GeoFormer: An Effective Transformer-Based Siamese Network for UAV Geolocalization

GeoFormer: An Effective Transformer-Based Siamese Network for UAV Geolocalization

Cross-view geolocalization of unmanned aerial vehicles (UAVs) is a challenging task due to the positional discrepancies and uncertainties in scale and distance between UAVs and satellite views. Existing transformer-based geolocalization methods mainly use encoders to mine image contextual informatio...

Full description

Bibliographic Details
Main Authors: Qingge Li, Xiaogang Yang, Jiwei Fan, Ruitao Lu, Bin Tang, Siyu Wang, Shuang Su
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Cross-view image retrieval
heterologous scene matching
linear attention
Siamese network
transformer
unmanned aerial vehicle (UAV) geolocalization
Online Access:https://ieeexplore.ieee.org/document/10506965/

Internet

https://ieeexplore.ieee.org/document/10506965/

Similar Items