火力与指挥控制2026，Vol.51Issue(4)：74-82,90,10.DOI:10.3969/j.issn.1002-0640.2026.04.009
基于KFSI-YOLOv5的无人机航拍图像遮挡小目标检测算法
Detection Algorithm for Occluded Small Targets in UAV Aerial Images Based on KFSI-YOLOv5
摘要
Abstract
A KFSI-YOLOv5 algorithm is proposed to address the problem of small and heavily occluded targets in aerial images.Firstly,K-Means++clustering is used to generate optimal anchor boxes suitable for aerial targets.Secondly,the Fp-SEAM attention mechanism is proposed and fused with the FPN P2 layer to improve the detection accuracy of occluded small targets.Then a dynamic label assignment strategy is adopted,which can assign sub-optimal labels for severely occluded targets.Finally,an α-Inner IoU loss function is proposed to make bounding box regression more accurate.Experiments on the VisDrone,Carpk and WiderPerson datasets verify that the proposed algorithm can effectively accomplish the task of occluded small target detection in aerial images.关键词
航拍图像/无人机/注意力机制/YOLOv5/遮挡小目标检测Key words
aerial image/UAV/attention mechanism/YOLOv5/occluded small target detection分类
信息技术与安全科学引用本文复制引用
刘洋,魏宇宁,徐晓淼,王竹筠..基于KFSI-YOLOv5的无人机航拍图像遮挡小目标检测算法[J].火力与指挥控制,2026,51(4):74-82,90,10.基金项目
国家自然科学基金(62003224) （62003224）
辽宁省教育厅基金资助项目(JYT2020042) （JYT2020042）
