Technology Category
Planning, Routing, and Scheduling: Activity and Plan RecognitionIntelligent Robots: Localization, Mapping, and NavigationComputer Vision: Low Level & Physics-based Vision
XPRESS: X-Band Radar Place Recognition via Elliptical Scan Shaping
🤖 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
Application Category
📝 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
Research questions and friction points this paper is trying to address.
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
Methods, ideas, or system contributions that make the work stand out.
Elliptical scan shaping for X-band radar
Object density-based candidate selection rule
Intentional degradation for robust retrieval performance
🔎 Similar Papers
No similar papers found.
