papers AI Learner
The Github is limit! Click to go to the new site.

Improving Nighttime Retrieval-Based Localization

2019-04-05
Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Abstract

Outdoor visual localization is a crucial component to many computer vision systems. We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening between daytime and nighttime. As revealed by recent long-term localization benchmarks, both traditional feature-based and retrieval-based approaches still struggle to handle such changes. Our novel localization method combines a state-of-the-art image retrieval architecture with condition-specific sub-networks allowing the computation of global image descriptors that are explicitly dependent of the capturing conditions. We show that our approach improves localization by a factor of almost 300\% compared to the popular VLAD-based methods on nighttime localization.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1812.03707

PDF

http://arxiv.org/pdf/1812.03707


Similar Posts

Comments