文献类型：期刊文献

英文题名：RailTrack-DaViT: A Vision Transformer-Based Approach for Automated Railway Track Defect Detection

作者：Phaphuangwittayakul, Aniwat[1,2];Harnpornchai, Napat[3];Ying, Fangli[4];Zhang, Jinming[1]

机构：[1]Chiang Mai Univ, Int Coll Digital Innovat, Chiang Mai 50200, Thailand;[2]Lancang Mekong Digital Intelligence Shijiazhuang T, Shijiazhuang 051230, Peoples R China;[3]Chiang Mai Univ, Fac Econ, Chiang Mai 50200, Thailand;[4]East China Univ Sci & Technol, Dept Comp Sci & Engn, State Key Lab Bioreactor Engn, Shanghai 200237, Peoples R China

年份：2024

卷号：10

期号：8

外文期刊名：JOURNAL OF IMAGING

收录：EI(收录号：20243516959459);WOS:【ESCI(收录号:WOS:001304741000001)】；

基金：This research was partially funded by China-Laos-Thailand Education Digitization International Joint Research and Development Center of Yunnan Province (Project Number: 202203AP140006).

语种：英文

外文关键词：railway track inspection; vision transformer; computer vision; transportation safety; public transportation monitoring

摘要：Railway track defects pose significant safety risks and can lead to accidents, economic losses, and loss of life. Traditional manual inspection methods are either time-consuming, costly, or prone to human error. This paper proposes RailTrack-DaViT, a novel vision transformer-based approach for railway track defect classification. By leveraging the Dual Attention Vision Transformer (DaViT) architecture, RailTrack-DaViT effectively captures both global and local information, enabling accurate defect detection. The model is trained and evaluated on multiple datasets including rail, fastener and fishplate, multi-faults, and ThaiRailTrack. A comprehensive analysis of the model's performance is provided including confusion matrices, training visualizations, and classification metrics. RailTrack-DaViT demonstrates superior performance compared to state-of-the-art CNN-based methods, achieving the highest accuracies: 96.9% on the rail dataset, 98.9% on the fastener and fishplate dataset, and 98.8% on the multi-faults dataset. Moreover, RailTrack-DaViT outperforms baselines on the ThaiRailTrack dataset with 99.2% accuracy, quickly adapts to unseen images, and shows better model stability during fine-tuning. This capability can significantly reduce time consumption when applying the model to novel datasets in practical applications.