An Orthogonal Fusion of Local and Global Features for Drone-based Geo-localization

Tian Zhan, Cheng Zhang, Sibo You, Kai Sun, Di Su

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Drone-based geo-localization is an image retrieval task which is the foundation of many drone-based multimedia applications, such as object detection, drone navigation and mapping. It is challenging due to the large visual appearance changes caused by viewpoint variation and time misalignment. Existing methods primarily focus on global representation embedding while disregarding the local features. We propose a CNN-based model containing a global and a local branch to extract features in these two perspectives and then features are subsequently aggregated by orthogonal fusion. We achieve competitive results on University-1652/160k datasets among the ViT-based state-of-the-art models. Experimental and qualitative results that validate the effectiveness of our solution are also shown.

Original languageEnglish
Title of host publicationUAVM 2023 - Proceedings of the 2023 Workshop on UAVs in Multimedia
Subtitle of host publicationCapturing the World from a New Perspective, Co-located with MM 2023
PublisherAssociation for Computing Machinery, Inc
Pages1-6
Number of pages6
ISBN (Electronic)9798400702860
DOIs
Publication statusPublished - 2 Nov 2023
Event2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective, UAVM 2023 - Ottawa, Canada
Duration: 2 Nov 2023 → …

Publication series

NameUAVM 2023 - Proceedings of the 2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective, Co-located with MM 2023

Conference

Conference2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective, UAVM 2023
Country/TerritoryCanada
CityOttawa
Period2/11/23 → …

Keywords

  • deep learning
  • drone
  • geo-localization
  • image retrieval

Fingerprint

Dive into the research topics of 'An Orthogonal Fusion of Local and Global Features for Drone-based Geo-localization'. Together they form a unique fingerprint.

Cite this