High-Resolution Infrastructure Defect Detection Dataset Sourced by Unmanned Systems and Validated with Deep Learning
Benyun Zhao1, Xunkuai Zhou2,1, Guidong Yang1, Junjie Wen1, Jihan Zhang1, Jia Dou1, Li Guang1, Xi Chen1, and
Ben M. Chen1 IEEE Fellow
Ben M. Chen1 IEEE Fellow
1.Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong
2.School of Electronics and Information Engineering,Tongji University
2.School of Electronics and Information Engineering,Tongji University
The sample images in CUBIT has been shown below. All the data are collected by autonomous unmanned systems such as UAV and UGV. Our dataset includes various infrastructure scenarios and defect categories, which is more plantiful than the existing open-source bounding-box-level defect detection dataset.
| Image Resolution | Year | Structure Type | Number of Images | Defect Type | Annotation Level |
|---|---|---|---|---|---|
| 4624x3472, 8000x6000 | 2023 | Building, Pavement, Bridge | 5527 | Crack, Spalling, Moisture | Bounding-box Level |
If you find this project helpful for your research, please consider citing our paper and giving a ⭐.
Any questions or academic discussion, please contact me at: byzhao@mae.cuhk.edu.hk
@article{ZHAO2024105405,
title = {High-resolution infrastructure defect detection dataset sourced by unmanned systems and validated with deep learning},
journal = {Automation in Construction},
volume = {163},
pages = {105405},
year = {2024},
issn = {0926-5805},
doi = {https://doi.org/10.1016/j.autcon.2024.105405},
author = {Benyun Zhao and Xunkuai Zhou and Guidong Yang and Junjie Wen and Jihan Zhang and Jia Dou and Guang Li and Xi Chen and Ben M. Chen},
}