back to list
Project: Improved AI framework for BIM Clash Classification
Description
Modern AI and Deep Learning can detect specific patterns in complex structures,
like 3D geometry and temporal or meta data. In a first feasibility study it was proven
that neural networks are able to fully automatically label relevant hard clashes (high,
medium or low priority) from geometry components with additional metadata. Input are potential clashes as calculated by the BimCollab Zoom tool developed at KUBUS, in the context of Building Information Modeling (BIM) issue management. Output would be a classification for each clash, including prediction confidence.
Detailed description
View PDFDetails
- Supervisor
-
Andrei Jalba
- Secondary supervisor
-
KKKUBUS
- External location
- KUBUS
- Interested?
- Get in contact