| 周炜杰,李智,张绍荣,唐洪贶,莫云.融合多级注意力与多尺度信息的铁轨缺陷分割网络[J].电子测量与仪器学报,2025,39(7):140-150 |
| 融合多级注意力与多尺度信息的铁轨缺陷分割网络 |
| Railway defect segmentation network with multi-level attention andmulti-scale information fusion |
| |
| DOI： |
| 中文关键词: 缺陷检测 语义分割 注意力机制 多尺度信息融合 小目标检测 |
| 英文关键词:defect detection semantic segmentation attention mechanism multi-perspective feature fusion small target detection |
| 基金项目:广西重点研发计划项目（桂科AB24010366）、广西自然科学基金面上项目（2025GXNSFAA069804）、桂林航天工业学院特色优势交叉学科发展战略研究专项（TS2024431）资助 |
|
|
| Author | Institution |
| Zhou Weijie | 1.School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China;
2.School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China |
| Li Zhi | School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China |
| Zhang Shaorong | School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China |
| Tang Hongkuang | School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China |
| Mo Yun | School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China |
|
| 摘要点击次数: 1023 |
| 全文下载次数: 539 |
| 中文摘要: |
| 铁路轨道缺陷检测技术面临许多挑战。轨道表面纹理复杂、背景噪声干扰严重，使得缺陷难以检出；缺陷种类多样，形态各异，导致检测方法难以同时捕捉所有细节特征；尺寸较小的缺陷由于特征不明显，往往会被漏检。为了精确分割铁路轨道表面缺陷，提出一种融合多级注意力与多尺度信息的铁轨缺陷分割网络。该网络的编码器通过堆叠倒置瓶颈卷积和融合倒置瓶颈卷积有效提高特征提取编码的效率；解码器部分使用多级并行像素级注意力模块辅助模型从大量背景噪声中聚焦定位缺陷区域；金字塔池化模块用于捕获多尺度上下文信息，增强模型对场景中的局部和全局特征的解析能力；多尺度信息融合方法融合像素级注意力模块和金字塔池化模块的输出，充分利用各阶段的特征信息。利用NRSD-MN数据集进行实验，在Craft和Real两类数据上，平均精度分别达到0.836 4和0.725 8；平均交并比分别达到0.685 8和0.634 2。实验结果表明，提出的网络在针对铁路轨道表面缺陷分割任务时，精度上显著优于现有的模型。 |
| 英文摘要: |
| Railway defect detection faces many challenges. The complex texture of the railway surface, background noise interference is serious, making it difficult to detect defects; defects of various types, different morphology, resulting in the traditional detection methods are difficult to capture all the details of the features at the same time; smaller defects due to the characteristics of the characteristics are not obvious, often missed. To address these issues, this paper proposes a novel semantic segmentation network that integrates a multi-level parallel attention mechanism and multi-scale information fusion to enhance defect segmentation accuracy. In the encoder, feature extraction and encoding efficiency are improved by leveraging stacked Inverted Bottleneck Convolutions and Fused Inverted Bottleneck Convolutions. The decoder incorporates a multi-level parallel pixel attention module (PAM) to enable the network to effectively focus on and localize defect regions amidst considerable background noise. Additionally, a pyramid pooling module (PPM) is introduced to capture multi-scale contextual information, enhancing the model’s ability to extract both local and global features. A multi-scale spatial information fusion strategy further integrates the outputs of PAM and PPM, maximizing the utilization of feature representations across different levels. Experimental evaluations on the NRSD-MN dataset demonstrate that the proposed method achieves mPA values of 0.836 4 and 0.725 8 and mIoU scores of 0.685 8 and 0.634 2 on the Craft and Real data subsets, respectively. The results confirm that the proposed network outperforms existing models in railway track surface defect segmentation, offering superior accuracy and robustness. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
