基于TSCD模型的轨道板裂缝检测方法

doi:10.3969/j.issn.0255-8297.2022.01.014

应用科学学报 ›› 2022, Vol. 40 ›› Issue (1): 155-166.doi: 10.3969/j.issn.0255-8297.2022.01.014

基于TSCD模型的轨道板裂缝检测方法

李文举^1,2, 张耀星¹, 陈慧玲², 李培刚¹, 沙利业³

1. 上海应用技术大学轨道交通学院, 上海 201418;
2. 上海应用技术大学计算机科学与信息工程学院, 上海 201418;
3. 上海普利森配料系统有限公司, 上海 201108

收稿日期:2021-07-14 出版日期:2022-01-28 发布日期:2022-01-28
通信作者: 李培刚,博士,讲师,研究方向为高速、重载及交通轨道结构。E-mail:lipeigang@sit.edu.cn E-mail:lipeigang@sit.edu.cn
基金资助:
上海市科技创新行动计划基金（No.21210750300）资助

Track Slab Crack Detection Method Based on TSCD Model

LI Wenju^1,2, ZHANG Yaoxing¹, CHEN Huiling², LI Peigang¹, SHA Liye³

1. School of Railway Transportation, Shanghai Institute of Technology, Shanghai 201418, China;
2. School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201418, China;
3. Shanghai Prinsen Dosing & Weighting System Co., Ltd, Shanghai 201108, China

Received:2021-07-14 Online:2022-01-28 Published:2022-01-28

摘要/Abstract

摘要： 为解决轨道板裂缝检测问题，提出了一种基于分支级联卷积神经网络的轨道板裂缝检测模型--TSCD。首先该模型通过注意力机制和搜索分支结构突出轨道板裂缝的位置信息，同时抑制干扰信息；然后采用检测分支结构完成裂缝的像素级检测；最后对检测结果中出现的图像细节退化问题，利用参数映射关系实现特征图的上采样。实验结果表明：所提出的方法能够准确地检测出轨道板表面图像中的裂缝，其像素准确率可达97.56%，F1-score可达86.28%，并且在跨数据集测试中表现出较强的泛化性。

关键词: 裂缝检测, 分支级联, 参数映射, 轨道板, 卷积神经网络

Abstract: In order to solve the problem of track slab crack detection, a track slab crack detection model based on branch cascaded convolutional neural network, TSCD, is proposed. First, the model highlights the position information of track slab cracks through attention mechanism and structure of search branches to suppress interference information. Second, it realizes the pixel-level detection of cracks by structure of detecting branches. Finally, in order to solve the problem of image detail degradation in detection results, parameter mapping is used to achieve up-sampling of the feature maps. Experimental results show that the proposed model in this paper can not only detect the cracks in track plate surface images accurately with pixel accuracy rate of 97.56% and F1-score of 86.28%, but also performs strong generalization in cross-dataset tests.

Key words: crack detection, branch cascade, parameter mapping, track plate, convolutional neural network

中图分类号:

TN911.73

李文举, 张耀星, 陈慧玲, 李培刚, 沙利业. 基于TSCD模型的轨道板裂缝检测方法[J]. 应用科学学报, 2022, 40(1): 155-166.

LI Wenju, ZHANG Yaoxing, CHEN Huiling, LI Peigang, SHA Liye. Track Slab Crack Detection Method Based on TSCD Model[J]. Journal of Applied Sciences, 2022, 40(1): 155-166.

参考文献

[1] 罗超, 黄成洋. 无砟轨道底座板混凝土裂缝的研究[J]. 工程建设与设计, 2019(10):192-193. Luo C, Huang C Y. Research on concrete cracks in the base slab of ballastless track[J]. Engineering Construction and Design, 2019(10):192-193. (in Chinese)
[2] Fan D P, Ji G P, Sun G, et al. Camouflaged object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:2777-2787.
[3] 王登涛, 李再帏, 何越磊, 等. 基于热成像的高速铁路轨道板表面裂缝检测方法研究[J]. 铁道标准设计, 2020, 64(7):22-28. Wang D T, Li Z W, He Y L, et al. Research on surface crack detection method of high-speed railway track slab based on thermal imaging[J]. Railway Standard Design, 2020, 64(7):22-28. (in Chinese)
[4] 王登涛, 路宏遥, 孟翔震, 等. 轨道板表面裂缝的热成像检测效果仿真分析[J]. 智能计算机与应用, 2020, 10(2):132-137. Wang D T, Lu H Y, Meng X Z, et al. Simulation analysis of thermal imaging detection effect of track plate surface cracks[J]. Intelligent Computers and Applications, 2020, 10(2):132-137. (in Chinese)
[5] 章梦. 基于图像处理的轨道裂缝检测技术的研究[D]. 上海:上海应用技术大学, 2019.
[6] 薛峰, 赵丽科, 柴雪松, 等. 基于图像处理的铁路轨道板裂缝检测研究[J]. 铁道建筑, 2015(12):123-126. Xue F, Zhao L K, Chai X S, et al. Study on detecting crack in railway track slab based on image processing technology[J]. Railway Engineering, 2015(12):123-126. (in Chinese)
[7] 战友, 阳恩慧, 马啸天, 等. 无砟轨道板裂缝三维激光检测系统研发与算法验证[J]. 铁道学报, 2021, 43(7):114-120. Zhan Y, Yang E H, Ma X T, et al. Development and algorithm verification of a threedimensional laser inspection system for cracks in ballastless track slabs[J]. Journal of the China Railway Society, 2021, 43(7):114-120. (in Chinese)
[8] 沈子豪. 基于机器视觉的CRTS II型轨道板裂缝检测技术研究[D]. 上海:上海应用技术大学, 2020.
[9] Fang F, Li L, Gu Y, et al. A novel hybrid approach for crack detection[J]. Pattern Recognition, 2020, 107:107-118.
[10] 李良福, 马卫飞, 李丽, 等. 基于深度学习的桥梁裂缝检测算法研究[J]. 自动化学报, 2019, 45(9):1727-1742. Li L F, Ma W F, Li L, et al. Research on bridge crack detection algorithm based on deep learning[J]. Journal of Automatica Sinica, 2019, 45(9):1727-1742. (in Chinese)
[11] 翁飘, 陆彦辉, 齐宪标, 等. 基于改进的全卷积神经网络的路面裂缝分割技术[J]. 计算机工程与应用, 2019, 55(16):235-239, 245. Weng P, Lu Y H, Qi X B, et al. Road crack segmentation technology based on improved fully convolutional neural network[J]. Computer Engineering and Applications, 2019, 55(16):235-239, 245. (in Chinese)
[12] 朱苏雅, 杜建超, 李云松, 等. 采用U-Net卷积网络的桥梁裂缝检测方法[J]. 西安电子科技大学学报, 2019, 46(4):35-42. Zhu S Y, Du J C, Li Y S, et al. Bridge crack detection method using U-Net convolutional network[J]. Journal of Xidian University, 2019, 46(4):35-42. (in Chinese)[1] 罗超, 黄成洋. 无砟轨道底座板混凝土裂缝的研究[J]. 工程建设与设计, 2019(10):192-193. Luo C, Huang C Y. Research on concrete cracks in the base slab of ballastless track[J]. Engineering Construction and Design, 2019(10):192-193. (in Chinese)
[2] Fan D P, Ji G P, Sun G, et al. Camouflaged object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:2777-2787.
[3] 王登涛, 李再帏, 何越磊, 等. 基于热成像的高速铁路轨道板表面裂缝检测方法研究[J]. 铁道标准设计, 2020, 64(7):22-28. Wang D T, Li Z W, He Y L, et al. Research on surface crack detection method of high-speed railway track slab based on thermal imaging[J]. Railway Standard Design, 2020, 64(7):22-28. (in Chinese)
[4] 王登涛, 路宏遥, 孟翔震, 等. 轨道板表面裂缝的热成像检测效果仿真分析[J]. 智能计算机与应用, 2020, 10(2):132-137. Wang D T, Lu H Y, Meng X Z, et al. Simulation analysis of thermal imaging detection effect of track plate surface cracks[J]. Intelligent Computers and Applications, 2020, 10(2):132-137. (in Chinese)
[5] 章梦. 基于图像处理的轨道裂缝检测技术的研究[D]. 上海:上海应用技术大学, 2019.
[6] 薛峰, 赵丽科, 柴雪松, 等. 基于图像处理的铁路轨道板裂缝检测研究[J]. 铁道建筑, 2015(12):123-126. Xue F, Zhao L K, Chai X S, et al. Study on detecting crack in railway track slab based on image processing technology[J]. Railway Engineering, 2015(12):123-126. (in Chinese)
[7] 战友, 阳恩慧, 马啸天, 等. 无砟轨道板裂缝三维激光检测系统研发与算法验证[J]. 铁道学报, 2021, 43(7):114-120. Zhan Y, Yang E H, Ma X T, et al. Development and algorithm verification of a threedimensional laser inspection system for cracks in ballastless track slabs[J]. Journal of the China Railway Society, 2021, 43(7):114-120. (in Chinese)
[8] 沈子豪. 基于机器视觉的CRTS II型轨道板裂缝检测技术研究[D]. 上海:上海应用技术大学, 2020.
[9] Fang F, Li L, Gu Y, et al. A novel hybrid approach for crack detection[J]. Pattern Recognition, 2020, 107:107-118.
[10] 李良福, 马卫飞, 李丽, 等. 基于深度学习的桥梁裂缝检测算法研究[J]. 自动化学报, 2019, 45(9):1727-1742. Li L F, Ma W F, Li L, et al. Research on bridge crack detection algorithm based on deep learning[J]. Journal of Automatica Sinica, 2019, 45(9):1727-1742. (in Chinese)
[11] 翁飘, 陆彦辉, 齐宪标, 等. 基于改进的全卷积神经网络的路面裂缝分割技术[J]. 计算机工程与应用, 2019, 55(16):235-239, 245. Weng P, Lu Y H, Qi X B, et al. Road crack segmentation technology based on improved fully convolutional neural network[J]. Computer Engineering and Applications, 2019, 55(16):235-239, 245. (in Chinese)
[12] 朱苏雅, 杜建超, 李云松, 等. 采用U-Net卷积网络的桥梁裂缝检测方法[J]. 西安电子科技大学学报, 2019, 46(4):35-42. Zhu S Y, Du J C, Li Y S, et al. Bridge crack detection method using U-Net convolutional network[J]. Journal of Xidian University, 2019, 46(4):35-42. (in Chinese)

[1]	朱丽, 杨青, 吴涛, 李晨, 李铭. 基于CNN和Bi-LSTM的脑电波情感分析[J]. 应用科学学报, 2022, 40(1): 1-12.
[2]	周传华, 徐文倩, 朱俊杰. 基于代价敏感卷积神经网络的集成分类算法[J]. 应用科学学报, 2022, 40(1): 69-79.
[3]	郑长亮, 庞明. 基于卷积神经网络的时空权重姿态运动特征提取算法[J]. 应用科学学报, 2021, 39(4): 594-604.
[4]	查玉坤, 张其林, 赵永标, 杭波. 基于三维卷积和CLSTM神经网络的水产养殖溶解氧预测[J]. 应用科学学报, 2021, 39(4): 615-626.
[5]	李文举, 何茂贤, 张耀星, 陈慧玲, 李培刚. 基于卷积神经网络和投票机制的轨道板裂缝检测[J]. 应用科学学报, 2021, 39(4): 627-640.
[6]	郝琰, 石慧宇, 霍首君, 韩丹, 曹锐. 基于脑电信号深度学习的情感分类[J]. 应用科学学报, 2021, 39(3): 347-346.
[7]	崔鹏涛, 张倩, 刘敬怀, 周超, 王斌, 司文. 基于FSCD-CNN的深度图像快速帧内预测模式选择算法[J]. 应用科学学报, 2021, 39(3): 433-432.
[8]	李磊, 张青苗, 赵军辉, 聂逸文. 基于改进CNN-LSTM组合模型的分时段短时交通流预测[J]. 应用科学学报, 2021, 39(2): 185-198.
[9]	张涵, 秦昆, 毕奇, 张晔, 许凯. 注意力引导的三维卷积网络用于遥感场景变化检测[J]. 应用科学学报, 2021, 39(2): 272-280.
[10]	刘之瑜, 张淑芬, 刘洋, 罗长银, 李敏. 基于图像梯度的数据增广方法[J]. 应用科学学报, 2021, 39(2): 302-311.
[11]	王孟轩, 张胜, 王月, 雷霆, 杜渂. 改进的CRNN模型在警情文本分类中的研究与应用[J]. 应用科学学报, 2020, 38(3): 388-400.
[12]	马鑫, 吴云, 鹿泽光. 基于混合神经网络的协同过滤推荐模型[J]. 应用科学学报, 2020, 38(3): 478-487.
[13]	刘伟, 章琬苓, 项世军. 基于LBP-MDCT和CNN的人脸活体检测算法[J]. 应用科学学报, 2019, 37(5): 609-617.
[14]	王灿军, 廖鑫, 陈嘉欣, 秦拯, 刘绪崇. 基于卷积神经网络的面部图像修饰检测[J]. 应用科学学报, 2019, 37(5): 618-630.
[15]	吴韵清, 吴鹏, 陈北京, 鞠兴旺, 高野. 基于残差全卷积网络的图像拼接定位算法[J]. 应用科学学报, 2019, 37(5): 651-662.

基于TSCD模型的轨道板裂缝检测方法

Track Slab Crack Detection Method Based on TSCD Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价