Application of Deep Learning in Ground Penetrating Radar Image Recognition

2021 ◽  
Author(s):  
Yang Jie ◽  
Song Fubin ◽  
Zhang Pengli ◽  
Wang Jiaming ◽  
Cui Chao
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Ground Penetrating Radar ◽  
Radar Image ◽  
Ground Penetrating

scholarly journals Research on GPR image recognition based on deep learning

2020 ◽  
Vol 309 ◽  
pp. 03027
Author(s):  
Zhimin Gong ◽  
Huaiqing Zhang
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Ground Penetrating Radar ◽  
Simulation Software ◽  
Accuracy Rate ◽  
Data Set ◽  
Average Accuracy ◽  
Recognition Ability ◽  
Ground Penetrating ◽  
Traditional Image

It is difficult for traditional image recognition methods to accurately identify ground penetrating radar (GPR) images. This paper proposes a deep-learning based Faster R-CNN algorithm for the automatic classification and recognition of GPR images. Firstly, GPR images with different features were obtained by using gprMax, a professional GPR simulation software. Then, the feature of the target in the image was taken as the recognition object and the data set was made. Finally, Faster R-CNN’s recognition ability of GPR images was analyzed from various accuracy, average accuracy and other indicators. The results showed that Faster R-CNN could successfully identify GPR images and accurately classify them, with an average accuracy rate of 93.9%.

A Ground-penetrating Radar Object Detection Method Based on Deep Learning

2021 ◽  
Author(s):  
Siyu Chen ◽  
Li Wang ◽  
Zheng Fang ◽  
Zhensheng Shi ◽  
Anxue Zhang
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Ground Penetrating Radar ◽  
Detection Method ◽  
Ground Penetrating

scholarly journals Application of Ground Penetrating Radar in Detecting Deeply Embedded Reinforcing Bars in Pile Foundation

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Daochuan Zhou ◽  
Haitang Zhu
Keyword(s):  
Ground Penetrating Radar ◽  
Pile Foundation ◽  
Field Testing ◽  
Radar Image ◽  
Reinforcing Bars ◽  
Raw Data ◽  
Centre Frequency ◽  
Wave Interference ◽  
Concrete Pile ◽  
Ground Penetrating

Ground penetrating radar (GPR) has been widely used for nondestructive testings in civil engineering. However, the GPR has not been adequately applied in detecting deeply embedded reinforcing bars, which is usually difficult to be revealed in radar image due to the wave interference and attenuation in large depth penetration. This study presents a new approach for the GPR detection of deeply embedded reinforcing bars in the reinforced concrete pile foundation. The aim of the GPR survey is to determine the existence and the depth of internal reinforcing bars in the pile foundation for solving engineering dispute. Low centre frequency antenna was used in GPR field testing to obtain the reflected raw data. Optimized procedures of digital filtering techniques were applied to process the GPR raw data. The deeply embedded reinforcing bars are revealed in the radar image after the field testing and postprocessing procedures. The depth of the reinforcing bars was estimated based on the hyperbola match method. The GPR test results were validated by the excavation of the pile foundation. The low centre frequency antenna has been found to be essential to obtain the reflected wave signals of deeply embedded reinforcing bars. The optimized processing procedures is useful to identify and display the reinforcing bars in radar image. The combination of low centre frequency antenna and the postprocessing procedures make the detection of deeply embedded reinforcing bars feasible. The proposed GPR testing method has been found to be effective to estimate the depth of deeply embedded reinforcing bars, which provides the key information for solving engineering dispute.

Sign in / Sign up

Export Citation Format

Share Document