Synthesizing Point Cloud Data Set for Historical Dome Systems

Mustafa Cem Güneş*, Alican Mertan, Yusuf H. Sahin, Gozde Unal, Mine Özkar

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

This paper offers a workflow for generating synthetic point cloud data sets to be used in deep learning algorithms in tasks of modeling historical architectural elements. Documentation of cultural heritage is a time-consuming process that requires high precision. Computational and semi-automatic tools enhance conventional methods to shorten the duration of the documentation phase and increase the accuracy of the output. Photogrammetry and laser scanning are how geometrical data is acquired and delivered as a point cloud with position, color, and optionally normal vector information. Segmenting architectural elements based on our interpretations of this data is possible using deep neural networks but is limited when, despite the millions of points from one building, the data is insufficient in terms of variance and quantity. To overcome this limitation, we propose a semi-automatic synthetic data set generation using parametric definitions of historic architectural elements. We create a synthetic dataset, namely the Historical Dome Dataset (HDD), consisting of nearly 1000 dome systems with four semantic classes. We quantitatively and qualitatively analyze the usefulness of the HDD by training a number of modern neural networks on it. Our method of synthesizing point clouds can quickly be adapted into similar cultural heritage projects to prepare relevant data to accurately train deep neural networks and process the collected cultural heritage data.

Original languageEnglish
Title of host publicationComputer-Aided Architectural Design. Design Imperatives
Subtitle of host publicationThe Future is Now - 19th International Conference, CAAD Futures 2021, Selected Papers
EditorsDavid Gerber, Evangelos Pantazis, Biayna Bogosian, Alicia Nahmad, Constantinos Miltiadis
PublisherSpringer Science and Business Media Deutschland GmbH
Pages538-554
Number of pages17
ISBN (Print)9789811912795
DOIs
Publication statusPublished - 2022
Event19th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2021 - Virtual, Online
Duration: 16 Jul 202118 Jul 2021

Publication series

NameCommunications in Computer and Information Science
Volume1465 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference19th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2021
CityVirtual, Online
Period16/07/2118/07/21

Bibliographical note

Publisher Copyright:
© 2022, Springer Nature Singapore Pte Ltd.

Funding

Acknowledgements. This work is supported by TÜB˙TAK (The Scientific and Technological Research Council of Turkey) Project Number: 119K896. A very special thanks to Demircan Tas¸ and Berkay Öztürk for providing photogrammetric data. Lastly, we would like to thank our research group for their valuable discussions.

FundersFunder number
TÜB˙TAK
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu119K896

    Keywords

    • Cultural heritage
    • Deep learning
    • Point clouds
    • Synthetic data set
    • Training data

    Fingerprint

    Dive into the research topics of 'Synthesizing Point Cloud Data Set for Historical Dome Systems'. Together they form a unique fingerprint.

    Cite this