Page 98 - 无损检测2024年第六期

缺陷的智能识别与分类专题
缺陷的智能识别与分类专题

DOI：10.11973/wsjc202406011

基于 Mask R-CNN 模型的铁路隧道衬砌机制

砂混凝土裂缝视觉检测

蒋志超，贺兆鹏
（陕西建工集团股份有限公司，西安 710003）

摘 要：铁路隧道衬砌结构裂缝图像具有复杂的灰度分布和变化特征，局部和全局的多特征信
息会干扰跟踪方向和边界跟踪参数，模型可扩展性受限，检测准确率较低。为此，提出基于Mask
R-CNN模型的铁路隧道衬砌机制砂混凝土裂缝视觉检测方法。首先输入分段线性变换后的砂混凝
土裂缝图像，抽取阈值，生成连通域标识，再以像素点为背景点，在Mask R-CNN模型中，同时检测
裂缝区域的位置和标记像素级的边缘掩膜，判定裂缝边界起点与裂缝宽度；然后进行累加视觉检测
方法设计，按照裂缝的几何特征以及排序结果，求解裂缝长度，获得完整的裂缝轮廓。试验结果表
明，所提方法可以较为完整地检测所有关键位置，裂缝参数信息检测准确率较高；迭代次数升高后，
检测结果受到的影响较小，可扩展性得到了改善，可适应任务需求，具有较好的应用价值。
关键词：Mask R-CNN模型；铁路隧道；衬砌机制；砂混凝土裂缝；视觉检测
中图分类号：U446；TG115.28 文献标志码：A 文章编号：1000-6656(2024)06-0060-06

Visual detection of sand concrete cracks in railway tunnel lining mechanism
based on Mask R-CNN model

JIANG Zhichao, HE Zhaopeng
（Shaanxi Construction Engineering Group Co., Ltd., Xi'an 710003，China）

Abstract: The crack image of railway tunnel lining structure has complex grayscale distribution and variation
characteristics, and local and global multi feature information interferes with tracking direction and boundary tracking
parameters. The model’s scalability is limited, and the detection accuracy is low. Therefore, a visual detection of sand
concrete cracks in railway tunnel lining mechanism based on Mask R-CNN model was proposed. Firstly, after inputting the
segmented linear transformation of the sand concrete crack image, a threshold was extracted to generate a connected domain
identifier. Pixel points were used as background points in the Mask R-CNN model to simultaneously detect the position of
the crack area and mark pixel level edge masks, the starting point and width of the crack boundary was determined, and a
cumulative visual detection method was designed. Based on the geometric characteristics and sorting results of the cracks,
the crack length was calculated, and the complete crack contour was obtained. The experimental results showed that after
using the method proposed in this paper, all key positions can be detected completely; After increasing the number of
iterations, the detection results were less affected, indicating that its scalability had been improved and can adapt to task
requirements; and therefore, it has good application value.
Key words: Mask R-CNN model; railway tunnel; lining mechanism; sand concrete crack; visual inspection

在铁路隧道衬砌机制中，速凝剂按照一定掺量
收稿日期：2023-11-02
与水泥发生反应，同时减水剂也存在保塌与缓凝成
作者简介：蒋志超（1983—），男，硕士，高级工程师，主要从事房
分。在实际喷射混凝土过程中 ，考虑到水灰比和
[1]
建施工与混凝土质量控制管理工作
用水量的问题，无限制地增加减水剂用量，会带来减
通信作者：蒋志超，sdsefv6@yeah.net
60
2024 年 第 46 卷 第 6 期
无损检测