Cross-view image matching for geo-localisation is a challenging problem due
to the significant visual difference between aerial and ground-level
viewpoints. The method provides localisation capabilities from geo-referenced
images, eliminating the need for external devices or costly equipment. This
enhances the capacity of agents to autonomously determine their position,
navigate, and operate effectively in environments where GPS signals are
unavailable. Current research employs a variety of techniques to reduce the
domain gap such as applying polar transforms to aerial images or synthesising
between perspectives. However, these approaches generally rely on having a
360{\deg} field of view, limiting real-world feasibility. We propose BEV-CV, an
approach which introduces two key novelties. Firstly we bring ground-level
images into a semantic Birds-Eye-View before matching embeddings, allowing for
direct comparison with aerial segmentation representations. Secondly, we
introduce the use of a Normalised Temperature-scaled Cross Entropy Loss to the
sub-field, achieving faster convergence than with the standard triplet loss.
BEV-CV achieves state-of-the-art recall accuracies, improving feature
extraction Top-1 rates by more than 300%, and Top-1% rates by approximately
150% for 70{\deg} crops, and for orientation-aware application we achieve a 35%
Top-1 accuracy increase with 70{\deg} crops.

我们提出了 BEV-CV 方法，该方法通过将地面图像转化为语义鸟瞰图进行嵌入匹配，并引入了一种归一化温度缩放的交叉熵损失函数，相比标准三元损失函数具有更快的收敛速度。BEV-CV 在 70 度裁剪图上实现了最新的召回率准确性，其特征提取 Top-1 率提高了 300% 以上，Top-1% 率提高了约 150%，对于方向感知应用，我们在 70 度裁剪图上实现了 35% 的 Top-1 准确率提高。

BEV-CV：鸟瞰图变换用于交叉视图地理定位

BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation

Retrieving relevant multimedia content is one of the main problems in a world
that is increasingly data-driven. With the proliferation of drones, high
quality aerial footage is now available to a wide audience for the first time.
Integrating this footage into applications can enable GPS-less geo-localisation
or location correction.
In this paper, we present an orientation-guided training framework for
UAV-view geo-localisation. Through hierarchical localisation orientations of
the UAV images are estimated in relation to the satellite imagery. We propose a
lightweight prediction module for these pseudo labels which predicts the
orientation between the different views based on the contrastive learned
embeddings. We experimentally demonstrate that this prediction supports the
training and outperforms previous approaches. The extracted pseudo-labels also
enable aligned rotation of the satellite image as augmentation to further
strengthen the generalisation. During inference, we no longer need this
orientation module, which means that no additional computations are required.
We achieve state-of-the-art results on both the University-1652 and
University-160k datasets.

通过建议的方向引导训练框架，本文在无人机成像中通过层级定位，预测方向标签以支持训练，实现了高精度的地理定位，同时还可以增强卫星图像对空间的推广。