Deep Learning and Laser-Based 3-D Pixel-Level Rail Surface Defect Detection Method

Rail surface defect inspection is of particular importance in modern railways. Accurate and efficient surface defect detection approaches support optimized maintenance. This enables the safe operation of the railway network. However, the scale and harsh working environments of the railway still pose challenges to existing manual and vision-based inspection methods. Inspired by recent advances in laser measurement and deep learning in computer vision, this article proposes a laser-based 3-D pixel-level rail surface defect detection method that combines high-precision laser measurement data with the concept of deep semantic segmentation. In the proposed method, the rail surface is first measured in 3-D using a low-cost 2-D laser triangulation sensor. Then, a new deep semantic segmentation network is introduced. The network is composed of a fully convolutional segmentation module and two symmetric mapping modules, which can take 3-D laser measurement data as input and output 3-D pixel-level defect detection results in an end-to-end manner. The modular design of the network allows the use of various segmentation modules for different applications or scenarios. Experiments on a 3-D rail dataset demonstrate the feasibility of the proposed method with a pixel-level detection accuracy measured by mean intersection over union (mIoU) of up to 87.9%. The 3-D output provides not only location and boundary information but also the 3-D characterization of defects, giving an essential reference for further defect management and repair tasks.

Automated summary

Rail surface defect inspection is crucial for modern railways to ensure safe operation. This article proposes a laser-based 3-D pixel-level rail surface defect detection method by combining high-precision laser measurement with deep semantic segmentation. The method utilizes a low-cost 2-D laser triangulation sensor for 3-D measurement and introduces a new deep semantic segmentation network that can output 3-D pixel-level defect detection results. Experiment results show a pixel-level detection accuracy of up to 87.9%, providing essential reference for defect management and repair tasks.