High-Speed Acquisition and Intelligent Tunnel Surface Defects Recognition

作     者：Wang, Yaodong Liao, Weisheng Dong, Anqi Xu, Lizhi Zhu, Liqiang Shi, Hongmei 

作者机构：School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Collaborative Innovation Center of Railway Traffic Safety Beijing China Department of Mechanical and Aerospace Engineering University of California IrvineCA United States 

出 版 物：《SSRN》 

年 卷 期：2023年

核心收录：

主　　题：Structural health monitoring 

摘      要：We introduce a framework to efficiently capture and identify the defects on the subway tunnel surfaces. Specifically, we design a high-speed multi-camera-synchronous acquisition system for scanning the tunnel surfaces and capturing the cracks from images. We propose an Improved Cascade Region-Based Convolutional Neural Network (R-CNN) method to locate and classify defects, with the crack being refined by image processing algorithms. The methodology is tested by on-site experiments carried out in an operational subway. The mAP value reaches 0.827, with a specific AP value of 0.625 and a newly proposed measure identification rate of 0.942 for crack objects. Notably, by training on bounding box labels, our overall algorithm exhibits the lowest Error Rate (ER) and the highest Intersection over Union (IoU) across all test images, surpassing the performance of classical semantic segmentation networks trained on pixel-level labels. © 2023, The Authors. All rights reserved.