Corrosion of roadway metal railings in seaside cities not only affects the cosmetic appearance but also brings an economic cost to local government. This study aims to inspect and evaluate the corrosion of roadside guardrails with deep learning technique. Hundreds of photos on corroded roadway metal railings are taken, considering various illumination conditions, diverse shooting angles and different shooting distances in order to improve the generalizing ability of the deep learning model. The pictures are annotated manually labelling damages pixel by pixel, and DeepLabV3+ is trained to semantically segment the pictures for detection of corrosion shape and location. A subset of the photo dataset which has not been used in the training process is tested for validation, and two models with different loss function were trained to compare the influence of the adopted loss function. Based on the validated photos, the DeepLabV3+ model can detect corrosion area present in the image, which is useful to help the inspectors to design the maintenance strategy for the roadway metal railings.
As a protective facility to ensure the safety of citizens or to guide the traffic flow, guardrails are almost visible everywhere in modern cities. The most commonly used material for roadside guardrail systems is steel. However, due to the influence of the marine environment, corrosion of roadside steel guardrail is ubiquitous in coastal cities, which not only damages the appearance and reputation of the city, but also poses a potential security threat by largely reducing the service-life and strength of the guardrail. Therefore, regular maintenance of guardrails, especially repairing the corroded area, is an important task to ensure their functionality. Detection of guardrail corrosion area is a task of top priority and the prerequisite for the following implementation of maintenance strategy, i.e., whether eliminating the corrosion area by repainting the corroded area or replacing some parts of the guardrail.
