The Development of a Framework for the Automated Translation of Sketch-Based Data into BIM Models
Autor(en): |
WoonSeong Jeong
ByungChan Kong Manik Das Adhikari Sang-Guk Yum |
---|---|
Medium: | Fachartikel |
Sprache(n): | Englisch |
Veröffentlicht in: | Buildings, 27 März 2024, n. 4, v. 14 |
Seite(n): | 916 |
DOI: | 10.3390/buildings14040916 |
Abstrakt: |
At the foundational phase of architectural design, it is of the utmost importance to precisely capture and articulate the visions and requirements of stakeholders, including building owners. This critical step ensures that professionals, including architects, can effectively translate the initial concepts into actionable designs. This research was directed towards developing a framework to facilitate the decision-making process by efficiently depicting the client’s intentions. This study demonstrates a framework that leverages deep learning to automate the creation of Building Information Modeling (BIM) models from sketched data. The framework’s methodology includes defining the necessary processes, system requirements, and data for system development, followed by the actual system implementation. It involves several key phases: (1) developing a process model to outline the framework’s operational procedures and data flows, (2) implementing the framework to translate sketched data into a BIM model through system and user interface development, and, finally, (3) validating the framework’s ability to precisely convert sketched data into BIM models. Our findings demonstrate the framework’s capacity to automatically interpret sketched lines as architectural components, thereby accurately creating BIM models. In the present study, the methodology and framework proposed enable clients to represent their understanding of spatial configuration through Building Information Modeling (BIM) models. This approach is anticipated to enhance the efficiency of communication with professionals such as architects. |
Copyright: | © 2024 by the authors; licensee MDPI, Basel, Switzerland. |
Lizenz: | Dieses Werk wurde unter der Creative-Commons-Lizenz Namensnennung 4.0 International (CC-BY 4.0) veröffentlicht und darf unter den Lizenzbedinungen vervielfältigt, verbreitet, öffentlich zugänglich gemacht, sowie abgewandelt und bearbeitet werden. Dabei muss der Urheber bzw. Rechteinhaber genannt und die Lizenzbedingungen eingehalten werden. |
10.07 MB
- Über diese
Datenseite - Reference-ID
10773884 - Veröffentlicht am:
29.04.2024 - Geändert am:
05.06.2024