Ground penetrating radar (GPR) sends short electromagnetic pulses into the ground and records the echoes that come back from buried objects and from changes in the soil. Reading those echoes is still largely a manual job that needs an experienced operator. Nairit's work since 2016 aims to make it automatic and quantitative.
On the hardware side, his group has built a prototype GPR on a Xilinx UltraScale+ MPSoC FPGA platform with a 14-bit, 1.0 GSPS ADC and a 16-bit, 2.8 GSPS DAC, along with a sand-filled test bed for controlled experiments. The system is designed to generate custom waveforms, work with different antennas and process the data on the FPGA in real time.
On the signal side, the work covers both A-scans (single traces) and B-scans (radargram images), in the time and frequency domains. Results so far include estimating the diameter of buried rods and pipes from A-scan spectra with a mean absolute percentage error of 1.89% on experimental data, predicting object size from B-scans, classifying target shape and material, detecting and fitting the hyperbolas that buried objects leave in B-scans, and estimating soil moisture and soil type.
Articles
Size estimation of underground targets from GPR frequency spectra: A deep learning approach
21 min read
Estimation of soil moisture from GPR data using Artificial Neural Networks
10 min read
A CNN model for predicting size of buried objects from GPR B-Scans
26 min read
Classification of Soil Types from GPR B-Scans using Deep Learning Techniques
12 min read
Publications
Efficient Hyperbola Detection and Fitting using Image Processing Techniques and Column-Connection Clustering
2023 Second International Conference on Advances in Computational Intelligence and Communication (ICACIC)
Size estimation of underground targets from GPR frequency spectra: A deep learning approach
Journal of Applied Geophysics, vol. 213, 105009
Automatic Material Classification of Targets from GPR Data using Artificial Neural Networks
2022 IEEE Silchar Subsection Conference (SILCON)
A CNN model for predicting size of buried objects from GPR B-Scans
Journal of Applied Geophysics, vol. 200, 104620
Estimation of soil moisture from GPR data using artificial neural networks
2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES)
Artificial Neural Network based automatic classification of target shapes from GPR data
2021 IEEE International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)
Classification of soil types from GPR B Scans using deep learning techniques
2021 6th IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT 2021)