Signboards are installed in different types and sizes depending on the shop characteristics. However, the local government is having difficulty managing signboards with frequent opening and closing of stores and insufficient management personnel. In this study, a methodology was proposed to standardize and efficiently manage signboard information. To this end, the signboard display method of the enforcement ordinance related to outdoor advertising was analyzed to define the attribute elements of standard signboard data. In addition, physical information of signboards was obtained through signboard recognition technology, which is a prior study, and attribute elements of signboard standard data were defined through information that can be read with the naked eye, building integration information of the Ministry of the Interior and Safety, and street name address. In order to standardize the signboard information by spatial characteristics, data product specifications and metadata were defined according to the national spatial information standard. Lastly, standard data for signboards were produced in XML (Extensible Markup Language) format for compatibility, and XSD (XML Schema Definition) was defined for XML integrity so that data validity could be verified. Through this, a standard data model for the informatization of signboards was designed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.2
• /
• pp.19-27
• /
• 2011

The objective of this study was to suggest technical approaches for preparation and down scaling of climate data used for predicting the potential forest distribution. To predict the forest distribution, we employed a Korean-specific forest distribution model, so-called the TAG(Thermal Analogy Group), and defined the PFT(Plant Functional Types) based on the HyTAG(Hydrological and Thermal Analogy Group). The climate data with 20km spatial resolution were interpolated to fit on the input data format with 1km spatial resolution. Two potential forest distribution maps were estimated using climate data constructed by kriging, one of the interpolation and down-scaling approaches, with and without lapse rate considered. Through the verification process by comparing two potential maps with the actual vegetation map, the forest distribution using the lapse rate was proven to be 38% more accurate.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.311-315
• /
• 2007

Since the first phase of NGIS (National Geographic Information System) project was launched in 1988, various types and spatial database has been produced and updated. With recent developments in the information technology, the application of spatial data has increased in amount as well as in the coverage of the area of interest. There is a need for production and management of a nationwide single continuous digital map. This paper looks into three problems of map edge matching when dealing with such a task : 1) different scales of adjacent maps, 2) different time of capture between adjacent maps, and 3) different responsible organization where map matching has not been peformed along the boundary.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.10-12
• /
• 2004

Nowadays, with the rapid emergence of XML as a standard for data exchange over the Internet had led to considerable interest In the problem of data management requirements such as the need to store and query XML documents in which the location path languages Xpath is of particular important for XML application since it is a core component of many XML processing standards such as XSLT or XQuery, This parer gives a brief overview about method and design by applying a new spatial-based indexing method namely Xp-free that used for supporting Xpath. Spatial indexing technique has been proved its capacity on searching in large databases. Based on accelerating a node using planar as combined with the numbering schema, we devise efficiently derivative algorithms, which are simple, but useful. Besides that, it also allows to trace all Its relative nodes of context node In a manner supporting queries natural to the types especially Xpath queries with predicates.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.4
• /
• pp.941-949
• /
• 2014

Unit level logistic regression model with mixed effects has been used for estimating small area proportions, which treats the spatial effects as random effects and assumes linearity between the logistic link and the covariates. However, when the functional form of the relationship between the logistic link and the covariates is not linear, it may lead to biased estimators of the small area proportions. In this paper, we relax the linearity assumption and propose two types of kernel-based logistic regression models for estimating small area proportions. We also demonstrate the efficiency of our propose models using simulated data and real data.

• Journal of Korea Multimedia Society
• /
• v.2 no.2
• /
• pp.109-119
• /
• 1999

As the importance and utilization of multimedia data increase, we need to study representing and processing multimedia data within databases. To process multimedia data within databases, we need to precisely model multimedia data, to define data types and operations, and to make up query language supporting them. Therefore, in this paper, we modeled multimedia data using OMT so that we can support multimedia data within databases. We also propose an extended SQL, called MMSQl, which includes new types for supporting multimedia data types and efficiently make a query. Especially, MMSQL provides a mechanism to express temporal and spatial relationships which exist among objects in a multimedia data (internal) or among several multimedia data (external).

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.242-244
• /
• 2004

In this paper, we design and implement an integrated management system for geographic data and vehicular images using a Geographic Information System (GIS). Integrated management of geographic data and vehicular images is very important to manage and to provide them to users effectively because of a large volume of vehicular images. To manipulate these data together, we consider a vehicular image as a polygon which is a type of popular geographic data types. The polygon represents a region in which spatial objects appear the vehicular image.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.203-214
• /
• 2002

This paper presents a physical database design methodology for spatial access structures using transformation techniques in spatial database systems. Recently, many spatial access structures have been proposed in the literature. However, there has been no effort for their physical database design. We first show that most spatial queries in the original space are transformed into one type of range queries in the transform space, and then propose a method for finding the optimal configuration of spatial access structures by using the relationship between the shapes of query regions, that are correspond to the range queries, and page regions, that are correspond to data pages, in the transform space. For performance evaluation, we perform extensive experiments with the MBR-MLGF, a spatial access structure using transformation techniques, using various types of queries and data distributions. The results indicate that our proposed method builds optimal MBR-MLGF according to the query types. When the interval ratio of a transformed four-dimensional query region is 1 : 16 : 256 : 4096, the performance of the proposed method is enhanced by as much as five times over that of the conventional cyclic splitting method. The result confirms that the proposed physical database design methodology is useful in a practical way.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.2
• /
• pp.30-47
• /
• 2022

This study analyzed the characteristics of cold air flow according to spatial types in urban areas of Changwon-si, Gyeongsangnam-do. The spatial types were classified by cluster analysis considering the land use map, building information, and topographic characteristics produced on the Changwon biotope map. The amount of cold air and wind speed were derived by KLAM_21 modeling. As a result, spatial types were classified into a total of 14 types considering the density and height of buildings, land use types, and topographic characteristics. Cold air flow was found to generate cold air in the valley of the forest area outside urban area, move through roads and open spaces, and accumulate in the low-lying national industrial complex, and then spread cold air throughout the urban areas. There was a lot of cold air flow in the tall building area, and the cold air accumulation was less in the slope and ridge areas. The results of this study were able to understand the characteristics of cold air flow according to building density, land use type, and topography, which will be usefully used as basic data for urban wind road construction to mitigate climate and improve air quality in urban areas.