We introduce a sophisticated detection framework named UAV-YOLOv5, which amalgamates the strengths of Swin Transformer V2 and YOLOv5. Firstly, we introduce Focal-EIOU, a refinement of the K-means algorithm tailored to generate anchor boxes better suited for the current dataset, thereby improving ...
Compared with the basal YOLOv5, SPH-YOLOv5 improves the mean Average Precision (mAP) by 0.071 on the DOTA dataset. Keywords: satellite images; object detection; self-attention mechanism; Swin transformer; deep learning Graphical Abstract1. Introduction Earth satellite technology usually acquires high-...