Instance Segmentation and Length Quantification Analysis of Tunnel Face Joints

Abstract Accurate segmentation and quantitative analysis of tunnel face joints are crucial for optimizing blasting parameters and ensuring construction safety. However, in complex tunnel environments, existing segmentation algorithms suffer from insufficient accuracy in segmenting small, elongated joint targets, leading to significant errors in subsequent length quantification. To address this issue, this paper proposes a segmentation algorithm U2Y11FL for the joint target of the tunnel face. The U2Y11FL algorithm utilizes UNetV2's encoder to extract basic features of the fractures, subsequently introduces the FDPN module to integrate feature information from different levels, and finally employs the LAWDS module for down-sampling. On a self-constructed joint dataset, the mask segmentation accuracy rate and Dice coefficient of U2Y11FL reach 85.4% and 72.9% respectively. On three open-source crack datasets, it demonstrated strong generalization capabilities with Dice coefficients as high as 85.6%, 79.4% and 76.5%. Based on this, a fractal approximation algorithm using chain codes was adopted to quantify the length characteristics of joints. By compensating for joint fractures occurring during the skeleton extraction stage in the original algorithm, the relative error between the quantified results and measured values was reduced to 2.2%~9.7%, providing an effective method for quantitative analysis of tunnel face joints.

Ҳали таржима қилинмаган