Research on UAV Target Detection Based on Improved YOLOv11

Abstract

In response to the challenges of small object detection in UAV aerial photog-raphy, such as complex backgrounds, tiny targets, dense targets, and edge de-ployment, the YOLOv11n model was improved. Specifically, an EfficiBack-bone module was designed for the backbone part, the C3K2 was improved using the RipViT block in the Neck part, and the original detection head was replaced with a dynamic detection head. The improved YOLOv11 network was thus completed. Experimental results show that the model has signifi-cantly improved mAP@0.5 and mAP@0.5:0.95 on the VisDrone2019 dataset, proving the effectiveness of the model.