Abstract
In order to save manpower on rail track inspection, computer vision-based methodologies are developed. We propose utilizing the YOLOv4-Tiny neural network to identify track defects in real time. There are ten defects covering fasteners, rail surfaces, and sleepers from the upward and six defects about the rail waist from the sideward. The proposed real-time inspection system includes a high-performance notebook, two sports cameras, and three parallel processes. The hardware is mounted on a flat cart running at 30 km/h. The inspection results about the abnormal track components could be queried by defective type, time, and the rail hectometer stake. In the experiments, data augmentation by a Cycle Generative Adversarial Network (GAN) is used to increase the dataset. The number of images is 3800 on the upward and 967 on the sideward. Five object detection neural network models—YOLOv4, YOLOv4-Tiny, YOLOX-Tiny, SSD512, and SSD300—were tested. The YOLOv4-Tiny model with 150 FPS is selected as the recognition kernel, as it achieved 91.7%, 92%, and 91% for the mAP, precision, and recall of the defective track components from the upward, respectively. The mAP, precision, and recall of the defective track components from the sideward are 99.16%, 96%, and 94%, respectively.
Funder
Harbor and Marine Technology Center (HMTC), Institute of Transportation (IOT), Ministry of Transportation and Communication
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference40 articles.
1. Wong, J.H. (2022, May 23). Digitization Upgrade the Safety—Taiwan Rail Track Inspection APP. Available online: https://reurl.cc/yrqZQM.
2. Plasser & Theurer (2022, November 03). Non-Contacting Measurement under Load in Real Time at up to 100 km/h. Available online: https://www.plassertheurer.com/en/machine/track-recording-cars/em80h.
3. Ensco (2022, November 11). Track Inspection Services. Available online: https://www.ensco.com/rail/track-inspection-services.
4. Fugro (2022, May 23). RILA3.0, Fugro. Available online: https://www.fugro.com/about-fugro/our-expertise/innovations/rila#tabbed1.
5. Tech, J.C. (2022, November 11). AI Automatic Track Inspection Robot. Available online: https://www.linkedin.com/company/jc-technology.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献