Redirigiendo al acceso original de articulo en 17 segundos...
ARTÍCULO
TITULO

Framework for Indoor Elements Classification via Inductive Learning on Floor Plan Graphs

Jaeyoung Song and Kiyun Yu    

Resumen

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 converted floor plan graphs. Our approach is able to capture different types of indoor elements including basic elements, such as walls, doors, and symbols, as well as spatial elements, such as rooms and corridors. In addition, the proposed method can also detect element shapes. Experimental results show that our framework can classify indoor elements with an F1 score of 95%, with scale and rotation invariance. Furthermore, we propose a new graph neural network model that takes the distance between nodes into account, which is a valuable feature of spatial network data.

 Artículos similares

       
 
Yang Dong, Jiaxuan Song, Dazhao Fan, Song Ji and Rong Lei    
In the field of geoinformation science, multiview, image-based 3D city modeling has developed rapidly, and image depth estimation is an important step in it. To address the problems of the poor adaptability of training models of existing neural network m... ver más

 
Sajal Chowdhury, Masa Noguchi and Hemanta Doloi    
Bangladesh is an emerging nation that is urbanizing the fastest. Generally, middle-income families (as the main economic contributors) reside in high-density urban housing due to their socioeconomic disparities in Dhaka, Bangladesh, where physical design... ver más
Revista: Buildings

 
Yueyong Pang, Lizhi Miao, Liangchen Zhou and Guonian Lv    
Indoor space is a core part of supporting indoor applications. Most of the existing indoor space models are expressed from three space scales: building, floor, and room, and the granularity is not fine enough, lacking the expression of each functional su... ver más

 
Zebiao Shao, Bo Wang, Yao Xu, Liang Sun, Xichen Ge, Lvpei Cai and Cheng Chang    
Building skin can provide comprehensive functions of energy production, daylighting, and shading with an integrated transmissive solar-concentrating panel. In this study, Rhino Grasshopper parametric modeling, Ladybug tool performance simulation, and Oct... ver más
Revista: Buildings

 
António Figueiredo, Filipe Rebelo, António Samagaio, Romeu Vicente and Jorge Lira    
Improving the energy efficiency of new and existing building stock while fostering the use of renewable energy is one of the major goals of the Renovation Wave initiative promoted by the European Union. In this framework, the present research focuses on ... ver más
Revista: Infrastructures