Generation of High-Precision Ground Penetrating Radar Images Using Improved Least Square Generative Adversarial Networks

Yanliang Du,Hai Liu,Yunpeng Yue,Xu Meng,Yinguang Li

doi:10.3390/rs13224590

Abstract

Deep learning models have achieved success in image recognition and have shown great potential for interpretation of ground penetrating radar (GPR) data. However, training reliable deep learning models requires massive labeled data, which are usually not easy to obtain due to the high costs of data acquisition and field validation. This paper proposes an improved least square generative adversarial networks (LSGAN) model which employs the loss functions of LSGAN and convolutional neural networks (CNN) to generate GPR images. This model can generate high-precision GPR data to address the scarcity of labelled GPR data. We evaluate the proposed model using Frechet Inception Distance (FID) evaluation index and compare it with other existing GAN models and find it outperforms the other two models on a lower FID score. In addition, the adaptability of the LSGAN-generated images for GPR data augmentation is investigated by YOLOv4 model, which is employed to detect rebars in field GPR images. It is verified that inclusion of LSGAN-generated images in the training GPR dataset can increase the target diversity and improve the detection precision by 10%, compared with the model trained on the dataset containing 500 field GPR images.

Highlights

Ground penetrating radar (GPR) is a popular geophysical technique and has been widely applied to near-surface investigation [1,2], archaeological prospection [3,4], hydrological investigation [5], lunar exploration [6], and civil engineering [7]
Since GPR data acquisition can operated at an ultra-fast speed, both detection accuracy and speed of be a deep learning model are important in thethe accuracy and speed of a deep learning model are important in the application narios
We propose an improved least square generative adversarial networks (LSGAN) for generation of GPR images to deal with the insufficient GPR images with labels for training the deep learning models with an aim of automatic subsurface target detection

Summary

Introduction

Ground penetrating radar (GPR) is a popular geophysical technique and has been widely applied to near-surface investigation [1,2], archaeological prospection [3,4], hydrological investigation [5], lunar exploration [6], and civil engineering [7]. GPR is used to detect voids, seepage, and rebar defects [8,9]. GPR is commonly used to measure reinforcement position, concrete thickness, and reinforcement corrosion degree [10,11]. With the rapid increase of detection requirements in civil engineering, GPR has been become a regular method for inspecting reinforced bars (rebars) in concrete, locating subsurface pipelines, structural performance evaluation, etc. Even for an experienced practitioner, interpretation of GPR data is extremely time- and labor-consuming due to complex field conditions and huge data volumes. Field data detected by a car-mounted GPR system in a day would take one week or even longer to be comprehensively interpreted [15]. The low efficiency of manual interpretation is a major factor that limits the fast decision-making for maintenance and rehabilitation [16,17]

Methods

Results

Discussion

Conclusion