Automated Corrosion Detection Using Crowd Sourced Training for Deep Learning
This addresses corrosion monitoring for industries needing remote inspection, but it is incremental as it applies existing crowd-sourcing methods to a specific domain.
The paper tackled automated corrosion detection from images or video by developing a deep learning model trained via crowd-sourced labeling through a website, achieving a system capable of assessing new images for corrosion presence after approximately one month of operation.
The automated detection of corrosion from images (i.e., photographs) or video (i.e., drone footage) presents significant advantages in terms of corrosion monitoring. Such advantages include access to remote locations, mitigation of risk to inspectors, cost savings and monitoring speed. The automated detection of corrosion requires deep learning to approach human level artificial intelligence (A.I.). The training of a deep learning model requires intensive image labelling, and in order to generate a large database of labelled images, crowd sourced labelling via a dedicated website was sought. The website (corrosiondetector.com) permits any user to label images, with such labelling then contributing to the training of a cloud based A.I. model - with such a cloud-based model then capable of assessing any fresh (or uploaded) image for the presence of corrosion. In other words, the website includes both the crowd sourced training process, but also the end use of the evolving model. Herein, the results and findings from the website (corrosiondetector.com) over the period of approximately one month, are reported.