当前位置: X-MOL 学术Autom. Constr. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improved Mask R-CNN with distance guided intersection over union for GPR signature detection and segmentation
Automation in Construction ( IF 9.6 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.autcon.2020.103414
Feifei Hou , Wentai Lei , Shuai Li , Jingchun Xi , Mengdi Xu , Jiabin Luo

Abstract Ground penetrating radar (GPR) has been used for non-destructive inspection of civil infrastructure systems such as bridges and pipelines. Manually extracting useful data from a large amount of non-intuitive GPR scans is tedious and error-prone. To address this challenge, a generalizable end-to-end framework is developed and implemented to simultaneously detect and segment object signatures in GPR scans. The proposed approach improves the Mask Region-based Convolutional Neural Network (R-CNN) by incorporating a novel distance guided intersection over union (DGIoU) as a new loss function for detection and segmentation. The DGIoU considers the center distance between two bounding boxes and overcomes the weakness of intersection over union (IoU) in training and evaluation. In addition, a new method is proposed to extract data points from the segmented mask patches containing both object signatures and background noises. The extracted data points can be further processed for object localization and characterization. Experiments were conducted using GPR scans collected from a concrete bridge deck. The hyperbolic signatures of rebars can be accurately detected and segmented using the proposed method. It was demonstrated that using DGIoU improves the regression effect of bounding box and mask. The improved Mask R-CNN achieved an average accuracy (AP) of 58.64% and 47.64% for the detection and segmentation task, respectively.

中文翻译:

用于 GPR 特征检测和分割的具有距离引导交集的改进 Mask R-CNN

摘要 探地雷达(GPR)已被用于桥梁和管道等民用基础设施系统的无损检测。从大量非直观 GPR 扫描中手动提取有用数据既乏味又容易出错。为了应对这一挑战,开发并实施了一个通用的端到端框架,以同时检测和分割 GPR 扫描中的对象签名。所提出的方法通过将一种新的距离引导交叉联合(DGIoU)作为检测和分割的新损失函数来改进基于掩膜区域的卷积神经网络(R-CNN)。DGIoU 考虑了两个边界框之间的中心距离,克服了训练和评估中的交集(IoU)的弱点。此外,提出了一种新方法来从包含对象特征和背景噪声的分割掩码块中提取数据点。提取的数据点可以进一步处理以进行对象定位和表征。使用从混凝土桥面板收集的 GPR 扫描进行了实验。使用所提出的方法可以准确地检测和分割钢筋的双曲线特征。结果表明,使用 DGIoU 提高了边界框和掩码的回归效果。改进后的 Mask R-CNN 在检测和分割任务中分别达到了 58.64% 和 47.64% 的平均准确率 (AP)。使用从混凝土桥面板收集的 GPR 扫描进行了实验。使用所提出的方法可以准确地检测和分割钢筋的双曲线特征。结果表明,使用 DGIoU 提高了边界框和掩码的回归效果。改进后的 Mask R-CNN 在检测和分割任务中分别达到了 58.64% 和 47.64% 的平均准确率 (AP)。使用从混凝土桥面板收集的 GPR 扫描进行了实验。使用所提出的方法可以准确地检测和分割钢筋的双曲线特征。结果表明,使用 DGIoU 提高了边界框和掩码的回归效果。改进后的 Mask R-CNN 在检测和分割任务中分别达到了 58.64% 和 47.64% 的平均准确率 (AP)。
更新日期:2021-01-01
down
wechat
bug