Enhancing Rail Surface Defect Detection Using a Hybrid YOLOv11–Vision Transformer Framework
Journal of Trends in Computer Science and Smart Technology · 24.04.2026 · 8 (2) · 291-303
DOI: 10.36548/jtcsst.2026.2.005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Trends in Computer Science and Smart Technology, online erschienen am 24.04.2026. Verfasst von Baburao Markapudi und 4 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
Railway track surface defects cause severe challenges to the safety of humans, trains, and transported goods. Modern YOLO-based detectors efficiently detect rail surface defects in real time. However, they mainly focus on local features and also confuse defects that look similar. On the other hand, Vision Transformers are good at modeling global context using self-attention, but they do not localize objects properly when used alone. To overcome these issues, this study introduces a hybrid YOLOv11 and Vision Transformer (YOLOv11a and ViT) framework for enhanced rail surface defect detection. The approach integrates a lightweight Vision Transformer module into the YOLOv11 backbone so that the model learns both detailed local features and captures global dependencies. Experiments are conducted on a merged public railway surface defect computer vision dataset comprising 8,177 labeled images of five defect categories. The results show that the new method achieves an mAP@0.5 of 0.951 with a precision of 0.899 and recall of 0.921, outperforming the baseline YOLO model. The most significant advancements have been made in identifying elongated defects such as cracks and light bands.The framework also maintains real-time performance, making it practical for use in railway safety inspections.
Zitieren
APA
Markapudi, B., Gundiga, L., Kondeti, V. R. B., Kanumuri, S., & Maddala, Y. (2026). Enhancing Rail Surface Defect Detection Using a Hybrid YOLOv11–Vision Transformer Framework. Journal of Trends in Computer Science and Smart Technology, 8(2), 291-303. https://doi.org/10.36548/jtcsst.2026.2.005
Vancouver
Markapudi B, Gundiga L, Kondeti VRB, Kanumuri S, Maddala Y. Enhancing Rail Surface Defect Detection Using a Hybrid YOLOv11–Vision Transformer Framework. Journal of Trends in Computer Science and Smart Technology. 2026;8(2):291-303. doi:10.36548/jtcsst.2026.2.005
BibTeX
@article{Markapudi2026,
author = {Markapudi, Baburao and Gundiga, Lahari and Kondeti, Venkata Ramesh Babu and Kanumuri, Sravanthi and Maddala, Yamini},
title = {Enhancing Rail Surface Defect Detection Using a Hybrid YOLOv11–Vision Transformer Framework},
journal = {Journal of Trends in Computer Science and Smart Technology},
year = {2026},
volume = {8},
number = {2},
pages = {291--303},
doi = {10.36548/jtcsst.2026.2.005}
}
EUVIMED