DCD-FPI: A Deformable Convolution-Based Fusion Network for Unmanned Aerial Vehicle Localization

In recent years, with the rapid development of UAV technology, drones have been widely applied in various fields. Obtaining accurate location information is crucial for UAVs when performing tasks in challenging environments. In previous research, a pure vision-based self-positioning method was employed, which determined the UAV’s position by matching the vertical view image of the UAV with offline satellite remote sensing images. However, in certain urban areas where architectural features are similar, and due to variations in image viewing angles, shooting positions, and sensor parameters, non-rigid deformations exist between UAV images and remote sensing images, posing significant challenges for UAV visual positioning. To address these challenges, we propose a novel approach called Deformable Convolutional Transformer-based UAV Positioning (DCD-FPI). Our approach combines the Transformer-based model with deformable convolution, enhancing the model’s capability to handle non-rigid image deformations and capture detailed information. We also employ adaptive spatial feature fusion through multi-scale fusion to preserve critical distinguishing features. Experimental comparisons on the UL14 dataset demonstrate that our model achieves improved performance, with an increase from 76.25 to 77.15 in terms of the evaluation index RDS. Moreover, our model reduces computational complexity from 14.28 GFLOPS to 11.54 GFLOPS and parameter quantity from 14.76 M to 13.96 M.