Floor-plan Generation from Noisy Point Clouds

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

10 Downloads (Pure)

Abstract

This paper proposes a growing-based floor-plan generation method that creates the global layout of buildings from noisy point clouds obtained by a stereo camera. We introduce a PCA-based line-growing concept with a subsequent filtering step, which is able to robustly handle the high noise levels in input point clouds. Experimental results show that this method outperforms the state-of-the-art techniques in floor-plan generation. The average score for building layouts has increased from 0.38 to 0.66 on our test dataset, compared to the previous best floor-plan generation method. Furthermore, the resulting floor plans are multiple thousands of times smaller in memory size than the input point clouds, while still preserving the main building structures.

Original languageEnglish
Title of host publicationFifteenth International Conference on Machine Vision (ICMV 2022)
EditorsWolfgang Osten, Dmitry Nikolaev, Jianhong Zhou
PublisherSPIE
Number of pages10
ISBN (Electronic)9781510666191
ISBN (Print)9781510666184
DOIs
Publication statusPublished - 7 Jun 2023
Event15th International Conference on Machine Vision, ICMV 2022 - Rome, Italy
Duration: 18 Nov 202220 Nov 2022
Conference number: 15
http://icmv.org/

Publication series

NameProceedings of SPIE
Volume12701
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference15th International Conference on Machine Vision, ICMV 2022
Abbreviated titleICMV 2022
Country/TerritoryItaly
CityRome
Period18/11/2220/11/22
Internet address

Keywords

  • Floor-plan generation
  • indoor stereo SLAM
  • noisy point cloud filtering

Fingerprint

Dive into the research topics of 'Floor-plan Generation from Noisy Point Clouds'. Together they form a unique fingerprint.

Cite this