Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation
With the development of 3D sensors, 3D point cloud data can now be obtained conveniently. Therefore, it is crucial to process point cloud data automatically. Region growing is a commonly used algorithm to segment point clouds, which greatly depends on the accuracy of points’ normals and r...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10108962/ |
_version_ | 1797805888497516544 |
---|---|
author | Wei Wang Yi Zhang Gengyu Ge Qin Jiang Yang Wang Lihe Hu |
author_facet | Wei Wang Yi Zhang Gengyu Ge Qin Jiang Yang Wang Lihe Hu |
author_sort | Wei Wang |
collection | DOAJ |
description | With the development of 3D sensors, 3D point cloud data can now be obtained conveniently. Therefore, it is crucial to process point cloud data automatically. Region growing is a commonly used algorithm to segment point clouds, which greatly depends on the accuracy of points’ normals and requires tuning two thresholds; i.e., the increment of curvature (<inline-formula> <tex-math notation="LaTeX">$\sigma _{th}$ </tex-math></inline-formula>) and normal angles (<inline-formula> <tex-math notation="LaTeX">$\theta _{th}$ </tex-math></inline-formula>). In this paper, we improve the region growing algorithm in two ways: Accurate normal estimation and strengthening the region growing criteria. For the first aspect, principal component analysis (PCA) is utilized to estimate the initial normals of the point cloud. Then, the points are divided into regular points (RP) and sharp feature points (SFP), according to their initial normals. A robust estimator-based PCA is then applied to refine the SFP normals. For the latter aspect, non-connected and non-coplanar points are detected and ignored when region grows. Finally, the segmentation performance of the proposed method is evaluated using internal and external indices. The results indicate that the proposed method can accurately estimate the point normals within an acceptable time, and obtain a better result than the classic PCA-based region growing algorithm and advanced DetMM-based methods. |
first_indexed | 2024-03-13T05:58:56Z |
format | Article |
id | doaj.art-656f4bcf130b4fb4a05b1e4f6e1083f2 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-13T05:58:56Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-656f4bcf130b4fb4a05b1e4f6e1083f22023-06-12T23:02:14ZengIEEEIEEE Access2169-35362023-01-0111425104252010.1109/ACCESS.2023.327070910108962Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal EstimationWei Wang0https://orcid.org/0000-0002-7610-0126Yi Zhang1https://orcid.org/0009-0007-1768-0566Gengyu Ge2Qin Jiang3Yang Wang4Lihe Hu5College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaWith the development of 3D sensors, 3D point cloud data can now be obtained conveniently. Therefore, it is crucial to process point cloud data automatically. Region growing is a commonly used algorithm to segment point clouds, which greatly depends on the accuracy of points’ normals and requires tuning two thresholds; i.e., the increment of curvature (<inline-formula> <tex-math notation="LaTeX">$\sigma _{th}$ </tex-math></inline-formula>) and normal angles (<inline-formula> <tex-math notation="LaTeX">$\theta _{th}$ </tex-math></inline-formula>). In this paper, we improve the region growing algorithm in two ways: Accurate normal estimation and strengthening the region growing criteria. For the first aspect, principal component analysis (PCA) is utilized to estimate the initial normals of the point cloud. Then, the points are divided into regular points (RP) and sharp feature points (SFP), according to their initial normals. A robust estimator-based PCA is then applied to refine the SFP normals. For the latter aspect, non-connected and non-coplanar points are detected and ignored when region grows. Finally, the segmentation performance of the proposed method is evaluated using internal and external indices. The results indicate that the proposed method can accurately estimate the point normals within an acceptable time, and obtain a better result than the classic PCA-based region growing algorithm and advanced DetMM-based methods.https://ieeexplore.ieee.org/document/10108962/Normal estimationregion growingPCArobust estimatorpoint cloud segmentation |
spellingShingle | Wei Wang Yi Zhang Gengyu Ge Qin Jiang Yang Wang Lihe Hu Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation IEEE Access Normal estimation region growing PCA robust estimator point cloud segmentation |
title | Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation |
title_full | Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation |
title_fullStr | Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation |
title_full_unstemmed | Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation |
title_short | Indoor Point Cloud Segmentation Using a Modified Region Growing Algorithm and Accurate Normal Estimation |
title_sort | indoor point cloud segmentation using a modified region growing algorithm and accurate normal estimation |
topic | Normal estimation region growing PCA robust estimator point cloud segmentation |
url | https://ieeexplore.ieee.org/document/10108962/ |
work_keys_str_mv | AT weiwang indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation AT yizhang indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation AT gengyuge indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation AT qinjiang indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation AT yangwang indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation AT lihehu indoorpointcloudsegmentationusingamodifiedregiongrowingalgorithmandaccuratenormalestimation |