SeqLGPR: A Sequential Subsurface Feature-Based Framework for Vehicle Place Recognition

Ground-penetrating radar (GPR) localization has gained increasing attention in autonomous driving due to its resilience against surface appearance and weather conditions. However, existing localization using GPR (LGPR) methods based on single-scan matching often suffer from limited sensing range and frequent mismatches, particularly in the absence of complementary sensors. To address these challenges, we propose the first dedicated sequence-based matching framework for LGPR localization, which systematically exploits temporal continuity for robust place recognition. The proposed framework comprises four key components: a learning-based pretraining module to suppress weather-induced variations in GPR signatures; an information–theoretic correlation method for estimating lateral deviations; a velocity-constrained search strategy to enforce spatial consistency during coarse alignment; and a reranking mechanism to refine the final matching outcome. Unlike existing methods that focus solely on descriptor design, our framework is modular, extensible, and emphasizes the sequential nature of localization. It supports both handcrafted and learning-based GPR features, enabling fair and reproducible comparisons across different extraction pipelines. Experiments on both public and in-house datasets show that our method significantly improves localization accuracy, validating its robustness, adaptability, and the critical role of sequence modeling in LGPR-based localization.