A Framework for Generating IndoorGML Data from Omnidirectional Images

Due to its efficiency and effectiveness, image data is widely used in many fields to express indoor space. Image data has the advantage of providing rich visual elements and having low construction cost. However, most spatial applications built on image data are limited to visualizing the indoor space because combining image with topology data is difficult. Topology data that expresses spatial relationships is essential to provide services such as routing and spatial queries in applications. To overcome those limitation, this study proposes the framework of generating topology data from image data. This paper discusses the methods of capturing image data from indoor space, detecting spatial entities and spatial relationships from omnidirectional images, and generating IndooGML NRG (Node-Relation Graph) data. The methodologies proposed in this study can create topology data using only images without additional data and build topology data at a low cost. Using the suggested framework, we expect to be able to provide a variety of services for more indoor spaces.