<<
[an error occurred while processing this directive] | [an error occurred while processing this directive] >>
Research on the Recognition Technology and APP for Sematic Segmentation of the Images of Drainage Hole Siltation by Crystals
(1. CCCC Guanglian Expressway Investment Development Co., Ltd., Qingyuan 511500; 2. CCCC Fourth Harbour Engineering Research Institute Co., Ltd, Guangzhou 510220; 3. School of Civil and Transportation Engineering, Guangdong University of Technology,Guangzhou 510006)
Abstract 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 over 75%, 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.
Abstract：
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 over 75%, 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.
LIU Wenjian1 ZHANG Guocai2 LV Jianbing3 LIU Feng3 WU Weijun3 CHEN Gongfa3
.Research on the Recognition Technology and APP for Sematic Segmentation of the Images of Drainage Hole Siltation by Crystals[J] MODERN TUNNELLING TECHNOLOGY, 2022,V59(4): 100-107
2022, Vol. 59 