HE-VPR: 一种结合高度估计的空中视觉位置识别框架以应对尺度变化
HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance
AI总结:
HE-VPR通过结合高度估计与轻量级旁路适配器,实现了高效且可扩展的空中视觉位置识别,提升了在GNSS拒止环境下的实用性。
摘要:
在本文中,我们提出了一种名为HE-VPR的视觉位置识别(VPR)框架,该框架集成了高度估计。我们的系统将高度推断与位置识别解耦,使两个模块能够共享一个冻结的DINOv2主干网络。两个轻量级的旁路适配器分支被整合到我们的系统中。第一个分支通过从紧凑的高度数据库中检索来估计查询图像的高度部分,第二个分支则在对应的特定高度子数据库中执行VPR。适应设计减少了训练成本,并显著减少了数据库的搜索空间。我们还采用了一种中心加权遮蔽策略,以进一步增强对尺度差异的鲁棒性。在两个自采集的具有多海拔挑战性数据集上的实验表明,HE-VPR在状态最先进ViT基线之上实现了高达6.1%的Recall@1提升,并将内存使用量减少了高达90%。这些结果表明,HE-VPR提供了一种可扩展且高效的解决方案,用于高度感知的空中VPR,使其在GNSS拒止环境中具有实际部署的可行性。本工作中的所有代码和数据集已发布在https://github.com/hmf21/HE-VPR。
英文摘要:
In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our system. The first estimates the height partition of the query image via retrieval from a compact height database, and the second performs VPR within the corresponding height-specific sub-database. The adaptation design reduces training cost and significantly decreases the search space of the database. We also adopt a center-weighted masking strategy to further enhance the robustness against scale differences. Experiments on two self-collected challenging multi-altitude datasets demonstrate that HE-VPR achieves up to 6.1\% Recall@1 improvement over state-of-the-art ViT-based baselines and reduces memory usage by up to 90\%. These results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments. All the code and datasets for this work have been released on https://github.com/hmf21/HE-VPR.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。