Daily Arxiv

This page organizes papers related to artificial intelligence published around the world.
This page is summarized using Google Gemini and is operated on a non-profit basis.
The copyright of the paper belongs to the author and the relevant institution. When sharing, simply cite the source.

Automated Facility Enumeration for Building Compliance Checking using Door Detection and Large Language Models

Created by
  • Haebom

Author

Licheng Zhang, Bach Le, Naveed Akhtar, Tuan Ngo

Outline

To address the problem of accurately enumerating facility types and their spatial distribution, a critical step in building code compliance inspection, we aim to address a largely overlooked issue in the literature. To improve this time-consuming and labor-intensive manual task, we propose a novel method that combines visual recognition and reasoning capabilities using LLM. We enhance performance through a statement-based inference pipeline. Experiments on real and synthetic floor plan data demonstrate the effectiveness and robustness of the proposed method.

Takeaways, Limitations

•
Takeaways:
◦
A novel approach to automating building code compliance checks.
◦
Effectively solve facility type enumeration problems using LLM.
◦
Improving LLM performance with Chain-of-Thought pipeline.
◦
Demonstrated generalizability across diverse datasets and facility types.
•
Limitations:
◦
Additional information is needed on the technical details and performance metrics of the specific methodology.
◦
Potential biases and potential errors in LLM-based systems need to be considered.
◦
Lack of discussion of the additional complexities and challenges of real-world application.
👍
Made with Slashpage