Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences
Semantically rich indoor models are increasingly used throughout a facility’s life cycle for different applications. With the decreasing price of 3D sensors, it is convenient to acquire point cloud data from consumer-level scanners. However, most existing methods in 3D indoor reconstructio...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/3/533 |
_version_ | 1811278485078933504 |
---|---|
author | Shengjun Tang Yunjie Zhang You Li Zhilu Yuan Yankun Wang Xiang Zhang Xiaoming Li Yeting Zhang Renzhong Guo Weixi Wang |
author_facet | Shengjun Tang Yunjie Zhang You Li Zhilu Yuan Yankun Wang Xiang Zhang Xiaoming Li Yeting Zhang Renzhong Guo Weixi Wang |
author_sort | Shengjun Tang |
collection | DOAJ |
description | Semantically rich indoor models are increasingly used throughout a facility’s life cycle for different applications. With the decreasing price of 3D sensors, it is convenient to acquire point cloud data from consumer-level scanners. However, most existing methods in 3D indoor reconstruction from point clouds involve a tedious manual or interactive process due to line-of-sight occlusions and complex space structures. Using the multiple types of data obtained by RGB-D devices, this paper proposes a fast and automatic method for reconstructing semantically rich indoor 3D building models from low-quality RGB-D sequences. Our method is capable of identifying and modelling the main structural components of indoor environments such as space, wall, floor, ceilings, windows, and doors from the RGB-D datasets. The method includes space division and extraction, opening extraction, and global optimization. For space division and extraction, rather than distinguishing room spaces based on the detected wall planes, we interactively define the start-stop position for each functional space (e.g., room, corridor, kitchen) during scanning. Then, an interior elements filtering algorithm is proposed for wall component extraction and a boundary generation algorithm is used for space layout determination. For opening extraction, we propose a new noise robustness method based on the properties of convex hull, octrees structure, Euclidean clusters and the camera trajectory for opening generation, which is inapplicable to the data collected in the indoor environments due to inevitable occlusion. A global optimization approach for planes is designed to eliminate the inconsistency of planes sharing the same global plane, and maintain plausible connectivity between the walls and the relationships between the walls and openings. The final model is stored according to the CityGML3.0 standard. Our approach allows for the robust generation of semantically rich 3D indoor models and has strong applicability and reconstruction power for complex real-world datasets. |
first_indexed | 2024-04-13T00:36:45Z |
format | Article |
id | doaj.art-81c4f983184b45d995099dc0fb8e7e10 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-13T00:36:45Z |
publishDate | 2019-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-81c4f983184b45d995099dc0fb8e7e102022-12-22T03:10:18ZengMDPI AGSensors1424-82202019-01-0119353310.3390/s19030533s19030533Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D SequencesShengjun Tang0Yunjie Zhang1You Li2Zhilu Yuan3Yankun Wang4Xiang Zhang5Xiaoming Li6Yeting Zhang7Renzhong Guo8Weixi Wang9Research Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaState Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430000, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaState Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430000, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaResearch Institute for Smart Cities & Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, School of Architecture and Urban Planning, Shenzhen University, Shenzhen 518060, ChinaSemantically rich indoor models are increasingly used throughout a facility’s life cycle for different applications. With the decreasing price of 3D sensors, it is convenient to acquire point cloud data from consumer-level scanners. However, most existing methods in 3D indoor reconstruction from point clouds involve a tedious manual or interactive process due to line-of-sight occlusions and complex space structures. Using the multiple types of data obtained by RGB-D devices, this paper proposes a fast and automatic method for reconstructing semantically rich indoor 3D building models from low-quality RGB-D sequences. Our method is capable of identifying and modelling the main structural components of indoor environments such as space, wall, floor, ceilings, windows, and doors from the RGB-D datasets. The method includes space division and extraction, opening extraction, and global optimization. For space division and extraction, rather than distinguishing room spaces based on the detected wall planes, we interactively define the start-stop position for each functional space (e.g., room, corridor, kitchen) during scanning. Then, an interior elements filtering algorithm is proposed for wall component extraction and a boundary generation algorithm is used for space layout determination. For opening extraction, we propose a new noise robustness method based on the properties of convex hull, octrees structure, Euclidean clusters and the camera trajectory for opening generation, which is inapplicable to the data collected in the indoor environments due to inevitable occlusion. A global optimization approach for planes is designed to eliminate the inconsistency of planes sharing the same global plane, and maintain plausible connectivity between the walls and the relationships between the walls and openings. The final model is stored according to the CityGML3.0 standard. Our approach allows for the robust generation of semantically rich 3D indoor models and has strong applicability and reconstruction power for complex real-world datasets.https://www.mdpi.com/1424-8220/19/3/533mobile mappingindoor reconstructiongeometric computationpoint cloudspace partition |
spellingShingle | Shengjun Tang Yunjie Zhang You Li Zhilu Yuan Yankun Wang Xiang Zhang Xiaoming Li Yeting Zhang Renzhong Guo Weixi Wang Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences Sensors mobile mapping indoor reconstruction geometric computation point cloud space partition |
title | Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences |
title_full | Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences |
title_fullStr | Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences |
title_full_unstemmed | Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences |
title_short | Fast and Automatic Reconstruction of Semantically Rich 3D Indoor Maps from Low-quality RGB-D Sequences |
title_sort | fast and automatic reconstruction of semantically rich 3d indoor maps from low quality rgb d sequences |
topic | mobile mapping indoor reconstruction geometric computation point cloud space partition |
url | https://www.mdpi.com/1424-8220/19/3/533 |
work_keys_str_mv | AT shengjuntang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT yunjiezhang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT youli fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT zhiluyuan fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT yankunwang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT xiangzhang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT xiaomingli fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT yetingzhang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT renzhongguo fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences AT weixiwang fastandautomaticreconstructionofsemanticallyrich3dindoormapsfromlowqualityrgbdsequences |