TR2024-128

Deep Calibration and Operator Learning for Ground Penetrating Radar Imaging


    •  Shastri, S., Ma, Y., Boufounos, P.T., Mansour, H., "Deep Calibration and Operator Learning for Ground Penetrating Radar Imaging", European Signal Processing Conference (EUSIPCO), August 2024.
      BibTeX TR2024-128 PDF
      • @inproceedings{Shastri2024aug,
      • author = {Shastri, Saurav and Ma, Yanting and Boufounos, Petros T. and Mansour, Hassan}},
      • title = {Deep Calibration and Operator Learning for Ground Penetrating Radar Imaging},
      • booktitle = {European Signal Processing Conference (EUSIPCO)},
      • year = 2024,
      • month = aug,
      • url = {https://www.merl.com/publications/TR2024-128}
      • }
  • MERL Contacts:
  • Research Areas:

    Computational Sensing, Dynamical Systems, Machine Learning

Abstract:

The accurate imaging of underground scenes using wave-based sensor technologies, such as ground penetrating radar, presents challenges due to ill-posedness, formulation com- plexities, and computational demands. In this paper, we propose a machine learning-based approach that leverages a learned forward model to simulate wave-object interactions inspired by physics principles as well as the calibration to realistic antenna configurations. Our approach combines a learned wave propagation model, referred to as Born FNO, with a deep calibration network that maps a point-receiver scattered wavefields to the response of a desired receiving antenna architecture. We evaluate our method on a simulated dataset that includes multiple ground layers and complex target structures. We demonstrate that our proposed calibration network enables the reconstruction of permittivity distributions and outperforms a linear calibration operator trained on the same dataset by over 4.5 dB in peak signal-to-noise ratio.