Curated datasets for AI in AEC

OpenConstruction Overview

A centralized, carefully maintained catalog of open-access visual datasets for construction monitoring, safety, and productivity—designed to accelerate reproducible research and practical AI deployment.

About

OpenConstruction

OpenConstruction is a curated collection of publicly available datasets focused on construction monitoring and analysis. This serves as a central hub for researchers, practitioners, and developers working on AI applications in the construction industry.

Vision

Why we built this

The industry is rapidly adopting AI-driven computer vision for monitoring, safety, and efficiency. Effective models need high-quality, diverse datasets. Our goals:

  • Provide a comprehensive catalog of open construction datasets
  • Standardize metadata for comparison and selection
  • Enable fair benchmarking and evaluation
  • Support reproducible research and education
Reference

Cite the catalog

Our work is documented in:

OpenConstruction: A Systematic Synthesis of Open Visual Datasets for Data-Centric Artificial Intelligence in Construction Monitoring
Ruoxin Xiong, Yanyu Wang, Jiannan Cai, Kaijian Liu, Yuansheng Zhu, Pingbo Tang, Nora El-Gohary
arXiv:2508.11482, 2025

BibTeX
@misc{xiong2025openconstructionsystematicsynthesisopen,
  title={OpenConstruction: A Systematic Synthesis of Open Visual Datasets for Data-Centric Artificial Intelligence in Construction Monitoring}, 
  author={Ruoxin Xiong and Yanyu Wang and Jiannan Cai and Kaijian Liu and Yuansheng Zhu and Pingbo Tang and Nora El-Gohary},
  year={2025},
  eprint={2508.11482},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2508.11482}
}
Feedback

Have an idea or request?

We’d love to hear from you. Share suggestions or feature requests here: Create a suggestion .

Policy

Request dataset removal

If you’d like a dataset removed, please email ruoxinx@outlook.com from an address that can verify ownership, and we’ll act quickly.