RASPNet: A Benchmark Dataset for Radar Adaptive Signal Processing Applications

TL;DR

RASPNet is a comprehensive large-scale dataset designed to advance radar adaptive signal processing by providing realistic scenarios and benchmark data for developing and evaluating data-driven models.

Contribution

The paper introduces RASPNet, a large-scale, realistic radar dataset that fills a critical gap for benchmarking and developing adaptive radar signal processing algorithms.

Findings

RASPNet contains over 16 TB of data across 100 scenarios.

The dataset supports benchmarking of radar and complex-valued neural networks.

A transfer learning example demonstrates RASPNet's practical application.

Abstract

We present a large-scale dataset called RASPNet for radar adaptive signal processing (RASP) applications to support the development of data-driven models within the adaptive radar community. RASPNet exceeds 16 TB in size and comprises 100 realistic scenarios compiled over a variety of topographies and land types across the contiguous United States. For each scenario, RASPNet comprises 10,000 clutter realizations from an airborne radar setting, which can be used to benchmark radar and complex-valued learning algorithms. RASPNet intends to fill a prominent gap in the availability of a large-scale, realistic dataset that standardizes the evaluation of RASP techniques and complex-valued neural networks. We outline its construction, organization, and several applications, including a transfer learning example to demonstrate how RASPNet can be used for real-world adaptive radar scenarios.