摘要
因长期受反复荷载作用,高速铁路钢轨会产生表面缺陷,为了提升复杂场景下多类多尺度钢轨表面缺陷检测的精度与速度,设计了一种基于双模态融合的钢轨表面缺陷分割网络(DAFNet)。首先构建了一个包含可见光和红外通道的钢轨表面缺陷数据集,并采用改进的双分支网络架构,提高了分割速度;同时,设计了双模态自适应融合模块(BAFM),实现了特征的自适应融合,提高了复杂场景下钢轨表面缺陷的分割精度;此外,设计了空间细节提取模块(SDEM)和关键信息增强模块(KIEM),进一步提高了对缺陷边缘的感知度,解决了复杂场景下缺陷与背景对比度不高的问题。实验表明,所设计网络分割的精确度和mIoU分别达到了68.13%, 59.96%,明显优于其他主流网络;且FLOPs、参数量和模型大小分别为17.41 GFLOPs,1.38 M和5.67 MB,优于大多数主流网络。所设计的网络显著提高了钢轨表面缺陷的分割精度,并且具有较高分割速度,对保障高铁的安全运营具有重要意义。
Due to the long-term repeated loading,surface defects occur in high-speed railway steel rails.In order to improve the accuracy and speed of surface defect detection for multiple classes and scales of steel rails in com-plex scenarios,a steel rail surface defect segmentation network based on multimodal fusion(DAFNet)is de-signed.Firstly,a steel rail surface defect dataset containing visible light and infrared channels is constructed,and an improved dual-branch network architecture is adopted to increase segmentation speed.Simultaneously,a bi-modal adaptive fusion module(BAFM)is designed to achieve adaptive feature fusion,improving the segmenta-tion accuracy of steel rail surface defects in complex scenarios.Additionally,a spatial detail extraction module(SDEM)and a key information enhancement module(KIEM)are designed to further enhance the perception of defect edges and address the low contrast between defects and backgrounds in complex scenarios.Experiments show that the accuracy and mIoU of the designed network segmentation reach 68.13%and 59.96%respectively,which are significantly better than other mainstream networks.Moreover,FLOPs,parameter quantity,and model size are 17.41 GFLOPs,1.38 M,and 5.67 MB respectively,which are better than most mainstream networks.The designed network significantly improves the segmentation accuracy of steel rail surface defects and has a high segmentation speed,which is of great significance for ensuring the safe operation of high-speed railways.
作者
罗晖
韩岳霖
马治伟
斯成浩
Luo Hui;Han Yuelin;Ma Zhiwei;Si Chenghao(School of Information and Software Engineering,East China Jiaotong University,Nanchang 330013,China)
出处
《华东交通大学学报》
2025年第1期52-60,共9页
Journal of East China Jiaotong University
基金
国家自然科学基金项目(62262021)。
关键词
语义分割
钢轨表面缺陷
深度学习
红外图像
可见光图像
双模态融合
semantic segmentation
rail surface defects
deep learning
infrared image
visible light image
bimodal fusion
