Unsupervised anomaly segmentation model for rail damage based on image-inpainting and cold diffusion

IF 9.6 1区 工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY
Chengjia Han, Yiqing Dong, Maggie Y. Gao, Liwei Dong, Yaowen Yang
{"title":"Unsupervised anomaly segmentation model for rail damage based on image-inpainting and cold diffusion","authors":"Chengjia Han,&nbsp;Yiqing Dong,&nbsp;Maggie Y. Gao,&nbsp;Liwei Dong,&nbsp;Yaowen Yang","doi":"10.1016/j.autcon.2025.106342","DOIUrl":null,"url":null,"abstract":"<div><div>Ensuring structural health of rail tracks is critical for safe train operations. While deep learning-based vision models are widely used for rail damage detection, supervised methods suffer from limited generalization due to scarce and diverse annotated data. Unsupervised models often experience missed detections and false positives when handling complex and variable rail background textures, as well as rail damage with significant intra-class variability. To address these limitations, this paper proposes an unsupervised pixel-level rail damage segmentation model based on a cold diffusion framework, called InpRailDiffusion. It introduces inpainting-based noise and uses a Mamba-enhanced, time-conditioned U-Net for progressive noise removal. Damage segmentation is achieved by analyzing pixel-wise differences between generated and original images with adaptive thresholding. A multi-scale masking strategy fuses reconstruction features at various spatial resolutions, reducing false positives and missed detections. Evaluated on RSDDs-I and RSDDs-II, InpRailDiffusion outperformed state-of-the-art baselines with MIoU/F1-Scores of 0.864/0.844 and 0.845/0.814, respectively.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106342"},"PeriodicalIF":9.6000,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automation in Construction","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926580525003826","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Ensuring structural health of rail tracks is critical for safe train operations. While deep learning-based vision models are widely used for rail damage detection, supervised methods suffer from limited generalization due to scarce and diverse annotated data. Unsupervised models often experience missed detections and false positives when handling complex and variable rail background textures, as well as rail damage with significant intra-class variability. To address these limitations, this paper proposes an unsupervised pixel-level rail damage segmentation model based on a cold diffusion framework, called InpRailDiffusion. It introduces inpainting-based noise and uses a Mamba-enhanced, time-conditioned U-Net for progressive noise removal. Damage segmentation is achieved by analyzing pixel-wise differences between generated and original images with adaptive thresholding. A multi-scale masking strategy fuses reconstruction features at various spatial resolutions, reducing false positives and missed detections. Evaluated on RSDDs-I and RSDDs-II, InpRailDiffusion outperformed state-of-the-art baselines with MIoU/F1-Scores of 0.864/0.844 and 0.845/0.814, respectively.
基于图像预处理和冷扩散的钢轨损伤无监督异常分割模型
确保轨道结构健康对列车安全运行至关重要。虽然基于深度学习的视觉模型被广泛用于轨道损伤检测,但由于标注数据的稀缺和多样性,监督方法的泛化程度有限。在处理复杂和可变的轨道背景纹理以及具有显着的类内可变性的轨道损坏时,无监督模型经常会经历错过检测和误报。为了解决这些限制,本文提出了一种基于冷扩散框架的无监督像素级轨道损伤分割模型,称为InpRailDiffusion。它引入了基于油漆的噪声,并使用曼巴增强的时间条件U-Net来逐步去除噪声。利用自适应阈值法分析生成图像与原始图像之间的像素差异,实现损伤分割。多尺度掩蔽策略融合了不同空间分辨率下的重建特征,减少了误报和漏检。在RSDDs-I和RSDDs-II评估中,InpRailDiffusion的MIoU/F1-Scores分别为0.864/0.844和0.845/0.814,优于最新基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Automation in Construction
Automation in Construction 工程技术-工程:土木
CiteScore
19.20
自引率
16.50%
发文量
563
审稿时长
8.5 months
期刊介绍: Automation in Construction is an international journal that focuses on publishing original research papers related to the use of Information Technologies in various aspects of the construction industry. The journal covers topics such as design, engineering, construction technologies, and the maintenance and management of constructed facilities. The scope of Automation in Construction is extensive and covers all stages of the construction life cycle. This includes initial planning and design, construction of the facility, operation and maintenance, as well as the eventual dismantling and recycling of buildings and engineering structures.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信