Sparse signal models for data augmentation in deep learning ATR

T Agarwal, N Sugavanam, E Ertin - Remote Sensing, 2023 - mdpi.com
Automatic target recognition (ATR) algorithms are used to classify a given synthetic aperture
radar (SAR) image into one of the known target classes by using the information gleaned …

High resolution mimo radar sensing with compressive illuminations

N Sugavanam, S Baskar, E Ertin - IEEE Transactions on Signal …, 2022 - ieeexplore.ieee.org
We present a compressive radar design that combines multitone linear frequency modulated
(LFM) waveforms in the transmitter with a classical stretch processor and sub-Nyquist …

Models of anisotropic scattering for 3D SAR reconstruction

N Sugavanam, E Ertin - 2022 IEEE Radar Conference …, 2022 - ieeexplore.ieee.org
We study different modeling approaches to anisotropic scattering from man-made objects to
derive novel solutions to the 3D imaging problem from multi-pass circular synthetic aperture …

Deep learning for three dimensional SAR imaging from limited viewing angles

N Sugavanam, E Ertin… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
A synthetic aperture radar (SAR) collects samples of the three-dimensional (3D) spatial
Fourier transform of the scene on a two dimensional conical manifold corresponding to the …

MrSARP: A hierarchical deep generative prior for SAR image super-resolution

T Agarwal, N Sugavanam, E Ertin - 2023 IEEE Radar …, 2023 - ieeexplore.ieee.org
Generative models learned from training using deep learning methods can be used as
priors in under-determined inverse problems, including imaging from sparse set of …

Compressing bistatic SAR target signatures with sparse‐limited persistence scattering models

N Sugavanam, E Ertin… - IET Radar, Sonar & …, 2019 - Wiley Online Library
Here, the authors study the modelling of bistatic synthetic aperture radar (SAR) target
signatures. They focus on building concise models inspired by physical phenomenology that …

Complex-valued deep-learning model for 3D SAR modeling and image generation

N Sugavanam, E Ertin - 2023 57th Asilomar Conference on …, 2023 - ieeexplore.ieee.org
Synthetic aperture radar (SAR) collects samples of the 3D Spatial Fourier transform on a two-
dimensional manifold corresponding to the backscatter data of wideband pulses launched …

Neural Implicit representations for 3D scene modeling and visualization using multipass SAR

N Sugavanam, E Ertin… - EUSAR 2024; 15th …, 2024 - ieeexplore.ieee.org
Synthetic aperture radar (SAR) collects samples of the 3D Spatial Fourier transform on a two-
dimensional surfaces corresponding to the backscatter data of wideband pulses launched …

Toward Internal Ice-Sheet Temperature Retrieval Using Microwave Radiometry and Simplified Ice-Flow Models

N Sugavanam, E Ertin, C Yardim… - IGARSS 2023-2023 …, 2023 - ieeexplore.ieee.org
Ice sheets are fundamental components of the Earth's system that impact the climate through
their contribution to global sea level. Knowledge of an ice sheet's internal temperature is …

Modeling frequency dependent scattering models for SAR Image Spectrum Extrapolation

N Sugavanam, E Ertin - 2023 IEEE Radar Conference …, 2023 - ieeexplore.ieee.org
The wavelength used for illumination dictates the scale of the mechanisms that interact with
the incident electromagnetic (EM) energy. We model the synthetic Aperture Radar Image of …