通过融合视角与姿态估计，实现厘米级城市级定位精度。
PEnG: Pose-Enhanced Geo-Localisation
- 分两阶段：先定位城市图谱中的可能边，再在边上做相对位姿估计
- 相较此前最佳水平，中位欧氏误差降低96.90%，从734米降至22.77米
- 首次在跨视图数据集中同时利用视角与姿态信息，适合高精度定位应用
跨视图地理定位通常只能达到粗粒度精度，因密集采样的卫星图像块重叠严重，难以区分。而稀疏采样虽可缓解此问题，却人为设定了定位精度上限——即使理想系统也无法超过瓦片平均间距。为突破这一限制，本文提出PEnG：一种两阶段系统，首先基于城市尺度图谱预测查询图像最可能所在的边，随后在该边上进行相对位姿估计以精确定位。PEnG是首个同时利用跨视图数据集中的两种视角信息提升定位精度的方法，实现亚米级甚至厘米级准确率。其集成方案在基准测试中取得顶尖性能：相对于先前最佳结果，相对Top-5m检索率提升213%；在90度水平视场角图像下，中位欧氏距离误差从734米降至22.77米。代码将公开于tavisshore.co.uk/PEnG。
原文摘要 · Abstract (English)
Cross-view Geo-localisation is typically performed at a coarse granularity, because densely sampled satellite image patches overlap heavily. This heavy overlap would make disambiguating patches very challenging. However, by opting for sparsely sampled patches, prior work has placed an artificial upper bound on the localisation accuracy that is possible. Even a perfect oracle system cannot achieve accuracy greater than the average separation of the tiles. To solve this limitation, we propose combining cross-view geo-localisation and relative pose estimation to increase precision to a level practical for real-world application. We develop PEnG, a 2-stage system which first predicts the most likely edges from a city-scale graph representation upon which a query image lies. It then performs relative pose estimation within these edges to determine a precise position. PEnG presents the first technique to utilise both viewpoints available within cross-view geo-localisation datasets to enhance precision to a sub-metre level, with some examples achieving centimetre level accuracy. Our proposed ensemble achieves state-of-the-art precision - with relative Top-5m retrieval improvements on previous works of 213%. Decreasing the median euclidean distance error by 96.90% from the previous best of 734m down to 22.77m, when evaluating with 90 degree horizontal FOV images. Code will be made available: tavisshore.co.uk/PEnG
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。