Learning Functional Properties of Rooms in Indoor Space from Point Cloud Data: A Deep Learning Approach

Guoray Cai, Yimu Pan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

This paper presents a method to derive functional labels of rooms from the spatial configuration of room objects detected from 3D point clouds representation. The method was inspired by the intuition that spatial configuration of room objects has intimate link with the intended functional purposes. To explore the possibility of inferring the room usage information from its spatial configuration, we designed and trained a deep learning model to learn the important features of spatial configuration of room scenes and examined the predictive power of the model in inferring room usage. We present an experiment on using the model to to predict room function category on Standford 3D (S3DIS) dataset, and achieved reasonable performance. Analysis of accuracy and confusion rates allows us to draw a number insight on the separability of rooms among top level categories (such as offices, conference rooms, lounge, hallways, and storage rooms). Our findings suggested that our method is promising, with an accuracy of 91.8% on predicting room function categories. Future work should further validate and refine our method using data with more balanced training samples on the range of room types as they become available.

Original languageEnglish (US)
Title of host publication29th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2021
EditorsXiaofeng Meng, Fusheng Wang, Chang-Tien Lu, Yan Huang, Shashi Shekhar, Xing Xie
PublisherAssociation for Computing Machinery
Pages350-353
Number of pages4
ISBN (Electronic)9781450386647
DOIs
StatePublished - Nov 2 2021
Event29th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2021 - Virtual, Online, China
Duration: Nov 2 2021Nov 5 2021

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference

Conference29th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2021
Country/TerritoryChina
CityVirtual, Online
Period11/2/2111/5/21

All Science Journal Classification (ASJC) codes

  • Earth-Surface Processes
  • Computer Science Applications
  • Modeling and Simulation
  • Computer Graphics and Computer-Aided Design
  • Information Systems

Fingerprint

Dive into the research topics of 'Learning Functional Properties of Rooms in Indoor Space from Point Cloud Data: A Deep Learning Approach'. Together they form a unique fingerprint.

Cite this