Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK

This paper presents an advanced hierarchical classification framework using the Random Forest (RF) algorithm to segment and classify large-scale point clouds of heritage buildings. By integrating the Uniclass classification system into a multi-resolution workflow, the research addresses key challeng...

Full description

Saved in:
Bibliographic Details
Main Authors: Aleksander Gil, Yusuf Arayici
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Heritage
Subjects:
Online Access:https://www.mdpi.com/2571-9408/8/5/147
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258075549696000
author Aleksander Gil
Yusuf Arayici
author_facet Aleksander Gil
Yusuf Arayici
author_sort Aleksander Gil
collection DOAJ
description This paper presents an advanced hierarchical classification framework using the Random Forest (RF) algorithm to segment and classify large-scale point clouds of heritage buildings. By integrating the Uniclass classification system into a multi-resolution workflow, the research addresses key challenges in point cloud classification, including class imbalance, computational constraints, and semantic overlap at coarse resolutions. It adopts an experimental research design using the heritage case study from Royal Greenwich Museum in the UK. The findings demonstrate that industry classification systems and data taxonomies can be aligned with machine learning workflows. This study contributes to Heritage-Building Information Modelling (HBIM) by proposing optimised hierarchical structures and scalable machine learning techniques. The research concludes with recommendations for future research, based on the performance of the Random Forest technique, particularly in further developing AI applications within HBIM.
format Article
id doaj-art-e7e648de642b47988fc5a0dfce333c8f
institution OA Journals
issn 2571-9408
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Heritage
spelling doaj-art-e7e648de642b47988fc5a0dfce333c8f2025-08-20T01:56:16ZengMDPI AGHeritage2571-94082025-04-018514710.3390/heritage8050147Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UKAleksander Gil0Yusuf Arayici1Department of Architecture and Built Environment, Sutherland Building, Northumbria University, Newcastle-upon-Tyne NE1 8ST, UKDepartment of Architecture and Built Environment, Sutherland Building, Northumbria University, Newcastle-upon-Tyne NE1 8ST, UKThis paper presents an advanced hierarchical classification framework using the Random Forest (RF) algorithm to segment and classify large-scale point clouds of heritage buildings. By integrating the Uniclass classification system into a multi-resolution workflow, the research addresses key challenges in point cloud classification, including class imbalance, computational constraints, and semantic overlap at coarse resolutions. It adopts an experimental research design using the heritage case study from Royal Greenwich Museum in the UK. The findings demonstrate that industry classification systems and data taxonomies can be aligned with machine learning workflows. This study contributes to Heritage-Building Information Modelling (HBIM) by proposing optimised hierarchical structures and scalable machine learning techniques. The research concludes with recommendations for future research, based on the performance of the Random Forest technique, particularly in further developing AI applications within HBIM.https://www.mdpi.com/2571-9408/8/5/147HBIMpoint cloudsemantic segmentationclassificationmachine learningdeep learning
spellingShingle Aleksander Gil
Yusuf Arayici
Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
Heritage
HBIM
point cloud
semantic segmentation
classification
machine learning
deep learning
title Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
title_full Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
title_fullStr Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
title_full_unstemmed Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
title_short Point Cloud Segmentation Based on the Uniclass Classification System with Random Forest Algorithm for Cultural Heritage Buildings in the UK
title_sort point cloud segmentation based on the uniclass classification system with random forest algorithm for cultural heritage buildings in the uk
topic HBIM
point cloud
semantic segmentation
classification
machine learning
deep learning
url https://www.mdpi.com/2571-9408/8/5/147
work_keys_str_mv AT aleksandergil pointcloudsegmentationbasedontheuniclassclassificationsystemwithrandomforestalgorithmforculturalheritagebuildingsintheuk
AT yusufarayici pointcloudsegmentationbasedontheuniclassclassificationsystemwithrandomforestalgorithmforculturalheritagebuildingsintheuk