摘要
为了提高隧道排水孔结晶淤堵情况的检测速度以及淤堵程度定性分析的精确程度,探究并使用了一种语义分割卷积神经网络模型DeepLab v3+resnet18,对隧道排水孔图像进行识别。将230张排水孔图像中的成分划分为“结晶”“、排水孔壁”和“其他”三个类别,并以138张图像(样本总数的60%)训练DeepLab v3+resnet18模型,之后92张(样本总数的40%)图像进行预测。结果表明,基于此语义分割网络模型的全局准确度达95%,其中结晶类的预测准确度在75%以上,达到了对排水孔结晶淤堵图像定性分析的基本要求。此外,还将此语义分割卷积神经网络模型自编至MATLAB APP中,能够让工作人员容易、方便地进行排水孔结晶淤堵病害的图像检测(预测)工作。
In order to improve the detection speed for siltation of tunnel drainage holes by crystals and the accuracy of qualitative analysis of siltation degree, this paper explores and uses a convolutional neural network of semantic segmentation(DeepLab v3+ resnet18) to recognize the images of tunnel drainage holes. In this paper, the components in 230 drainage hole images were split into three categories: "crystal", "drainage hole wall" and "others". Furthermore, 138 images(60% of the total samples) were used to train the DeepLab v3+ resnet18 model, and the remaining 92 images(40% of the total samples) were used for image prediction. The results showed that the global accuracy based on this semantic segmentation model was up to 95%, and the prediction accuracy of crystals was over75%, complying with the basic requirements for qualitative analysis of images of drainage hole siltation by crystals.In addition, this convolutional neural network of semantic segmentation was also self-programmed in MATLAB APP, so that staff could easily and conveniently detect(and predict) the images of drainage hole siltation by crystals.
作者
刘文建
张国才
吕建兵
刘锋
吴维俊
陈贡发
LIU Wenjian;ZHANG Guocai;LV Jianbing;LIU Feng;WU Weijun;CHEN Gongfa(CCCC Guanglian Expressway Investment Development Co.,Ltd.,Qingyuan 511500;CCCC Fourth Harbour Engineering Research Institute Co.,Ltd,Guangzhou 510220;School of Civil and Transportation Engineering,Guangdong University of Technology,Guangzhou 510006)
出处
《现代隧道技术》
CSCD
北大核心
2022年第4期100-107,共8页
Modern Tunnelling Technology
关键词
排水孔结晶淤堵
图像检测
语义分割
卷积神经网络
APP
Drainage hole siltation by crystals
Image detection
Semantic segmentation
Convolutional neural network
APP