Kiyun Yu

This paper presents a novel approach to retrieve indoor structures from raster images of complicated floor plans. We extract the building elements in the floor plan and process them into a vectorized form to provide indoor layout information. Unlike conventional approaches, the proposed model is robust when recognizing rooms and openings surrounded by obscuring patterns, including superimposed graphics and irregular notation. To this end, we integrate various floor plan formats into a unified st

A critical problem in mapping data is the frequent updating of large data sets. To solve this problem, the updating of small-scale data based on large-scale data is very effective. Various map generalization techniques, such as simplification, displacement, typification, elimination, and aggregation, must therefore be applied. In this study, we focused on the elimination and aggregation of the building layer, for which each building in a large scale was classified as “0-eliminated,” “1-retained,

Automatic floor plan analysis has gained increased attention in recent research. However, numerous studies related to this area are mainly experiments conducted with a simplified floor plan dataset with low resolution and a small housing scale due to the suitability for a data-driven model. For practical use, it is necessary to focus more on large-scale complex buildings to utilize indoor structures, such as reconstructing multi-use buildings for indoor navigation. This study aimed to build a fr

This paper presents a new framework to classify floor plan elements and represent them in a vector format. Unlike existing approaches using image-based learning frameworks as the first step to segment the image pixels, we first convert the input floor plan image into vector data and utilize a graph neural network. Our framework consists of three steps. (1) image pre-processing and vectorization of the floor plan image; (2) region adjacency graph conversion; and (3) the graph neural network on co

산림의 효율적인 관리를 위해 최근 원격탐사 기법을 이용하여 산림에 관련된 정보를 추출하려는 노력들이 활발히 이루어지고 있다. 하지만 단일 원격탐사 데이터를 이용하는 경우 수목 인식의 정확도 및 추출되는 정보의 양적인 면에서 많은 한계를 가진다. 본 연구는 최근의 수목모델링을 위한 핵심기술들을 컬러항공사진과 LiDAR 데이터에 적용하여 국내 환경에서의 수목 모델링을 수행하고, 그 결과를 평가하는데 그 목적을 두고 있다. 대전광역시 내에 존재하는 소규모 산림 지역 중 침엽수만으로 이루어진 단순림을 대상 지역으로 하였다. 컬러항공사진과 LiDAR 데이터를 이용하여 추정된 개체수의 정확도 평가 결과 R2값이 0.77로 나타났다. 수고의 경우 집단 정확도 평가 결과 최근 변화가 일어나지 않은 지역은 측정값과 추정값의 차이가 없는 것으로 나타났고, 개별 정확도 평가의 경우 R2값이 0.83으로 높은 상관도를 보였다.

In recent years, question answering on knowledge bases (KBQA) has emerged as a promising approach for providing unified, user-friendly access to knowledge bases. Nevertheless, existing KBQA systems struggle to answer spatial-related questions, prompting the introduction of geographic knowledge ba se question answering (GeoKBQA) to address such challenges. Current GeoKBQA systems face three primary issues: (1) the limited scale of questions, restricting the effective application of neural network

Demand for a Pedestrian Navigation Service (PNS) is on the rise. To provide a PNS for the transportation of vulnerable people, more detailed information of pedestrian facilities and obstructions should be included in Pedestrian Network Data (PND) used for PNS. Such data can be constructed efficiently by collecting GPS trajectories and integrating them with the existing PND. However, these two kinds of data have geometric differences and topological inconsistencies that need to be addressed. In t

Though the airborne laser scanning (ALS) technique is becoming more popular in many applications, horizontal accuracy of points scanned by the ALS is not yet satisfactory when compared with the accuracy achieved for vertical positions. One of the major reasons is the drift that occurs in the inertial measurement unit (IMU) during the scanning. This paper presents an algorithm that adjusts for the error that is introduced mainly by the drift of the IMU that renders systematic differences between

선진국에서는 폭염이 발생하면 폭염경고시스템을 바탕으로 경보가 발령되며 이에 따른 지방자치단체(지자체)별 행동요령이나 대응 시나리오가 구축되어 있다. 우리나라도 소방방재청에서 수립한 폭염종합대책을 토대로 지자체별로 계획을 세우고 있으나, 폭염경고시스템이나 폭염취약계층에 대한 정의 및 구체적인 대응 시나리오가 마련되어 있지 않다. 이에 본 연구에서 예방 및 대비, 대응, 복구의 재해관리 단계로 나누어 외국의 선진 사례를 분석하고, 우리나라 폭염종합대책의 현황과 문제점을 살펴보았으며 나아가 폭염종합대책의 위상 강화와 내용을 보완하는 운영방안을 도출하였다.

Recently, open-domain question-answering systems have achieved tremendous progress because of developments in large language models (LLMs), and have successfully been applied to question-answering (QA) systems, or Chatbots. However, there has been little progress in open-domain question answering in the geographic domain. Existing open-domain question-answering research in the geographic domain relies heavily on rule-based semantic parsing approaches using few data. To develop intelligent GeoQA

With rapidly widening access to high-capacity geospatial data via high-speed Internet, user demand for multiform and accurate information has increased. Correspondingly, there is a growing need for hybrid map services that can combine heterogeneous data. Conflation, defined as the combining of information from diverse sources so as to reconcile spatial inconsistencies, has emerged to meet that need. In this research, we developed an approach that conflates road maps with aerial images using road