<p>FRA-mandated railroad track inspections result in significant labor costs and occupy valuable network capacity.&nbsp; These factors, combined with advancements in the field of machine vision, have encouraged transition from human visual inspections to machine-based alternatives. &nbsp;While commercial machine vision technologies for railway inspection currently exist, many depend on human interpretation of captured information which suffers similar limitations to fully manual inspections.&nbsp; Automated analysis approaches which deliver objective results are also available in the industry.&nbsp; However, they are limited to a “pass/fail” approach through the detection of components which fail to meet maintenance or safety thresholds, as opposed to being able to detect subtle changes in track conditions to identify evolving problems.&nbsp; To overcome the limitations of human interpretation and simple “pass/fail” defect-finding, this paper describes field deployment and validation of a system that pairs three-dimensional (3D) machine vision with automated change detection technology.&nbsp; The change detection approach uses a combination of traditional image processing and a deep convolutional neural network (DCNN) to accurately characterize network conditions between repeat runs before analyzing differences.&nbsp; This paper first provides context for the current automated track inspection technology and discusses the applicability of change detection. &nbsp;Then it discusses the process for 3D image capture and how DCNNs were trained with these 3D images. &nbsp;Finally, it compares the trained DCNNs to an expert human inspector.&nbsp; Results from this study suggest that this technology can successfully identify present, broken, and missing spikes and fasteners with percent accuracies in excess of 98%.</p>

Development of Deep Convoluted Neural Networks (Dcnns) and Change Detection Technology for Improved Railway Track Inspection

Paper Proceedings: https://asmedigitalcollection.asme.org/JRC/JRC2021/volume/84775

2021 Joint Rail Conference (JRC2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.