http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
IndoorGML-based Topological Data Generation from Omnidirectional Images
Claridades, Alexis Richard(알랙시스 리차드 클라리다데스),Lee, Jiyeong(이지영),Blanco, Ariel(아리옐블랑코) 한국측량학회 2019 한국측량학회 학술대회자료집 Vol.2019 No.4
As applications for spatial information move towards navigation indoors, the need to generate 3D data for this purpose have been gaining attention. However, most available methodologies for generating 3D spatial data require expensive sensors, or complex methodologies involving computationally-heavy data. This study aims to present a methodology to generate a 3D Topological Model based on IndoorGML (Indoor Geographic Markup Language) from omnidirectional images taken along a building’s interior. Using a camera, fisheye lens and a rotator setup, images were taken along Shooting Points in the corridors with relative positions obtained from the floor plan. From the images, doors that indicate presence of indoor spaces were identified from the images, and 3D node-relation graphs representing adjacency, connectivity and accessibility were generated.
Using Omnidirectional Images for Semi-Automatically Generating IndoorGML Data
Claridades, Alexis Richard,이지영,Blanco, Ariel 한국측량학회 2018 한국측량학회지 Vol.36 No.5
As human beings spend more time indoors, and with the growing complexity of indoor spaces, more focus is given to indoor spatial applications and services. 3D topological networks are used for various spatial applications that involve navigation indoors such as emergency evacuation, indoor positioning, and visualization. Manually generating indoor network data is impractical and prone to errors, yet current methods in automation need expensive sensors or datasets that are difficult and expensive to obtain and process. In this research, a methodology for semi-automatically generating a 3D indoor topological model based on IndoorGML (Indoor Geographic Markup Language) is proposed. The concept of Shooting Point is defined to accommodate the usage of omnidirectional images in generating IndoorGML data. Omnidirectional images were captured at selected Shooting Points in the building using a fisheye camera lens and rotator and indoor spaces are then identified using image processing implemented in Python. Relative positions of spaces obtained from CAD (ComputerAssisted Drawing) were used to generate 3D node-relation graphs representing adjacency, connectivity, and accessibility in the study area. Subspacing is performed to more accurately depict large indoor spaces and actual pedestrian movement. Since the images provide very realistic visualization, the topological relationships were used to link them to produce an indoor virtual tour.
Developing a Strategy for Integrating Network Datasets for Supporting Multimodal Transportation
Alexis Richard C. Claridades,Jiyeong Lee 한국측량학회 2023 한국측량학회지 Vol.41 No.6
As urban areas have been undergoing accelerated development, there has also been increasing interest in solving problems in mobility. Experts have identified multimodal transportation as a key concept in addressing this problem by providing transportation options. In providing LBS (Location-based Services), spatial datasets, particularly network data, are essential in representing the navigable spaces for each mode of transportation. However, previous studies on spatial data modeling of multimodal transportation have omitted the spaces that exist between the spaces represented by such network data. Additionally, the integration of these datasets for providing such services is still faced with numerous problems, such as lack of specification, the variety in data formats, potential difficulties in data conversion, or computational burdens due to reliance on geometric properties. This paper proposes a method for integrating network datasets to represent the connectivity of various navigable spaces for supporting multimodal transportation based on topological relationships, described in a spatial data model expressed in UML (Unified Modeling Language). Moreover, using sample data, we demonstrate the models potential for representing seamless travel across transportation modes in a routing experiment. This paper presents a topological relationship-based method to integrate existing network data representing multimodal transportation despite the differences in data format or standard.
Alexis Richard C. Claridades,최현상,이지영 한국측량학회 2023 한국측량학회지 Vol.41 No.5
Spatial data is important for virtually representing the real world and is essential in developing applications for making informed decisions. With the growing interest in seamless indoor-outdoor environments, spatial data from different sources exists in various formats for use in LBS (Location-Based Services). Previous research has utilized deep learning for indoor omnidirectional images to generate NRS (Node-Relation Structure), a network-based topological data, for supporting spatial analysis for navigation while providing visualization. This study proposes an approach to detect building entrances in street view omnidirectional images through a deep learning-based object detection algorithm for supporting indoor-outdoor LBS. This paper focuses on formulating refinement conditions for constructing an image training dataset that combines both an open dataset and directly captured omnidirectional images to address the challenge of establishing a huge volume of images for training the object detection model. By applying the conditions, the mAP (mean Average Precision) of 61.20% obtained from training with open data increased to 85.72%, and applying image augmentation methods improved the mAP to 87.42%. These results show that the proposed conditions can be used as a framework for constructing generalized training data that results in accurate entrance detection in street view images, regardless of the study area.
스키마 맵핑을 이용한 실내공간 데이터모델 비교분석 연구
김미선(Kim, Misun),박인혜(Park, Inhye),알렉시스 리차드 클라리데스(Claridades, Alexis Richard),이지영(Lee, Jiyeong) 한국측량학회 2021 한국측량학회 학술대회자료집 Vol.2021 No.11
세계적으로 디지털 트윈, 매타버스 등이 유행하고 있다. 공간정보 데이터는 가상현실 구축에 핵심적인 데이터이나, 기구축된 공간 데이터는 가상공간 구현에 곧바로 사용될 수 없다. 이를 위해서는 공간 데이터의 통합 활용이 선행되어야 한다. 데이터 통합 활용을 위한 기존 연구들은 데이터 변환에 치중되어 있었다. 변환법은 기초적이고 편리한 방법이나 변환 시 정보의 누락이 불가피하다는 한계가 있다. 변환 사용의 한계점을 극복하면서 근본적으로 문제를 해결할 방안은 데이터모델 표준화 작업이다. 본 연구는 실내공간 모델링에 보편적으로 사용되는 데이터모델의 비교분석을 통해 실내공간 피처 모델 표준화 작업에 가이드라인을 제시한다. 실내공간 모델링에 보편적으로 사용되는 다섯 가지 모델을 스키마 맵핑 기법을 이용하여 비교하고 모델들이 공통적으로 포함하는 요소와 피처 클래스를 파악한다.