Surface Penetrating Radar and Other Non-Destructive Testing Methods
I have been working on the development of intelligent surface-penetrating radar systems. This research is highly interdisciplinary, drawing upon knowledge from advanced antenna systems, radar technologies, and artificial intelligence. My contributions include the design of ultra-wideband multi-polarimetric GPR antennas, the advancement of measurement techniques, and the development of deep learning augmented data processing and interpretation algorithms. As a pioneering attempt, we have combined powerful capabilities of deep learning algorithms with GPR domain knowledge and engineered several neural network architectures in completing challenging GPR tasks, including clutter removal in radargrams, object parameter estimation, and underground scenario mapping. All of my work on GPR can be found on this page.
 | Learning from Clutter: An Unsupervised Learning-Based Clutter Removal Scheme for GPR B-Scans |
 | MAPD-Net: A GPR-Based Method for Estimating Rebar Parameters and Concrete Moisture Content |
 | Early Detection of Corrosion Damage in Reinforced Concrete Using GPR Array Imaging Method |
 | Corrosion Damage Detection in Reinforced Concrete Using Rayleigh Wave-Based Method |
 | 3DInvNet: A Deep Learning-Based 3D Ground-Penetrating Radar Data Inversion |
 | Diameter Estimation of Cylindrical Metal Bar Using Wideband Dual-Polarized Ground-Penetrating Radar |
 | Estimating the Diameter of Reinforcing Bars Using an Ultra-Wideband MIMO GPR Array |
 | A Deep Learning-Based GPR Forward Solver for Predicting B-Scans of Subsurface Objects |
 | Learning to Remove Clutter in Real-World GPR Images Using Hybrid Data |
 | DMRF-UNet: A Two-Stage Deep Learning Scheme for GPR Data Inversion under Heterogeneous Soil Conditions |
 | Tree Roots Reconstruction Framework for Accurate Positioning in Heterogeneous Soil |
 | Estimating Parameters of the Tree Root in Heterogeneous Soil Environments via Mask-Guided Multi-Polarimetric Integration Neural Network |
 | The Orientation Estimation of Elongated Underground Objects via Multi-Polarization Aggregation and Selection Neural Network |
 | Dual-Cross-Polarized GPR Measurement Method for Detection and Orientation Estimation of Shallowly Buried Elongated Object |
 | Compact Dual-Polarized Vivaldi Antenna with High Gain and High Polarization Purity for GPR Applications |