The detection of Rail Surface Defects (RSDs) plays a critical role in railway track maintenance. Traditional image processing methods exhibit limitations due to their intricate design and insufficient robustness, thereby restricting their broader applications. Recently, deep learning-based RSD detection methods have drawn great attention. However, these methods predominantly rely on Convolutional Neural Networks (CNN), neglecting the hierarchical linkages amongst disparate features, which impedes the refined portrayal of RSDs. To address these issues, we propose RailFormer, a novel system leveraging the capabilities of Transformer-based networks for the precise and efficient detection of RSDs. The encoder in RailFormer incorporates overlapped patch merging, efficient self-attention, and a Mix-feed Forward Network (FFN), all meticulously designed to bolster feature fusion from both global and local perspectives. Additionally, we have implemented a Criss-Cross attention module within the decoder to facilitate RSD detection and manage computational complexity. In this study, the proposed RailFormer and four other models including SegFormer, Swin Transformer, ViT, and UNet are trained and compared. We employ the widely used public RSD datasets RSDD, encompassing both Type-I and Type-II RSDD images and a customized RSD dataset, as a basis for performance comparison. The training outcomes and visualization results show that RailFormer achieves the highest mean Intersection over Union (mIoU) and superior visualization performance on the RSDD and the customized RSD datasets. These results demonstrate the superiority of RailFormer and underline its potential for future deployment in railway track inspection applications.

中文翻译：

---

使用基于变压器的网络进行轨道表面缺陷检测

钢轨表面缺陷 (RSD) 的检测在铁路轨道维护中发挥着至关重要的作用。传统的图像处理方法由于其复杂的设计和鲁棒性不足而​​表现出局限性，从而限制了其更广泛的应用。近年来，基于深度学习的RSD检测方法引起了广泛关注。然而，这些方法主要依赖于卷积神经网络（CNN），忽略了不同特征之间的层次联系，这阻碍了 RSD 的精细描述。为了解决这些问题，我们提出了 RailFormer，这是一种利用基于 Transformer 的网络功能来精确有效地检测 RSD 的新颖系统。RailFormer 中的编码器融合了重叠补丁合并、高效的自注意力和混合前馈网络 (FFN)，所有这些都经过精心设计，旨在从全局和局部角度支持特征融合。此外，我们在解码器中实现了十字交叉注意力模块，以促进 RSD 检测并管理计算复杂性。在本研究中，对所提出的 RailFormer 和其他四种模型（包括 SegFormer、Swin Transformer、ViT 和 UNet）进行了训练和比较。我们采用广泛使用的公共 RSD 数据集 RSDD，包括 I 型和 II 型 RSDD 图像以及定制的 RSD 数据集，作为性能比较的基础。训练结果和可视化结果表明，RailFormer 在 RSDD 和定制 RSD 数据集上实现了最高的平均交集 (mIoU) 和卓越的可视化性能。这些结果证明了 RailFormer 的优越性，并强调了其未来在铁路轨道检查应用中部署的潜力。