BEV-Patch-PF：基于鸟瞰图空域特征匹配的无GPS轨迹定位系统
BEV-Patch-PF: Particle Filtering with BEV-Aerial Feature Matching for Off-Road Geo-Localization
AI总结：
BEV-Patch-PF通过结合鸟瞰图与空域特征匹配，实现了无GPS的非公路地理定位，显著降低轨迹误差并实现实时运行。
摘要：
我们提出BEV-Patch-PF，一种无需GPS的顺序地理定位系统，该系统集成了粒子滤波器与学习得到的鸟瞰图（BEV）和空域特征图。从车载RGB和深度图像中，我们构建了一个BEV特征图。对于每个3自由度的粒子姿态假设，我们从局部空域图像查询的近似位置处提取对应的空域特征块。BEV-Patch-PF通过匹配BEV特征与空域特征块计算每个粒子的对数似然。在两个真实世界非公路数据集中，我们的方法在已见路线上的绝对轨迹误差（ATE）比基于检索的基线低9.7倍，在未见路线上的ATE降低6.6倍，同时在密集树冠和阴影条件下保持准确性。该系统在NVIDIA Tesla T4上以10 Hz的实时速率运行，使机器人部署成为可能。
英文摘要：
We propose BEV-Patch-PF, a GPS-free sequential geo-localization system that integrates a particle filter with learned bird's-eye-view (BEV) and aerial feature maps. From onboard RGB and depth images, we construct a BEV feature map. For each 3-DoF particle pose hypothesis, we crop the corresponding patch from an aerial feature map computed from a local aerial image queried around the approximate location. BEV-Patch-PF computes a per-particle log-likelihood by matching the BEV feature to the aerial patch feature. On two real-world off-road datasets, our method achieves 9.7x lower absolute trajectory error (ATE) on seen routes and 6.6x lower ATE on unseen routes than a retrieval-based baseline, while maintaining accuracy under dense canopy and shadow. The system runs in real time at 10 Hz on an NVIDIA Tesla T4, enabling practical robot deployment.
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。
