Welcome to GitHub Pages of HKUST BIM LAB
We are a research team from the Hong Kong University of Science and Technology (HKUST) working on Building Information Modeling (BIM) and construction information technology (IT), led by Prof. Jack C.P. Cheng, currently an Associate Professor of HKUST. Here is our GitHub profile [click].
Goal
This page aims to share latest studies and datasets published by HKUST BIM LAB. You can directly download our public datasets for your research. We also select some of our published papers and provide the PDF files here. Hope our resources can help your research.
Resources
Following is a list of our public resources. (More resources will be ready soon.)
Computer vision and AI for construction equipment
-
Dataset: Construction equipment poses [click]. (Please cite: Luo H, Wang M, Wong PKY, Cheng JCP (2020) Full body pose estimation of construction equipment using computer vision and deep learning techniques. Automation in Construction 110:1–41. https://doi.org/10.1016/j.autcon.2019.103016)
-
Dataset: Construction machine motion capture dataset (time-series pose data) [click]. (Please cite: H. Luo, M. Wang, P.K.-Y. Wong, J. Tang, J.C.P. Cheng, Construction Machine Pose Prediction Considering Historical Motions and Activity Attributes Using Gated Recurrent Unit (GRU), Automation in Construction. 121 (2021) 103444. https://doi.org/10.1016/j.autcon.2020.103444.)
Point cloud processing and BIM reconstruction
-
Dataset: Point clouds of industrial scenes [click]. Please cite:
Chao Yin, Boyu Wang, Vincent JL Gan, Mingzhu Wang, Jack CP Cheng. Automated semantic segmentation of industrial point clouds using ResPointNet++. Automation in Construction. 130 (2021) 103874. https://doi.org/10.1016/j.autcon.2021.103874)
Boyu Wang, Chao Yin, Han Luo, Jack CP Cheng, Qian Wang. Fully automated generation of parametric BIM for MEP scenes based on terrestrial laser scanning data, Automation in Construction. 125 (2021) 103615. https://doi.org/10.1016/j.autcon.2021.103615)
Licenses
Resources publised by HKUST BIM LAB are freely available for non-commercial use under Apache-2.0 license. Interested in a commercial license? Please contact us through email.