Conditional Generative Models for High-Resolution Range Profiles: Capturing Geometry-Driven Trends in a Large-Scale Maritime Dataset

2026-02-09

AI Summary

This study addresses the sensitivity of high-resolution range profiles (HRRPs) to data acquisition conditions, which undermines the robustness of radar automatic target recognition in complex operational scenarios. To tackle this challenge, the authors leverage a large-scale real-world maritime dataset and, for the first time, treat ship geometric parameters—such as physical dimensions and aspect angles—as core conditioning variables to develop a controllable HRRP generative model. This approach overcomes the limitations of prior methods that rely on small-scale or scenario-specific data, successfully reproducing the line-of-sight geometry–driven distribution patterns observed in real HRRPs. The results demonstrate that incorporating geometric conditions is pivotal for enhancing both the fidelity of synthetic HRRPs and their generalization across diverse operational environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

High-resolution range profiles (HRRPs) enable fast onboard processing for radar automatic target recognition, but their strong sensitivity to acquisition conditions limits robustness across operational scenarios. Conditional HRRP generation can mitigate this issue, yet prior studies are constrained by small, highly specific datasets. We study HRRP synthesis on a largescale maritime database representative of coastal surveillance variability. Our analysis indicates that the fundamental scenario drivers are geometric: ship dimensions and the desired aspect angle. Conditioning on these variables, we train generative models and show that the synthesized signatures reproduce the expected line-of-sight geometric trend observed in real data. These results highlight the central role of acquisition geometry for robust HRRP generation.

Problem

• High-resolution range profiles
• Radar automatic target recognition
• Acquisition geometry
• Robustness
• Conditional generation

Innovation

• conditional generative models
• high-resolution range profiles
• acquisition geometry
• maritime dataset
• radar automatic target recognition