Processing tree point clouds using Gaussian Mixture Models

While traditionally used for surveying and photogrammetric fields, laser scanning is increasingly being used for a wider range of more general applications. In addition to the issues typically associated with processing point data, such applications raise a number of new complications, such as the c...

Full description

Bibliographic Details
Main Authors: Belton, David, Moncrieff, Simon, Chapman, Jane
Other Authors: M. Scaioni
Format: Conference Paper
Published: ISPRS 2013
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/10188
_version_ 1848746163562348544
author Belton, David
Moncrieff, Simon
Chapman, Jane
author2 M. Scaioni
author_facet M. Scaioni
Belton, David
Moncrieff, Simon
Chapman, Jane
author_sort Belton, David
building Curtin Institutional Repository
collection Online Access
description While traditionally used for surveying and photogrammetric fields, laser scanning is increasingly being used for a wider range of more general applications. In addition to the issues typically associated with processing point data, such applications raise a number of new complications, such as the complexity of the scenes scanned, along with the sheer volume of data. Consequently, automated procedures are required for processing, and analysing such data. This paper introduces a method for modelling multi-modal, geometrically complex objects in terrestrial laser scanning point data; specifically, the modelling of trees. The model method comprises a number of geometric features in conjunction with a multi-modal machine learning technique. The model can then be used for contextually dependent region growing through separating the tree into its component part at the point level. Subsequently object analysis can be performed, for example, performing volumetric analysis of a tree by removing points associated with leaves. The workflow for this process is as follows: isolate individual trees within the scanned scene, train a Gaussian mixture model (GMM), separate clusters within the mixture model according to exemplar points determined by the GMM, grow the structure of the tree, and then perform volumetric analysis on the structure.
first_indexed 2025-11-14T06:28:53Z
format Conference Paper
id curtin-20.500.11937-10188
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:28:53Z
publishDate 2013
publisher ISPRS
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-101882023-02-07T08:01:24Z Processing tree point clouds using Gaussian Mixture Models Belton, David Moncrieff, Simon Chapman, Jane M. Scaioni R. C. Lindenbergh S. Oude Elberink D. Schneider F. Pirotti Laser Scanning Classification Gaussian Mixture Models Principal Component Analysis While traditionally used for surveying and photogrammetric fields, laser scanning is increasingly being used for a wider range of more general applications. In addition to the issues typically associated with processing point data, such applications raise a number of new complications, such as the complexity of the scenes scanned, along with the sheer volume of data. Consequently, automated procedures are required for processing, and analysing such data. This paper introduces a method for modelling multi-modal, geometrically complex objects in terrestrial laser scanning point data; specifically, the modelling of trees. The model method comprises a number of geometric features in conjunction with a multi-modal machine learning technique. The model can then be used for contextually dependent region growing through separating the tree into its component part at the point level. Subsequently object analysis can be performed, for example, performing volumetric analysis of a tree by removing points associated with leaves. The workflow for this process is as follows: isolate individual trees within the scanned scene, train a Gaussian mixture model (GMM), separate clusters within the mixture model according to exemplar points determined by the GMM, grow the structure of the tree, and then perform volumetric analysis on the structure. 2013 Conference Paper http://hdl.handle.net/20.500.11937/10188 10.5194/isprsannals-II-5-W2-43-2013 ISPRS unknown
spellingShingle Laser Scanning
Classification
Gaussian Mixture Models
Principal Component Analysis
Belton, David
Moncrieff, Simon
Chapman, Jane
Processing tree point clouds using Gaussian Mixture Models
title Processing tree point clouds using Gaussian Mixture Models
title_full Processing tree point clouds using Gaussian Mixture Models
title_fullStr Processing tree point clouds using Gaussian Mixture Models
title_full_unstemmed Processing tree point clouds using Gaussian Mixture Models
title_short Processing tree point clouds using Gaussian Mixture Models
title_sort processing tree point clouds using gaussian mixture models
topic Laser Scanning
Classification
Gaussian Mixture Models
Principal Component Analysis
url http://hdl.handle.net/20.500.11937/10188