An Improved Convolutional Neural Network System for Automatically Detecting Rebar in GPR Data

Abstract

As a mature technology, Ground Penetration Radar (GPR) is now widely employed in detecting rebar and other embedded elements in concrete structures. Manually recognizing rebar from GPR data is a time-consuming and error-prone procedure. Although there are several approaches to automatically detect rebar, it is still challenging to find a high resolution and efficient method for different rebar arrangements, especially for closely spaced rebar meshes. As an improved Convolution Neural Network (CNN), AlexNet shows superiority over traditional methods in image recognition domain. Thus, this paper introduces AlexNet as an alternative solution for automatically detecting rebar within GPR data. In order to show the efficiency of the proposed approach, a traditional CNN is built as the comparative option. Moreover, this research evaluates the impacts of different rebar arrangements, and different window sizes on the accuracy of results. The results revealed that: (1) AlexNet outperforms the traditional CNN approach, and its superiority is more notable when the rebar meshes are densely distributed; (2) the detection accuracy significantly varies with changing the size of splitting window, and a proper window should contain enough information about rebar; (3) uniformly and sparsely distributed rebar meshes are more recognizable than densely or unevenly distributed items, due to lower chances of signal interferences.

Arbitrarily-oriented tunnel lining defects detection from Ground Penetrating Radar images using deep Convolutional Neural networks

“…Tong et al [15] utilized the deep learning model of network in networks and GPR data to identify pavement distress types and measure the distress locations and sizes, which produced reasonable stability with different transmitting frequencies, numbers of samples per trace, and pavement structures. For rebar inspection, Xiang et al [16] automatically detected the rebars of concrete structures using AlexNet and GPR images. The authors also evaluated the effects of different rebar arrangements and window sizes on the results.…”

Training data augmentations for improving hyperbola recognition in ground penetrating radar B-scan image for tree roots detection

“…Wen et al (2020) proposed a shearlet transform to perform noise removal from B-Scan images and achieved better denoising results in some image evaluation metrics. Deep learning models are being widely used to detect the internal structure of tree root systems (Xiang et al 2019;Hou et al 2021;Zhang et al 2021). Hou et al (2021) proposed using MS R-CNN architecture for the detection of GPR subsurface scanned objects, while using the transfer learning technique to obtain pre-trained models to solve the problem of the insufficient model training set (93 GPR root scans).…”

Deep Learning-Based Rebar Clutters Removal and Defect Echoes Enhancement in GPR Images

“…Liu et al [17] used an SSD (single shot multi-box detector) model to identify the hyperbolic regions of interest in GPR images, and then offset and binarized the target regions for the purpose of estimating the horizontal positions and depths of the rebar. Xiang et al [18] used the AlexNet network to realize end-to-end identifications of rebar in GPR images, which was found to improve the identification accuracy. In addition to rebar identifications, a great deal of research has been conducted regarding noise removal based on deep neural networks.…”