期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 61, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2023.3300276
关键词
Clutter; Principal component analysis; Permittivity; Training; Antennas; Finite difference methods; Estimation; Background removal; concrete; deep learning; finite-difference time-domain (FDTD); ground-penetrating radar (GPR); hyperbola fitting; machine learning (ML); migration; neural networks (NNs); processing; reverse-time migration (RTM)
The performance of ground-penetrating radar (GPR) is affected by cross coupling between the transmitter and the receiver, as well as the background response. Background clutter suppression and velocity estimation are crucial for effectively locating targets. A novel deep learning scheme combining artificial neural networks (ANNs) and principal component analysis (PCA) was developed, which accurately predicts the background clutter and estimates the background permittivity and conductivity. This scheme outperforms commonly used background removal techniques and conventional migration, making it effective for real complex scenarios.
The performance of ground-penetrating radar (GPR) is greatly influenced by the cross coupling between the transmitter and the receiver, and the response from the background. Their combined effect often masks the weaker target signals, especially in cases where shallow buried targets are present. Moreover, errors in velocity estimation result to over/under-migrated images, which further compromises the reliability of GPR, especially in case of nonhomogeneous media. Therefore, background clutter suppression and velocity estimation are both pivotal for effectively locating targets. For this purpose, a novel deep learning scheme for background clutter prediction was developed, where a two joint artificial neural networks (ANNs) architecture combined with principal component analysis (PCA) is implemented. In the suggested scheme, the first network predicts the background response, which is subsequently subtracted, while the second network estimates the background permittivity and conductivity. Subsequently, the permittivity profile along the measurement line is used as input in reverse-time migration (RTM) to focus the signal without the need of hyperbola fitting and homogeneity assumptions. The training data were generated synthetically using the finite-difference time-domain (FDTD) method. A model of a real GPR antenna is used in the simulations, making the scheme applicable to real data. The efficiency of the proposed method is validated using both numerical and real data, with successful predictions in all cases, demonstrating its ability to perform well even when tested with previously unseen real complex scenarios. Via a series of examples, the proposed scheme was proven superior to commonly used background removal techniques and conventional migration.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据