Journal Article

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

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

2021

Overview

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.

• Publisher: MDPI AG
• Subject: Adaptability / Artificial neural networks / Concrete / Data acquisition / data augmentation / data collection / Datasets / Deep learning / Expected values / fields / Generative adversarial networks / Ground penetrating radar / ground penetrating radar (GPR) / image analysis / least square generative adversarial networks (LSGAN) / Least squares / Neural networks / Object recognition / Radar / Radar imaging / Remote sensing / Training