Development of an Omnidirectional-Image-Based Data Model through Extending the IndoorGML Concept to an Indoor Patrol Service

Abstract

Different indoor representation methods have been studied for their ability to provide indoor location-based services (LBS). Among them, omnidirectional imaging is one of the most typical and simple methods for representing an indoor space. However, a georeferenced omnidirectional image cannot be used for simple attribute searches, spatial queries, and spatial awareness analyses. To perform these functions, topological data are needed to define the features of and spatial relationships among spatial objects including indoor spaces as well as facilities like CCTV cameras considered in patrol service applications. Therefore, this study proposes an indoor space application data model for an indoor patrol service that can implement functions suited to linking indoor space data and service objects. In order to do this, the study presents a method for linking data between omnidirectional images representing indoor spaces and topological data on indoor spaces based on the concept of IndoorGML. Also, we conduct an experimental implementation of the integrated 3D indoor navigation model for patrol service using GIS data. Based on the results, we evaluate the benefits of using such a 3D data fusion method that integrates omnidirectional images with vector-based topological data models based on IndoorGML for providing indoor LBS in built environments.

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

“…Data fusion techniques aim to bridge this problem, by providing solutions to unify datasets coming from various sources, collected using different sensors or methods, or are based on different data standards, but still provide the same, if not increased, level of information that the individual sources provide. Various approaches have been explored for this purpose, such as data conversion where one data format is exchanged to its counterpart (Teo and Yu, 2017), mapping attributes to develop correspondence between features (Ok et al, 2009), developing a relation model among spatial objects (Lee et al, 2014), or using a reference data to establish relationships (Jung and Lee, 2017).…”

“…To overcome this, Jung and Lee (2017) proposed an Omnidirectional image-based data model by extending the IndoorGML data model by defining an association between the CellSpace class and the Omnidirectional image. This data model was implemented by representing each node in the IndoorGML NRG as an image through a topology authoring tool.…”

“…In this application, however, delivery of object information relies by calculating the image coordinate and comparing this coordinate to a polygon in a reference data. The identified polygon will then be used to select which corresponding Node representing an IndoorGML State, the contained information of which will be displayed to the user (Jung and Lee, 2017). Figure 1.…”

“…Figure 1. Delivery of object information in Omnidirectional image from Topological data through a Reference data (Jung and Lee, 2015) In the same study, the Indoor Patrol Service Platform is built upon the base of discretely-connected omnidirectional images, where each image shows a 360-degree view about a point, so navigating to another location will remove the image from view and load another omnidirectional image (Jung and Lee, 2017). While expressing connectivity between spaces, the corresponding adjacency is not expressed despite being provided by the topological data.…”

“…Data fusion has been used on linking IndoorGML data with another dataset representing indoor space, but this is based on geometric information (Lee et al, 2014), or by using datasets based on other data models (Kim et al, 2013), both of which are not applicable for image data. Omnidirectional images has been linked with topological information from IndoorGML data to provide an indoor patrol service, but this approach used an external reference data that contains attribute information for the indoor spaces and objects (Jung and Lee, 2017).…”