
浏览全部资源
扫码关注微信
1.中国地质大学(武汉)地理与信息工程学院,湖北 武汉,430074
2.中国地质大学(武汉)区域生态过程与环境演变湖北省重点实验室,湖北 武汉,430074
3.中国地质大学(武汉)信息技术湖北省重点学科实验室,湖北 武汉,430074
4.中国地质大学(武汉)计算机学院,湖北 武汉,430074
Revised:2026-08-21,
Published:05 October 2026
移动端阅览
王东豪,吴云龙,袁梦瑶,等.基于自适应背景差分与二维最大熵的钢轨表面缺陷检测[J].测绘地理信息,2026,51(5):130-137
WANG Donghao,WU Yunlong,YUAN Mengyao,et al.Steel Rail Surface Defect Detection Based on Adaptive Background Difference and Two-Dimensional Maximum Entropy[J].Journal of Geomatics,2026,51(5):130-137
王东豪,吴云龙,袁梦瑶,等.基于自适应背景差分与二维最大熵的钢轨表面缺陷检测[J].测绘地理信息,2026,51(5):130-137 DOI: 10.14188/j.2095-6045.20260335.
WANG Donghao,WU Yunlong,YUAN Mengyao,et al.Steel Rail Surface Defect Detection Based on Adaptive Background Difference and Two-Dimensional Maximum Entropy[J].Journal of Geomatics,2026,51(5):130-137 DOI: 10.14188/j.2095-6045.20260335.
针对复杂轨面图像中灰度不均衡和噪声干扰
导致缺陷与背景可分性下降的问题,提出一种自适应局部趋势背景建模与邻域一致性二维最大熵的钢轨表面缺陷检测方法。首先,根据列灰度的局部变化趋势自适应估计背景,抑制列向亮度漂移产生的差分残差;随后结合灰度对比度增强与缺陷比例限制,提高缺陷与背景之间的灰度可分性;进一步引入邻域平均灰度构建二维统计信息,实现最大熵自适应分割,并采用形态学重构抑制残余噪声。实验结果表明,本文方法的召回率、精确率和
<math id="M1"><msub><mrow><mi>F</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msub></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980426&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980438&type=
3.30200005
3.21733332
-score 分别达到92.8%、92.6%和92.7%,其中
<math id="M2"><msub><mrow><mi>F</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msub></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980428&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980419&type=
3.30200005
3.21733332
-score 高于对比方法,表明该方法在复杂轨面条件下具有较好的综合检测性能。
To address the problem of decreased separability between defects and background due to uneven gray levels and noise interference in complex rail surface images, an adaptive local trend background modeling and neighborhood consistency two-dimensional maximum entropy method for steel rail surface defect detection is proposed. Firstly, the background is adaptively estimated based on the local change trend of column gray levels, and the differential residuals caused by column-wise brightness
drift are suppressed; then, by combining gray contrast enhancement and defect proportion limitation, the gray separability between defects and background is improved; further, the neighborhood average gray level is introduced to construct two-dimensional statistical information, achieving adaptive segmentation by maximum entropy, and morphological reconstruction is adopted to suppress residual noise. Experimental results show that the recall rate, precision rate and
F
2
-score of this method reach 92.8%, 92.6% and 92.7% respectively. Among them, the
<math id="M3"><msub><mrow><mi>F</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msub></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980430&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=119980429&type=
3.30200005
3.21733332
-score is higher than that of the comparison method, indicating that this method has better comprehensive detection performance under complex rail surface conditions.
Xu CanYang , Liao Yingying , Liu Yongqiang , et al . Lightweight Rail Surface Defect Detection Algorithm Based on an Improved YOLOv8 [J]. Measurement , 2025 , 242 : 115922
张辉 , 宋雅男 , 王耀南 , 等 . 钢轨缺陷无损检测与评估技术综述 [J]. 仪器仪表学报 , 2019 , 40 ( 2 ): 11 - 25
Ni X , Liu H , Ma Z , et al . Detection for Rail Surface Defects via Partitioned Edge Feature [J]. IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 6 ): 5 806 - 5 822
Zhang Hui , Jin Xiating , Wu Q . M. J, et al. Automatic Visual Detection System of Railway Surface Defects With Curvature Filter and Improved Gaussian Mixture Model[J]. IEEE Transactions on Instrumentation and Measurement , 2018 , 67 ( 7 ): 1 593 - 1 608
Lei Kou . A Review of Research on Detection and Evaluation of the Rail Surface Defects [J]. Acta Polytechnica Hungarica , 2022 , 19 ( 3 ): 167 - 186
Dubey A K , Jaffery Z A . Maximally Stable Extremal Region Marking-Based Railway Track Surface Defect Sensing [J]. IEEE Sensors Journal , 2016 , 16 ( 24 ) : 9 047 - 9 052
Li Qingyong , Ren Shengwei . A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads [J]. IEEE Transactions on Instrumentation and Measurement , 2012 , 61 ( 8 ): 2 189 - 2 199
袁小翠 , 吴禄慎 , 陈华伟 . 基于Otsu方法的钢轨图像分割 [J]. 光学精密工程 , 2016 , 24 ( 7 ): 1 772 - 1 781
贺振东 , 王耀南 , 刘洁 , 等 . 基于背景差分的高铁钢轨表面缺陷图像分割 [J]. 仪器仪表学报 , 2016 , 37 ( 3 ): 640 - 649
闵永智 , 岳彪 , 马宏锋 , 等 . 基于图像灰度梯度特征的钢轨表面缺陷检测 [J]. 仪器仪表学报 , 2018 , 39 ( 4 ): 220 - 229
曹义亲 , 刘龙标 . 基于缺陷比例限制的背景差分钢轨表面缺陷检测方法 [J]. 计算机应用 , 2020 , 40 ( 10 ): 3 066 - 3 074
王国伟 , 陈光武 , 魏宗寿 . 基于背景差分与最大熵的轨面缺陷分割 [J]. 计算机系统应用 , 2022 , 31 ( 10 ): 184 - 190
张琳娜 , 岑翼刚 . 铁轨图像的低秩矩阵分解缺陷检测 [J]. 信号处理 , 2019 , 35 ( 4 ): 667 - 675
张辉 , 李平 , Wu Q . M . J,等. 基于改进马尔可夫随机场的钢轨缺陷分割[J]. 计算机工程与设计 , 2020 , 41 ( 4 ): 1 052 - 1 061
Niu Menghui , Song Kechen , Huang Liming , et al . Unsupervised Saliency Detection of Rail Surface Defects Using Stereoscopic Images [J]. IEEE Transactions on Industrial Informatics , 2021 , 17 ( 3 ): 2 271 - 2 281
Ren S , He K , Girshick R , et al . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1 137 - 1 149
Liu W , Anguelov D , Erhan D , et al . SSD: Single Shot MultiBox Detector [C]// Computer Vision – ECCV 2016 . Cham : Springer , 2016 : 21 - 37
Redmon J , Farhadi A . YOLOv3:An Incremental Improvement [PP/OL]. arXiv , 2018 , doi: 10.48550/arXiv.1804.02767 http://dx.doi.org/10.48550/arXiv.1804.02767
彭方进 . 一种高鲁棒性的钢轨表面缺陷检测算法 [J]. 中国机械工程 , 2019 , 30 ( 3 ): 266 - 270
Kurhan D , Havrylov M . Mathematical Support of Machine Surfacing for the Railway Track [J]. Acta Technica Jaurinensis , 2020 , 13 ( 3 ): 246 - 267
张蒙蒙 , 李伟 , 刘欢 , 等 . 基于形态变换与空间逻辑聚合的高光谱森林树种分类 [J]. 测绘学报 , 2023 , 52 ( 7 ): 1 202 - 1 211
孙昆襄 , 丁雨淋 , 曾浩炜 , 等 . 基于精细DEM的同震滑坡隐患自动提取方法 [J]. 测绘地理信息 , 2022 , 47 ( 4 ): 82 - 86
Gan Jinrui , Li Qingyong , Wang Jianzhu , et al . A Hierarchical Extractor-Based Visual Rail Surface Inspection System [J]. IEEE Sensors Journal , 2017 , 17 ( 23 ): 7 935 - 7 944
Li Qingyong , Shi Zhiping , Zhang Huayan , et al . A Cyber-Enabled Visual Inspection System for Rail Corrugation [J]. Future Generation Computer Systems , 2018 , 79 : 374 - 382
0
Views
1
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621