• Corpus ID: 257378684

Data-Driven Target Localization Using Adaptive Radar Processing and Convolutional Neural Networks

  title={Data-Driven Target Localization Using Adaptive Radar Processing and Convolutional Neural Networks},
  author={Shyam Venkatasubramanian and Sandeep Gogineni and Bosung Kang and Ali Pezeshki and Muralidhar Rangaswamy and Vahid Tarokh},
Facilitated by the recent emergence of radio frequency (RF) modeling and simulation tools purposed for adaptive radar processing applications, data-driven approaches to classical problems in radar have rapidly grown in popularity over the past decade. Despite this surge, limited focus has been directed toward the theoretical foundations of these data-driven approaches. In this regard, using adaptive radar processing techniques, we propose a data-driven approach in this work to address the… 

Subspace Perturbation Analysis for Data-Driven Radar Target Localization

This work augments their data-driven approach to radar target localization by performing a subspace perturbation analysis, which allows them to benchmark the localization accuracy of their proposed deep learning framework across mismatched scenarios.



Toward Data-Driven STAP Radar

This paper describes an amalgamation of techniques from classical radar, computer vision, and deep learning, and presents a regression network in this paper for estimating target locations to demonstrate the feasibility of and significant improvements provided by the data-driven approach to space-time adaptive processing (STAP) radar.

Optimal and adaptive reduced-rank STAP

A comprehensive performance comparison is conducted both analytically and via Monte Carlo simulation which clearly demonstrates the superior theoretical compression performance of signal-dependent rank-reduction, its broader region-of-convergence, and its inherent robustness to subspace leakage.

Passive Radar Detection With Noisy Reference Channel Using Principal Subspace Similarity

A new detector is developed that utilizes a test statistic based on the cross correlation of the principal left singular vectors of the reference and surveillance signal-plus-noise matrices that offers better performance by exploiting the inherent low-rank structure when the transmitted signals are a weighted periodic summation of several identical waveforms.

MVDR Beamforming for Through-the-Wall Radar Imaging

The paper considers both cases of known and unknown wall parameters and uses manifold constraints to allow target localization in high-definition imaging in the presence of wall errors and shows how to effectively use the spatial spectrum to improve covariance matrix estimation and subsequently enhance image quality in the sense of lower sidelobes.

Assessment of multichannel airborne radar measurements for analysis and design of space-time processing architectures and algorithms

This paper proposes a preliminary scheme to detect and excise nonhomogeneous secondary data in the sample covariance estimation, thereby dramatically improving STAP performance as shown through a specific example using monostatic MCARM data.

High Fidelity RF Clutter Modeling and Simulation

A radar challenge dataset generated using state-of-the-art radio frequency clutter modeling and simulation techniques that can enable testing and benchmarking of all cognitive radar algorithms and techniques is introduced.

Adaptive subspace detectors

A unified analysis of the statistical behavior of the entire class of ASDs is presented, obtaining statistically identical decompositions in which each ASD is simply decomposed into the nonadaptive matched filter, the non Adaptive cosine or t-statistic, and three other statistically independent random variables that account for the performance-degrading effects of limited training data.

Performance of Parametric and Covariance Based STAP Tests in Compound-Gaussian Clutter

The performance of a parametric space–time adaptive processing method is presented here and signal detection in additive disturbance containing compound-Gaussian clutter plus additive Gaussian thermal white noise is considered.

Rapid Convergence Rate in Adaptive Arrays

A direct method of adaptive weight computation, based on a sample covariance matrix of the noise field, has been found to provide very rapid convergence in all cases, i.e., independent of the eigenvalue distribution.

Adaptive matched subspace detectors and adaptive coherence estimators

  • L. ScharfL. T. McWhorter
  • Mathematics
    Conference Record of The Thirtieth Asilomar Conference on Signals, Systems and Computers
  • 1996
We adapt the matched subspace detectors (MSDs) of Scharf (1991) and Scharf and Friedlander (see IEEE Trans. Signal Proc., vol.42, no.8. p.2146-57, 1994) to unknown noise covariance matrices in order