Robust segmentation in laser scanning 3D point cloud data

Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outlier...

Full description

Bibliographic Details
Main Authors: Nurunnabi, Abdul, Belton, David, West, Geoffrey
Other Authors: -
Format: Conference Paper
Published: IEEE eXpress Conference Publishing 2012
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/16069
_version_ 1848749067653349376
author Nurunnabi, Abdul
Belton, David
West, Geoffrey
author2 -
author_facet -
Nurunnabi, Abdul
Belton, David
West, Geoffrey
author_sort Nurunnabi, Abdul
building Curtin Institutional Repository
collection Online Access
description Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outliers. Hence segmentation results can be erroneous and unreliable. The problems of surface segmentation in laser scanning point cloud data are investigated in this paper. We propose a region growing based statistically robust segmentation algorithm that uses a recently introduced fast Minimum Covariance Determinant (MCD) based robust PCA approach. Experiments for several real laser scanning datasets show that PCA gives unreliable and non-robust results whereas the proposed robust PCA based method has intrinsic ability to deal with noisy data and gives more accurate and robust results for planar and non planar smooth surface segmentation.
first_indexed 2025-11-14T07:15:03Z
format Conference Paper
id curtin-20.500.11937-16069
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:15:03Z
publishDate 2012
publisher IEEE eXpress Conference Publishing
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-160692017-11-02T05:47:45Z Robust segmentation in laser scanning 3D point cloud data Nurunnabi, Abdul Belton, David West, Geoffrey - feature extraction robust statistics robust normal region growing outlier covariance technique Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outliers. Hence segmentation results can be erroneous and unreliable. The problems of surface segmentation in laser scanning point cloud data are investigated in this paper. We propose a region growing based statistically robust segmentation algorithm that uses a recently introduced fast Minimum Covariance Determinant (MCD) based robust PCA approach. Experiments for several real laser scanning datasets show that PCA gives unreliable and non-robust results whereas the proposed robust PCA based method has intrinsic ability to deal with noisy data and gives more accurate and robust results for planar and non planar smooth surface segmentation. 2012 Conference Paper http://hdl.handle.net/20.500.11937/16069 10.1109/DICTA.2012.6411672 IEEE eXpress Conference Publishing fulltext
spellingShingle feature extraction
robust statistics
robust normal
region growing
outlier
covariance technique
Nurunnabi, Abdul
Belton, David
West, Geoffrey
Robust segmentation in laser scanning 3D point cloud data
title Robust segmentation in laser scanning 3D point cloud data
title_full Robust segmentation in laser scanning 3D point cloud data
title_fullStr Robust segmentation in laser scanning 3D point cloud data
title_full_unstemmed Robust segmentation in laser scanning 3D point cloud data
title_short Robust segmentation in laser scanning 3D point cloud data
title_sort robust segmentation in laser scanning 3d point cloud data
topic feature extraction
robust statistics
robust normal
region growing
outlier
covariance technique
url http://hdl.handle.net/20.500.11937/16069