基于改进YOLOv5s的无人机小目标检测算法  

UAV small target detection algorithm based on improved YOLOv5s

作　　者：宋耀莲[1] 王粲 李大焱[1] 刘欣怡 SONG Yaolian;WANG Can;LI Dayan;LIU Xinyi(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《浙江大学学报（工学版）》2024年第12期2417-2426,共10页Journal of Zhejiang University：Engineering Science

基　　金：国家自然科学基金资助项目(61962032);云南省优秀青年基金资助项目(202001AW070003);云南省基础研究计划面上资助项目(202301AT070452)。

摘　　要：为了解决传统目标检测算法对无人机(UAV)航拍小目标存在错漏检严重的问题,提出基于YOLOv5的无人机小目标检测算法FDB-YOLO.在YOLOv5的基础上增加小目标检测层,优化特征融合网络,充分利用网络浅层小目标细粒信息,提升网络感知能力;提出损失函数FPIoU,通过充分利用锚框的几何性质,采用四点位置偏置约束函数,优化锚框定位,加快损失函数收敛速度;采用结合注意力机制的动态目标检测头(DyHead),通过增加尺度、空间、任务感知提升算法检测能力;在特征提取部分引入双级路由注意力机制(BRA),通过有选择性地对相关区域进行计算,过滤无关区域,提升模型的检测精确度.实验证明,在VisDrone2019数据集上,本算法与YOLOv5s目标检测算法相比,精确率提升了3.7个百分点,召回率提升了5.1个百分点,mAP50增加了5.8个百分点,mAP_(50∶95)增加3.4个百分点,并且相比当前主流算法而言都有更加优秀的表现.An unmanned aerial vehicle(UAV)small target detection algorithm based on YOLOv5,termed FDB-YOLO,was proposed to address the significant issue of misidentification and omissions in traditional target detection algorithms when applied to UAV aerial photography of small targets.Initially,a small target detection layer was added on the basis of YOLOv5,and the feature fusion network was optimized to fully leverage the fine-grained information of small targets in shallow layers,thereby enhancing the network’s perceptual capabilities.Subsequently,a novel loss function,FPIoU,was introduced,which capitalized on the geometric properties of anchor boxes and utilized a four-point positional bias constraint function to optimize the anchor box positioning and accelerate the convergence speed of the loss function.Furthermore,a dynamic target detection head(DyHead)incorporating attention mechanism was employed to enhance the algorithm’s detection capabilities through increased awareness of scale,space,and task.Finally,a bi-level routing attention mechanism(BRA)was integrated into the feature extraction phase,selectively computing relevant areas to filter out irrelevant regions,thereby improving the model’s detection accuracy.Experimental validation conducted on the VisDrone2019 dataset demonstrated that the proposed algorithm outperformed the YOLOv5s baseline in terms of Precision by an increase of 3.7 percentage points,Recall by an increase of 5.1 percentage points,mAP_(50) by an increase of 5.8 percentage points,and mAP_(50:95) by an increase of 3.4 percentage points,showcasing superior performance compared to current mainstream algorithms.

关 键 词：无人机视角 小目标检测层 损失函数 注意力机制 YOLOv5 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]