What type of study is this?

This is a Quantitative Study study.

October 3, 2025SymmetryOpen Access

From Symmetry to Semantics: Improving Heritage Point Cloud Classification with a Geometry-Aware, Uniclass-Informed Taxonomy for Random Forest Implementation in Automated HBIM Modelling

View Full Paper

Ask AI

Bookmark

Authors

This analysis demonstrates improved classification accuracy in heritage structures using a tailored Uniclass taxonomy and machine learning methods.

Classification accuracy improved by 15% with the bespoke taxonomy for the Level 1 classifier, suggesting a potential for better automated workflows.
The proposed method employs a hierarchical random forest model across varying point cloud resolutions of 50 mm, 20 mm, and 5 mm to achieve precision.
Geometric properties and principles of symmetry were considered to refine the taxonomy for heritage buildings, leading to lower misclassification rates.
This research highlights the need for adaptive taxonomies in machine learning applications specifically for heritage architecture.

Gil et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

This analysis demonstrates improved classification accuracy in heritage structures using a tailored Uniclass taxonomy and machine learning methods.