XPRESS: X-Band Radar Place Recognition via Elliptical Scan Shaping

2025-11-12

IEEE Robotics and Automation Letters

AI Summary

Low-resolution X-band radar data—characterized by poor spatial resolution and limited information content—pose significant challenges for place recognition in maritime autonomous navigation. To address this, we propose a robust place recognition algorithm specifically designed for low-resolution radar. Our method introduces three key innovations: (i) elliptical scan-based image shaping to preserve geometric structure; (ii) target-density-driven candidate region filtering to prioritize discriminative areas; and (iii) a controllable radar detection degradation mechanism to enhance generalization under low signal-to-noise ratios. Extensive experiments on both public and newly collected multi-source maritime radar datasets demonstrate superior performance over state-of-the-art methods. Ablation studies confirm the consistent and complementary contributions of each module to accuracy and robustness. This work establishes an interpretable, lightweight, and practical paradigm for scene understanding with low-resolution radar.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

X-band radar serves as the primary sensor on maritime vessels, however, its application in autonomous navigation has been limited due to low sensor resolution and insufficient information content. To enable X-band radar-only autonomous navigation in maritime environments, this letter proposes a place recognition algorithm specifically tailored for X-band radar, incorporating an object density-based rule for efficient candidate selection and intentional degradation of radar detections to achieve robust retrieval performance. The proposed algorithm was evaluated on both public maritime radar datasets and our own collected dataset, and its performance was compared against state-of-the-art radar place recognition methods. An ablation study was conducted to assess the algorithm’s performance sensitivity with respect to key parameters.

Problem

• Enables X-band radar-only autonomous maritime navigation
• Addresses low resolution and insufficient information in radar
• Develops robust place recognition via intentional detection degradation

Innovation

• Elliptical scan shaping for X-band radar
• Object density-based candidate selection rule
• Intentional degradation for robust retrieval performance