Two-Stage GPR Image Inversion Method Based on Multi-Scale Dilated Convolution and Hybrid Attention Gate
Open Access
- 17 January 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (2) , 322
Abstract
Ground penetrating radar (GPR) image inversion is of great significance for interpreting GPR data. In practical applications, the complexity and nonuniformity of underground structures bring noise and clutter interference, making GPR inversion problems more challenging. To address these issues, this study proposes a two-stage GPR image inversion network called MHInvNet based on multi-scale dilated convolution (MSDC) and hybrid attention gate (HAG). This method first denoises the B-scan through the first network MHInvNet1, then combines the denoised B-scan from MHInvNet1 with the undenoised B-scan as input to the second network MHInvNet2 for inversion to reconstruct the distribution of the permittivity of underground targets. To further enhance network performance, the MSDC and HAG modules are simultaneously introduced to both networks. Experimental results from simulated and actual measurement data show that MHInvNet can accurately invert the position, shape, size, and permittivity of underground targets. A comparison with existing methods demonstrates the superior inversion performance of MHInvNet.Keywords
Funding Information
- National Natural Science Foundation of China (62361015, AA21077008)
- Guangxi special fund project for innovation-driven development (62361015, AA21077008)
This publication has 14 references indexed in Scilit:
- DMRF-UNet: A Two-Stage Deep Learning Scheme for GPR Data Inversion Under Heterogeneous Soil ConditionsIEEE Transactions on Antennas and Propagation, 2022
- GPRInvNet: Deep Learning-Based Ground-Penetrating Radar Data Inversion for Tunnel LiningsIEEE Transactions on Geoscience and Remote Sensing, 2021
- Deep Neural Network-Based Permittivity Inversions for Ground Penetrating Radar DataIEEE Sensors Journal, 2021
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks2020
- Multiscale Full-Waveform Dual-Parameter Inversion Based on Total Variation Regularization to On-Ground GPR DataIEEE Transactions on Geoscience and Remote Sensing, 2019
- Application of Ground Penetrating Radar (GPR) to Detect Joints in Organic Soft RockGeotechnical Testing Journal, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- High resolution GPR mapping of Late Bronze Age architecture at Kalavasos-Ayios Dhimitrios, CyprusJournal of Applied Geophysics, 2014
- Removal of wavelet dispersion from ground-penetrating radar dataGeophysics, 2003
- A Real-Time Algorithm for Signal Analysis with the Help of the Wavelet Transform1989