摘要
衬砌线识别作为隧道缺陷检测分析的关键步骤,长期面临检测数据解析困难问题,为突破传统解析方法的局限性,提高解析结果的准确性、鲁棒性,本文对CenterNet算法进行改进,提出了受监督热图算法的隧道衬砌线关键点识别算法。该算法主要分为关键点检测和曲线拟合两个阶段,包括网格分类任务、外围点监督、抗噪声扰动3种改进方法。双阶段共同训练时,在关键点检测阶段,首先,新增网格分类任务,依据分类结果监督热图拟合过程,以改进CenterNet算法对于密集关键点的热图拟合能力;其次,在训练的前10轮中额外输出一定数量外围点热图,通过外围点监督热图拟合,配合网络分类任务改进热图拟合能力。曲线拟合阶段微调训练时,对该阶段的输入加入抗噪声扰动,以缓解图像噪声干扰。为验证本文算法的改进效果,构建了隧道衬砌数据集,先验证单独使用网格分类任务、外围点监督、抗噪声扰动3种具体改进方法对衬砌线识别的影响;再通过消融实验,进一步展示3种改进方法的组合对算法识别结果的影响。实验结果表明:本文算法对比CenterNet和CornerNet算法识别效果提升明显,使用网格分类任务识别的曲线间距误差均降低约0.4个像素点;训练过程前10轮使用8~10个外围点监督模型学习,识别效果提升最大;抗噪声扰动强度σ为0.08时识别效果最佳,且抗噪声扰动强度不宜过大;此外,以上3种改进方法的任意组合均能有效提升识别效果。本文提出的受监督热图隧道雷达数据衬砌线识别算法可为工程建设领域探地雷达无损检测数据解译工作提供技术支撑。
Objective As a critical step in tunnel defect detection and analysis,lining line identification has long faced challenges in analyzing detection data.This study proposes using supervised heatmap algorithms and anti-noise disturbance techniques to recognize keypoints of lining lines,based on the CenterNet algorithm,to overcome the limitations of traditional analysis methods and enhance the accuracy and robustness of the results.Methods The algorithm is divided into two stages:keypoint detection and curve fitting.It includes three improvement methods:grid classification task,peripheral point supervision,and anti-noise disturbance.Initially,during the two-stage training process,the keypoint detection phase aims to improve the CenterNet algorithm’s limited heatmap fitting capability for dense keypoints by incorporating a heatmap grid classification task.The grid sequence,aligned in the vertical(A-scan)direction,is divided equally into several segments.These segments are categorized based on the location of keypoints within the sequence.A transformer is employed to learn the mapping from grid sequences to classification labels through supervised training.This supervision of the heatmap fitting process is based on the classification results.Simultaneously,a certain number of outer-point heatmaps are produced in the initial training rounds,and the model’s learning process is constrained through the positional information between outer points and keypoints.In the fine-tuning stage of curve fitting,Gaussian noise is introduced to the curve,and anti-noise disturbance is applied to counteract image noise interference.Finally,the tunnel lining dataset,divided into training,validation,and test sets,is utilized.The training set contains 3200 images with 753562 keypoints and a data size of 12.35 GB.The validation set comprises 600 images with 188635 keypoints and a data size of 2.88 GB.The test set consists of 999 images,including 236742 keypoints,and a data size of 3.52 GB.This dataset is test data in the experimental stag
作者
宋恒
张宜声
耿天宝
王东杰
SONG Heng;ZHANG Yisheng;GENG Tianbao;WANG Dongjie(Management and Technol.Inst.,China Railway No.4 Eng.Group Co.,Ltd.,Hefei 230000,China)
出处
《工程科学与技术》
EI
CAS
CSCD
北大核心
2024年第4期78-87,共10页
Advanced Engineering Sciences
基金
中国中铁股份有限公司2021年度揭榜挂帅重大项目(2021-重大-14)。
关键词
探地雷达
衬砌线检测
网格分类任务
外围点监督
抗噪声扰动
ground penetrating radar
lining line detection
grid classification task
outer-points supervision
anti-noise disturbance
