Machine Learning Generalisation across Different 3D Architectural Heritage

Abstract

The use of machine learning techniques for point cloud classification has been investigated extensively in the last decade in the geospatial community, while in the cultural heritage field it has only recently started to be explored. The high complexity and heterogeneity of 3D heritage data, the diversity of the possible scenarios, and the different classification purposes that each case study might present, makes it difficult to realise a large training dataset for learning purposes. An important practical issue that has not been explored yet, is the application of a single machine learning model across large and different architectural datasets. This paper tackles this issue presenting a methodology able to successfully generalise to unseen scenarios a random forest model trained on a specific dataset. This is achieved looking for the best features suitable to identify the classes of interest (e.g., wall, windows, roof and columns).

A Hierarchical Machine Learning Approach for Multi-Level and Multi-Resolution 3D Point Cloud Classification

“…Starting from these considerations, the developed classification method uses a Random Forest (RF) classifier [54], following the successful supervised approach based on geometric features introduced in [34] and the study on features importance in Random Forest [20,33]. Compared to DL approaches, RF methods do not need a significant amount of manually annotated datasets to be effective.…”

“…The method iteratively extracts the most relevant features considering a set of geometric characteristics strictly related to the architectural element dimensions. The same author has then verified the possibility to generalise the classification model across different architectural scenarios in [34].…”

Unsupervised Object-Based Clustering in Support of Supervised Point-Based 3d Point Cloud Classification

“…This paper aims at an easy-to-implement and user-friendly supervised method generalisable to several contexts and domains. To achieve this, we explore how unsupervised objectbased features (Poux and Billen, 2019;Poux and Ponciano, 2020) can help a supervised point-based classification (Grilli et al, 2019;Grilli and Remondino, 2020). The goal is to combine two different classification approaches to maximise results' accuracy, minimise human efforts and deliver a 3D classification method that is case-and context-independent while usable by non-experts.…”

“…Our idea is that, when training is not available, the training's size should be as limited as possible and the annotation step rapid and user friendly. • Train a standard machine learning algorithm: based on previous performance analysis (Grilli et al, 2019;Grilli and Remondino, 2020;Matrone et al, 2020), we selected the widely known Random Forest classifier (Breinman, 2001) among different classifiers available in the literature (SVM, Decision tree, etc.). • Assess the achieved point-wise classification outcomes through quality metrics extracted for the entire test set: among the several metrics existing in the literature (Goutte and Gaussier, 2005), the Overall Accuracy (OA) is used to evaluate the classifier's ability to predict labels based on all observations.…”

Enhancing City Sustainability through Smart Technologies: A Framework for Automatic Pre-Emptive Action to Promote Safety and Security Using Lighting and ICT-Based Surveillance

“…Promising examples can be found for artificial intelligence (AI)-enabled building information modelling (BIM), architectural elements analysis, defect detection, materials engineering, smart furniture, etc. [21][22][23][24][25]. Coupling imaging data with field surveys, Xu et al introduced a machine-learning-based evaluation of land usage and defective policies based on the discrepancy between detected and simulated urbanizations.…”