陕西师范大学学报（自然科学版）2026，Vol.54Issue(5)：94-105,12.DOI:10.15983/j.cnki.jsnu.2026509
YOLOv8-Aerial:面向无人机航拍图像的目标检测优化方法
YOLOv8-Aerial:object detection optimization for unmanned aerial vehicle aerial images
摘要
Abstract
Object detection for aerial images is crucial for smart cities and disaster monitoring but faces challenges like complex backgrounds,scale variations among objects,and densely distributed small objects.To address these challenges,a YOLOv8-Aerial model is proposed that systematically optimizes three key components of YOLOv8s:the feature extraction network,feature fusion network,and detection head.First,a C2f_MaskUnitAtt module incorporating a masked attention mechanism is designed to enhance the model's feature extraction capability in complex backgrounds.Next,for feature fusion,a bidirectional adjacent layer feature fusion method combined with a super-resolution enhancement strategy is proposed,to fully exploit multi-scale features and mitigate the feature attenuation problem of small objects in deep networks.For the final detection,a small object-oriented detection head is additionally introduced and a local feature enhancement module with dilated convolution is designed to improve detection accuracy for small objects.Experimental results demonstrate our model's superiority over existing models.关键词
目标检测/航拍图像/多尺度特征融合/超分辨率Key words
object detection/aerial images/multi-scale feature fusion/super-resolution分类
信息技术与安全科学引用本文复制引用
张翼,黄志清,王宏伟,池曦锵,高健,胡文霞..YOLOv8-Aerial:面向无人机航拍图像的目标检测优化方法[J].陕西师范大学学报（自然科学版）,2026,54(5):94-105,12.基金项目
温州图盛控股集团有限公司科技项目(CF058807002023004) （CF058807002023004）
