Exploiting the Earth’s Spherical Geometry to Geolocate Images

Exploiting the Earth’s Spherical Geometry to Geolocate Images
复制标题

利用地球的球形几何形状对图像进行地理定位

DOI:
10.1007/978-3-030-46147-8_1
复制
发表时间:
2020
期刊:
Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019.
影响因子:
--
通讯作者:
Izbicki M., Papalexakis E.E.
Izbicki M., Papalexakis E.E.
中科院分区:
--
文献类型:
--
作者:
Izbicki M., Papalexakis E.E.

文献摘要

相似文献

用于地理定位图像的现有方法使用标准分类或图像检索技术。这些方法的理论性质很差,因为它们没有利用地球的球形几何形状。在某些情况下,它们需要随着特征维度的数量呈指数增长的训练数据集。本文介绍了冯-米塞斯-费舍尔混合损失函数(MvMF),它是第一个利用地球的球形几何形状来提高地理定位精度的损失函数。我们证明了这种损失只需要一个数据集的大小线性的特征维数,和经验结果表明,我们的方法优于以前的方法与数量级少的训练数据和计算。
Existing methods for geolocating images use standard classification or image retrieval techniques. These methods have poor theoretical properties because they do not take advantage of the earth’s spherical geometry. In some cases, they require training data sets that grow exponentially with the number of feature dimensions. This paper introduces theMixture of von-Mises Fisher(MvMF) loss function, which is the first loss function that exploits the earth’s spherical geometry to improve geolocation accuracy. We prove that this loss requires only a dataset of size linear in the number of feature dimensions, and empirical results show that our method outperforms previous methods with orders of magnitude less training data and computation.