RESUMO
Within research on the cross-view geolocation of UAVs, differences in image sources and interference from similar scenes pose huge challenges. Inspired by multimodal machine learning, in this paper, we design a single-stream pyramid transformer network (SSPT). The backbone of the model uses the self-attention mechanism to enrich its own internal features in the early stage and uses the cross-attention mechanism in the later stage to refine and interact with different features to eliminate irrelevant interference. In addition, in the post-processing part of the model, a header module is designed for upsampling to generate heat maps, and a Gaussian weight window is designed to assign label weights to make the model converge better. Together, these methods improve the positioning accuracy of UAV images in satellite images. Finally, we also use style transfer technology to simulate various environmental changes in order to expand the experimental data, further proving the environmental adaptability and robustness of the method. The final experimental results show that our method yields significant performance improvement: The relative distance score (RDS) of the SSPT-384 model on the benchmark UL14 dataset is significantly improved from 76.25% to 84.40%, while the meter-level accuracy (MA) of 3 m, 5 m, and 20 m is increased by 12%, 12%, and 10%, respectively. For the SSPT-256 model, the RDS has been increased to 82.21%, and the meter-level accuracy (MA) of 3 m, 5 m, and 20 m has increased by 5%, 5%, and 7%, respectively. It still shows strong robustness on the extended thermal infrared (TIR), nighttime, and rainy day datasets.