通过高度估计提升无人机视觉定位，解决尺度变化难题。
HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance
- 分步处理：先估高度再在对应高度库中检索
- 相比顶尖方法召回率提升6.1%，内存降低90%
- 适合无人机在无GPS环境下的高精度定位
本文提出HE-VPR，一种融合高度估计的视觉位置识别框架。系统将高度推断与位置识别解耦，共享冻结的DINOv2骨干网络。引入两个轻量级旁路适配分支：首个分支通过查询紧凑高度数据库估算查询图像的高度分区，第二个分支在对应的高度子数据库内完成VPR。该设计降低训练成本并显著缩小数据库搜索空间。同时采用中心加权掩码策略，进一步增强对尺度差异的鲁棒性。在两个自建的多高度挑战性数据集上的实验表明，HE-VPR相比最先进的基于ViT的基线，最多提升6.1%的Recall@1，内存使用减少高达90%。结果表明，HE-VPR为高度感知的空中VPR提供了可扩展且高效的解决方案，适用于无GNSS环境的实际部署。代码与数据集已开源至https://github.com/hmf21/HE-VPR。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。