Invert Spaces: Automated Building Element Modeling from Room Scans
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for automatically modeling building elements from scanned room data require manual adjustments and are prone to inaccuracies due to imperfect data and non-parallel surfaces, leading to unreliable generation and classification of 3D architectural models.
Innovation Solution
A method involving extruding piecewise planar objects with a user-defined thickness, forming a fused object, intersecting it with planes to create cells, and classifying these cells as building elements based on their position and orientation, ensuring accurate identification and classification of exterior and interior walls, floors, and roofs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated methods are used to model building elements from scanned room data, then productivity is improved, but manufacturing precision deteriorates due to imperfect data and non-parallel surfaces
Solution Approach 1:
The patent inverts the traditional approach by not trying to fit scanned data to ideal geometric primitives, but rather growing solids from the scanned surfaces themselves. This inversion allows the model to adapt to the actual imperfect geometry of scanned surfaces while maintaining automated processing, thus resolving the contradiction between automation and precision
Solution Approach 2:
The patent changes the parameter representation from idealized geometric parameters to scanned surface-based parameters. By representing building elements as grown solids from actual scanned surfaces rather than fitted primitives, the system maintains automation while capturing the true geometry of imperfect surfaces, thereby improving modeling accuracy without sacrificing productivity
2Manufacturing precision
If manual adaptations are applied to correct segmentation errors, then manufacturing precision is improved, but loss of time increases
Solution Approach 1:
The patent implements self-service by having the system automatically correct segmentation errors through the growth and fusion process. The algorithm autonomously identifies and resolves issues with non-parallel surfaces and small inclusions by growing solids from scanned surfaces and fusing them according to their spatial relationships, eliminating the need for manual time-consuming adjustments while maintaining high segmentation accuracy
3Device complexity
If simple geometric primitives are used to represent building elements, then device complexity is reduced, but measurement precision deteriorates due to imperfect scanned data
Solution Approach 1:
The patent applies segmentation by dividing the building model into distinct grown solids corresponding to different building elements (walls, floors, ceilings). Each element is grown from its corresponding scanned surface, allowing the model to maintain simplicity through discrete geometric primitives while achieving measurement precision by basing each primitive on actual scanned data rather than idealized assumptions
Data Source
AI summary
A computer implemented method for generating building elements from a set of piecewise planar objects that are obtained from scanning data from room interiors within a building. This method allows for the automatic generation and classification of building elements from a set of room interior representations, enabling an efficient modelling process in architectural and construction projects.