Scopus
🔓 Açık Erişim
A New Rail Surface Defects Detection Approach Using 3D Laser Cameras Based on ResNet50
Traitement du Signal · Ağustos 2022
Makale Bilgileri
DergiTraitement du Signal
Yayın TarihiAğustos 2022
Cilt / Sayfa39 · 1339-1345
Scopus ID2-s2.0-85139878557
Erişim🔓 Açık Erişim
Özet
Rail transportation systems, which are used as one of the most common means of transportation worldwide, should be regularly inspected to prevent accidents that may occur. The rail condition monitoring can be performed in high accuracy and real time using computer vision, deep learning algorithms today. In this study, a new deep learning based approach using 3D laser cameras for rail inspection is presented. In the proposed approach, two 3D laser cameras placed on a real train, seeing the rail line from the left and right surfaces were used. These data consisting of sensitive distance value constitute the input data of the ResNet50 transfer learning model. The training was carried out on Nvidia Cuda supported graphics processing units using ResNet50 Convolutional Neural Network. During the test phase, the operation speed and accuracy rate of the method was measured by repeating the process on real-time rail profiles. The accuracy rate was calculated as 94%. As a result a new approach is presented based on deep learning using 3D laser cameras for rail inspection is presented.
Yazarlar (4)
1
Yunus Santur
2
Merve Yilmazer
3
Mehmet Karaköse
4
Erhan Akin
ORCID: 0000-0001-6476-9255
Anahtar Kelimeler
deep learning
laser cameras
rail surface defects
railway inspection
ResNet-50 architecture
Kurumlar
Firat Üniversitesi
Elazig Turkey
Munzur University
Tunceli Turkey
Metrikler
1
Atıf
4
Yazar
5
Anahtar Kelime