Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
Paper in proceeding, 2024

Computer vision models trained on Google Street View images can create material cadastres. However, current approaches need manually annotated datasets that are difficult to obtain and often have class imbalance. To address these challenges, this paper fine-tuned a Swin Transformer model on a synthetic dataset generated with OpenAI’s DALL E and compared the performance to a similar manually annotated dataset. Although manual annotation remains the gold standard, the synthetic dataset performance demonstrates a reasonable alternative. The findings will ease annotation needed to develop material cadastres, offering architects insights into opportunities for material reuse, thus contributing to the reduction of demolition waste.

Author

Josie Harrison

Chalmers, Architecture and Civil Engineering, Building Technology

Alexander Hollberg

Chalmers, Architecture and Civil Engineering, Building Technology

Yinan Yu

Chalmers, Computer Science and Engineering (Chalmers), Functional Programming

Proceedings of the European Conference on Computing in Construction

26841150 (eISSN)

Vol. 2024 120-127
9789083451305 (ISBN)

European Conference on Computing in Construction, EC3 2024
Chania, Greece,

Digital material inventories for sustainable urban mining

Swedish Foundation for Strategic Research (SSF) (FFL21-0082), 2022-08-01 -- 2027-12-31.

Subject Categories

Civil Engineering

Computer Systems

DOI

10.35490/EC3.2024.197

More information

Latest update

9/20/2024