Methodology for Activity Unit Segmentation of Design 3D Models Using PointNet Deep Learning Technique

• Published in: KSCE journal of civil engineering Vol. 28; no. 1; pp. 29 - 44
• Main Authors: Lee, JaeHee, Park, SangMi, Kang, LeenSeok
• Format: Journal Article
• Language: English
• Published: Seoul Korean Society of Civil Engineers 2024; Springer Nature B.V; 대한토목학회
• Subjects: Bridge construction; Bridges; Civil Engineering; Construction; Construction industry; Construction Management; Deep learning; Design; Engineering; Geotechnical Engineering & Applied Earth Sciences; Industrial Pollution Prevention; Methodology; Methods; Project engineering; Segmentation; Three dimensional models; 토목공학; 4D simulation; Building information model; 3D model segmentation; PointNet; Schedule management
• ISSN: 1226-7988; 1976-3808
• DOI: 10.1007/s12205-023-0816-3

This paper discusses the challenge of using 3D models created during the design stage in the construction stage due to the need for segmentation or remodeling to incorporate activity concepts. To address this challenge, the paper proposes a methodology that uses the PointNet deep learning technique to automatically classify and segment design model elements into activity units for the construction stage while preserving attribute information. The authors introduce a module that utilize the bounding box concept to simplify the segmentation process after importing the 3D model into the 4D system used in the construction stage. This eliminates the need for separate CAD software and allows for direct segmentation into activity units within the 4D system and simultaneous simulation. The proposed methodology was applied to two real bridge projects and demonstrated increased 3D model reusability in the construction stage. The paper concludes that this approach can improve the usability of 3D models for construction projects.