A new rail inspection method based on deep learning using laser cameras

Abstract

Rail systems are one of the most important transportation methods used in today's world. The abnormalities that occur on railway tracks due to various causes result in breakdowns and accidents. For this reason, railway tracks must be periodically inspected. This study proposes a new approach for rail inspection. Today, the railway inspection process is generally performed using computer vision. But the oil and dust residues occurring on railway surfaces can be detected as an false-positive by the image processing software can lead to loss of time and additional costs in the railway maintenance process. In this study, a hardware and software architecture are presented to perform railway surface inspection using 3D laser camera and deep learning. The use of 3D laser cameras in railway inspection process provides high accuracy rates in real time. The reading rate of laser cameras to read up to 25.000 profiles per second is another important advantage provided in real time railway inspection. Consequently, a computer vision-based approach in which 3D laser cameras that could allow for contact-free and fast detection of the railway surface and lateral defects such as fracture, scouring and wear with high accuracy are used in the railway inspection process was proposed in the study.