Cargando…

An Online Rail Track Fastener Classification System Based on YOLO Models

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 abo...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsieh, Chen-Chiung, Hsu, Ti-Yun, Huang, Wei-Hsin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9783312/
https://www.ncbi.nlm.nih.gov/pubmed/36560339
http://dx.doi.org/10.3390/s22249970
_version_ 1784857548432605184
author Hsieh, Chen-Chiung
Hsu, Ti-Yun
Huang, Wei-Hsin
author_facet Hsieh, Chen-Chiung
Hsu, Ti-Yun
Huang, Wei-Hsin
author_sort Hsieh, Chen-Chiung
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9783312
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97833122022-12-24 An Online Rail Track Fastener Classification System Based on YOLO Models Hsieh, Chen-Chiung Hsu, Ti-Yun Huang, Wei-Hsin Sensors (Basel) Article 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. MDPI 2022-12-17 /pmc/articles/PMC9783312/ /pubmed/36560339 http://dx.doi.org/10.3390/s22249970 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hsieh, Chen-Chiung
Hsu, Ti-Yun
Huang, Wei-Hsin
An Online Rail Track Fastener Classification System Based on YOLO Models
title An Online Rail Track Fastener Classification System Based on YOLO Models
title_full An Online Rail Track Fastener Classification System Based on YOLO Models
title_fullStr An Online Rail Track Fastener Classification System Based on YOLO Models
title_full_unstemmed An Online Rail Track Fastener Classification System Based on YOLO Models
title_short An Online Rail Track Fastener Classification System Based on YOLO Models
title_sort online rail track fastener classification system based on yolo models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9783312/
https://www.ncbi.nlm.nih.gov/pubmed/36560339
http://dx.doi.org/10.3390/s22249970
work_keys_str_mv AT hsiehchenchiung anonlinerailtrackfastenerclassificationsystembasedonyolomodels
AT hsutiyun anonlinerailtrackfastenerclassificationsystembasedonyolomodels
AT huangweihsin anonlinerailtrackfastenerclassificationsystembasedonyolomodels
AT hsiehchenchiung onlinerailtrackfastenerclassificationsystembasedonyolomodels
AT hsutiyun onlinerailtrackfastenerclassificationsystembasedonyolomodels
AT huangweihsin onlinerailtrackfastenerclassificationsystembasedonyolomodels