Hyperspectral imaging systems for corrosion detection from remotely operated vehicles

The detection of corrosion, especially in early stages, is a key factor for cost reduction in the maintenance of steel infrastructure. However, manual inspection is time consuming and takes considerable effort of people and equipment. Remotely operated vehicles with application‐specific sensors may overcome this problem. Novel sensing approaches like hyperspectral imaging (HSI) systems in combination with machine learning algorithms open new pathways for the rapid inspection of large surface areas in complex environments. In contrast to conventional RGB imaging, HSI contains both spatial and spectral reflectivity information over the complete visual spectral range and near infrared. This offers improved material characterization and classification possibilities using the chemical properties contained in the local reflection spectrum.

This paper presents advantages and disadvantages of hyperspectral imaging systems for the detection of corrosion of steel infrastructure as well as suitable wavelength ranges for use with remotely operated vehicles. Furthermore, in‐field measurements with HSI for the inspection of corrosion on steel structures are shown.