Technology Category
Machine Learning: Transfer, Domain Adaptation, Multi-Task LearningCognitive Modeling & Cognitive Systems: Adaptive BehaviorPlanning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
RASPNet: A Benchmark Dataset for Radar Adaptive Signal Processing Applications
🤖 AI Summary
The adaptive radar signal processing (RASP) community lacks large-scale, high-fidelity, geographically diverse real-world clutter benchmark datasets, hindering the development of data-driven models and standardized algorithm evaluation.
Method: We introduce RASPNet—an open-source, >16 TB benchmark dataset—comprising 10,000 complex-valued airborne radar clutter snapshots per scene across 100 geographically distinct real-world locations in the contiguous United States. It integrates GIS-driven scene modeling, complex-valued signal acquisition, and structured metadata annotation.
Contribution/Results: RASPNet is the first publicly available RASP benchmark enabling rigorous cross-scene generalization and transfer learning validation. Experiments demonstrate that transfer models trained on RASPNet achieve a 3.2 dB improvement in signal-to-interference-plus-noise ratio (SINR) for clutter suppression in unseen regions, significantly advancing the practical deployment of complex-domain deep learning in operational radar systems.
Technology Category
Application Category
📝 Abstract
We present a large-scale dataset for radar adaptive signal processing (RASP) applications to support the development of data-driven models within the adaptive radar community. The dataset, RASPNet, exceeds 16 TB in size and comprises 100 realistic scenarios compiled over a variety of topographies and land types from across the contiguous United States. For each scenario, RASPNet consists of 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 adaptive radar processing 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 realistic adaptive radar processing scenarios.
Problem
Research questions and friction points this paper is trying to address.
Develop benchmark for radar signal processing
Standardize adaptive radar technique evaluation
Support complex-valued neural network training
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large-scale radar dataset
Realistic airborne scenarios
Complex-valued learning benchmarks
🔎 Similar Papers
No similar papers found.
