Intelligent Recognition Method for Tunnel Smooth Blasting Borehole Residues Based on Cascade Mask Region-Convolutional Neural Network-ResNeSt
(1.Guizhou Road and Bridge Group Co., Ltd.,Guiyang 550001; 2. School of Civil Engineering, Central South University, Changsha 410075; 3.Chongqing Geological Exploration and Mineral Resources Development Group Inspection and Testing Co., Ltd., Chongqing 400700)
Abstract：
In order to solve the problems such as insufficient recognition accuracy, low robustness, and slow detec‐ tion speed in existing methods for recognizing tunnel borehole residues, an algorithm named Cascade Mask RegionConvolutional Neural Network (Cascade Mask R-CNN) is proposed. This algorithm is based on the Cascade Mask R-CNN instance segmentation algorithm and utilizes the advanced ResNeSt network as its backbone (Cascade Mask R-CNN-S) to enhance the feature extraction capability, thereby improving recognition accuracy. Multi-scale training methods and learning rate adjustment strategies are employed to train the network, resulting in an intelligent recognition model that enhances the robustness of the recognition algorithm. The model's performance was compared to traditional algorithms like Cascade Mask R-CNN and Mask R-CNN using mean average precision (mAP) as the evaluation metric. The study shows that the improved algorithm achieves an average precision value of 0.415 for bounding boxes (b_mAP(50)) and 0.350 for segmentation (s_mAP(50)) at an IoU threshold of 0.5. Compared to traditional instance segmentation algorithms, the improved algorithm significantly enhances the accuracy of tunnel borehole residue recognition, with a length recognition error of only 8.3%. It also demonstrates better robustness and anti-interference capabilities in the complex working environment of tunnels.
KUANG Huajiang1 LIU Guanghui1 LI Dalin1 XU Xiao1 YANG Weikang1 YANG Tingfa1 DENG Xingxing1ZHAGN Yunbo2 TIAN Maohao3
.Intelligent Recognition Method for Tunnel Smooth Blasting Borehole Residues Based on Cascade Mask Region-Convolutional Neural Network-ResNeSt[J] MODERN TUNNELLING TECHNOLOGY, 2024,V61(5): 99-110
2024, Vol. 61 