Corrosion Condition Rating Database

Published: 2023

Author(s):
Ameli, Z.
Landis, E

Publication Name: UMaine Digital Commons

Publication URL: https://digitalcommons.library.umaine.edu/student_work/30/

Research Area:
Keywords:
, ,

Abstract:

This dataset contains 514 RGB images and corresponding pixel-level annotation files in two separate formats; .json and .txt. The images are collected from steel bridge elements using a drone and a Nikon camera. The images was randomly split into 412 training images and 90 validation and 12 testing images. Two dataset for training Mask RCNN and YOLOv8 models are included in the database. All the annotations are carefully performed for quality assurance. The three classes used in this study, represents different levels of corrosion severity (corrosion condition states) according to American Association of State Highway and Transportation Officials (AASHTO) and and Bridge Inspector’s Reference Manual (BIRM) regulations.