Drone-view target localization
6 papers with code • 1 benchmarks • 1 datasets
(Drone -> Satellite) Given one drone-view image or video, the task aims to find the most similar satellite-view image to localize the target building in the satellite view.
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph.
However it still has some limitations, e. g., it can only extract part of the information in the neighborhood and some scale reduction operations will make some fine-grained information lost.
Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.
In this article, we present a simplified but effective architecture based on contrastive learning with symmetric InfoNCE loss that outperforms current state-of-the-art results.