Comparing Machine and Deep Learning Methods for Large 3D Heritage Semantic Segmentation

• Published in: ISPRS international journal of geo-information Vol. 9; no. 9; p. 535
• Main Authors: Matrone, Francesca, Grilli, Eleonora, Martini, Massimo, Paolanti, Marina, Pierdicca, Roberto, Remondino, Fabio
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2020
• Subjects: Algorithms; Annotations; Architectural elements; Architecture; Artificial intelligence; Case studies; Classification; computer vision; Cultural heritage; Cultural resources; data collection; Datasets; Deep learning; digital cultural heritage; digital images; Historic sites; image analysis; Image segmentation; Lasers; Learning algorithms; lidar; Machine learning; Masonry; Methods; Photogrammetry; point clouds; Semantic segmentation; Semantics; Three dimensional models; Italy
• ISSN: 2220-9964; 2220-9964
• DOI: 10.3390/ijgi9090535

In recent years semantic segmentation of 3D point clouds has been an argument that involves different fields of application. Cultural heritage scenarios have become the subject of this study mainly thanks to the development of photogrammetry and laser scanning techniques. Classification algorithms based on machine and deep learning methods allow to process huge amounts of data as 3D point clouds. In this context, the aim of this paper is to make a comparison between machine and deep learning methods for large 3D cultural heritage classification. Then, considering the best performances of both techniques, it proposes an architecture named DGCNN-Mod+3Dfeat that combines the positive aspects and advantages of these two methodologies for semantic segmentation of cultural heritage point clouds. To demonstrate the validity of our idea, several experiments from the ArCH benchmark are reported and commented.