Developing a Method to Generate Indoorgml Data From the Omni-Directional Image

Kim, M.; Lee, Jiyeong

doi:10.5194/isprsarchives-xl-2-w4-17-2015

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Popular web maps such as Google Street View (Google, 2018) have used omnidirectional images to represent outdoor transportation networks for visualization, as well as interiors of major public areas (Daum, 2018;Google, 2018). Its implementation in generating IndoorGML-based topological data has been through the identification of spaces in the image through methods such as image filtering and classification (Kim et al, 2016;Kim and Lee, 2015), and through a moving window approach (Claridades et al, 2018). In both approaches, the IndoorGML notion of indoor space are applied first on how the images are collected along the interior, say at Shooting Points (Claridades et al, 2018), and how their respective topological relationships among each other are defined, the latter elaborating more on generating specific NRGs.…”

Section: Related Studiesmentioning

confidence: 99%

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

Claridades

Ahn

Lee

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

As the interest in indoor spaces increases, there is a growing need for indoor spatial applications. As these spaces grow in complexity and size, research is being carried out towards effective and efficient representation. Omnidirectional images give a snapshot of interiors and give visually rich content, but only contain pixel data. For it to be used in providing indoor services, its limitations must be overcome. First, the images must be connected to each other to represent indoor space continuously based on spatial relationships that may be provided by topological data. Second, the objects and spaces that we see in these images must also be recognized. This paper presents a study on how to link omnidirectional images and an IndoorGML data without the need for data conversion, provision of reference data, or use of different data models in order to provide Indoor Location-Based Service (LBS). We introduce the use of the Spatial Extended Point (SEP) to characterize the relationship between the omnidirectional image and the topological data. Position information of the object is used to define a region of 3D space, to determine the inclusion relationship of an IndoorGML node. We conduct an experimental implementation of the integrated data in the form of a 3D Virtual Tour. The connection of the Omnidirectional images is demonstrated by a visualization of navigation through a hallway towards a room's interior delivered to the user through a clicking action on the image.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

Claridades

Ahn

Lee

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…These services form part of the core requirement of Smart Cities, as localities around the world aim to establish seamless integration of technology to the daily life of its citizens. Now, as interest in indoor space continues to rise [5], the demand for spatial applications and services also increases. These technologies that signal that we are now living in a digital world spark interest in digitizing real-world indoor scenes [6].…”

Section: Introductionmentioning

confidence: 99%

Developing a Data Model of Indoor Points of Interest to Support Location-Based Services

Claridades

Lee

2020

Journal of Sensors

View full text Add to dashboard Cite

Focus on indoor spatial applications has been rising with the growing interest in indoor spaces. Along with the widespread use of mobile devices and the internet, it has increased demands for indoor location-based services (LBS), demanding more efficient representation and management of indoor spatial data. Indoor points of interest (Indoor POI) data, representing both spaces and facilities located indoors, provide the infrastructure for these services. These datasets are vital in delivering timely and accurate information to users, such as in cases of managing indoor facilities. However, even though there are studies that explore its use across applications and efforts exerted towards the standardization of the data model, most POI development studies have focused on the outdoors and remain underdeveloped in the indoors. In this paper, we propose a spatial-temporal Indoor POI data model to provide direction for the establishment of indoor POI data and to address limitations in currently available data specifications. By exploring how different Indoor POIs are from its outdoor counterparts, particularly on extending its outdoor counterparts’ functions on searching, sharing, and labeling, we describe the data model and its components using the Unified Modeling Language (UML). We perform an SQL-based query experiment to demonstrate the potential use of the data model using sample data.

show abstract

“…In that context, (Hwang et al, 2012) developed an editor and a viewer for IndoorGML to mainly support related researches, concerned about representation methods for 2D and 3D indoor space and connection method between indoor and outdoor. Semi-automatic methods to generate IndoorGML data from images is presented in (Kim and Lee, 2015). The authors relied on image segmentation and classification methods to identify specific features such as doors and extract the corresponding connectivity graph with indoor spaces such as corridors.…”

Section: Related Workmentioning

confidence: 99%

About the Subdivision of Indoor Spaces in Indoorgml

Diakité

Zlatanova

Joune

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Boosted by the dynamic urbanization of cities, indoor environments are getting more and more complex in order to be able to host people properly. While most of our time is spent inside buildings, the need of GIS tools to assist our daily activities that can become tedious, such as indoor navigation or facility management, became more and more urgent. In that perspective, the IndoorGML standard is aiming to address the gaps left by other standards regarding the spatial modelling for indoor navigation. It includes several concepts such as the organization of the spaces into cells along with their network representation and the possibility to represent multiple connected layers. However, being at its first stage, several concepts of the standard could be improved. One of these is the cell subspacing that is not enough discussed in the current version of the standard. In this paper, we explore all the aspects involved in the subdivision process, from the identification of the navigable and non-navigable space cells to the generation of a navigation graph. We propose several criteria on which the indoor sub-spacing can rely to be automatically performed and and illustrate them on a 3D indoor model.

show abstract

Developing a Method to Generate Indoorgml Data From the Omni-Directional Image

Cited by 7 publications

References 9 publications

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

Developing a Data Model of Indoor Points of Interest to Support Location-Based Services

About the Subdivision of Indoor Spaces in Indoorgml

Contact Info

Product

Resources

About