Can I read Optimal Feature Transport for Cross-View Image Geo-Localization on EtoBox?

Optimal Feature Transport for Cross-View Image Geo-Localization by Shi, Yujiao; Yu, Xin; Liu, Liu; Zhang, Tong; Li, Hongdong is a scholarly article available to read on EtoBox.

What is Optimal Feature Transport for Cross-View Image Geo-Localization about?

This paper addresses the problem of cross-view image geo-localization, where the geographic location of a ground-level street-view query image is estimated by matching it against a large scale aerial map (e.g., a high-resolution satellite image). State-of-the-art deep-learning based methods tackle this problem as deep metric learning which aims to learn global feature representations of the scene seen by the two different views. Despite promising results are obtained by such deep metric learning methods, they, however, fail to exploit a crucial cue relevant for localization, namely, the spatial layout of local features. Moreover, little attention is paid to the obvious domain gap (between aerial view and ground view) in the context of cross-view localization. This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images. Specifically, we implement the CVFT as network layers, which transports features from one domain to the other, leading to more meaningful feature similarity comparison. Our model is differentiable and can be learned end-to-end. Experime

Author

Shi, Yujiao; Yu, Xin; Liu, Liu; Zhang, Tong; Li, Hongdong

Published

2019

Language

EN