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
Xi Chen1, and 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
The Chinese University of Hong Kong
2.School of Electronics and Information Engineering,Tongji University
Dataset can be available at:
https://drive.google.com/drive/folders/1LWwEKQ8rSB97fCRD4sG7b6UcK40rSdA2?usp=drive_link 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 scenarios and defect categories compared with 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 |
