Cultural Heritage (CH) assets may be defined as integrated spatial systems composed of inter-connected shapes. The classification and organization of geometries within a hierarchical system are functional to their correct interpretation, which is often performed using 3D point clouds. The recurring shapes recognition becomes a crucial activity, nowadays accelerated by Machine Learning (ML) procedures able to associate semantic meaning to geometric data. An interdisciplinary research team [1] has developed a ML supervised approach, tested on the Milan Cathedral and Pomposa Abbey datasets, which presents an innovative multi–level and multi–resolution classification (MLMR) process. The methodology improves the learning activity and optimizes the 3D classification by a hierarchical concept.
A Hierarchical Machine Learning Approach for Multi-Level and Multi-Resolution 3D Point Cloud Classification
The recent years saw an extensive use of 3D point cloud data for heritage documentation, valorisation and visualisation. Although rich in metric quality, these 3D data lack structured information such as semantics and hierarchy between parts. In this context, the introduction of point cloud classification methods can play an essential role for better data usage, model definition, analysis and conservation. The paper aims to extend a machine learning (ML) classification method with a multi-level and multi-resolution (MLMR) approach. The proposed MLMR approach improves the learning process and optimises 3D classification results through a hierarchical concept. The MLMR procedure is tested and evaluated on two large-scale and complex datasets: the Pomposa Abbey (Italy) and the Milan Cathedral (Italy). Classification results show the reliability and replicability of the developed method, allowing the identification of the necessary architectural classes at each geometric resolution.