改进YOLOv11n的无人机小目标检测算法  

Improved YOLOv11n Small Object Detection Algorithm in UAV View

作　　者：李彬[1] 李生林 LI Bin;LI Shenglin(School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学软件工程学院,重庆400065

出　　处：《计算机工程与应用》2025年第7期96-104,共9页Computer Engineering and Applications

基　　金：国家自然科学基金(62106205)。

摘　　要：为了有效应对无人机航拍中小目标检测面临的复杂背景、目标密集、目标微小化和移动端部署等挑战,对YOLOv11n模型进行了改进。使用RFCBAMConv模块改进C3k2,增强了特征提取能力。设计了膨胀特征金字塔卷积(dilated featurepyramidconvolution,DFPC)模块,替代了原有的SPPF层。通过多尺度膨胀卷积,加强了对无人机小目标细节特征的提取。提出了一种新的特征金字塔结构,在P2层增加160×160尺寸的特征图输出,以提取小目标特征信息。该方法替代了传统通过添加P2小目标检测头的做法。引入了CSPOK模块和ContextGuidedBlock_Down(CGBD)卷积,显著提升了全局特征的提取能力和多尺度特征的融合能力。采用动态检测头(DyHead)替代了原有的检测头,提升了模型的目标检测精度。实验结果表明,改进模型在VisDrone数据集上的mAP@0.5和mAP@0.5:0.95指标分别提高了0.071和0.049。此外,在AI-TOD和SODA-A等数据集上的泛化实验也显示,改进模型在mAP@0.5上分别获得0.055和0.048的提升,充分验证了模型的有效性和泛用性。In order to effectively deal with the challenges of complex background,dense target,target miniaturization and mobile terminal deployment faced by small target detection in UAV aerial photography,the YOLOv11n model is improved.Firstly,RFCBAMConv module is used to improve C3k2,which enhances the ability of feature extraction.Then,the dilated feature pyramid convolution(DFPC)module is designed to replace the original SPPF layer.Through multi-scale dilated convolution,the extraction of small target detail features of UAV is strengthened.Secondly,a new feature pyramid structure is proposed,and a feature map output of 160×160 size is added to the P2 layer to extract the feature information of small targets.This method replaces the traditional practice of adding P2 small target detection head.The CSPOK module and ContextGuidedBlock_Down(CGBD)convolution are introduced,which significantly improves the extraction ability of global features and the fusion ability of multi-scale features.Finally,the dynamic detection head(DyHead)is used to replace the original detection head,which improves the target detection accuracy of the model.The experimental results show that the mAP@0.5 and mAP@0.5:0.95 indicators of the improved model on the VisDrone dataset are increased by 0.071 and 0.049,respectively.In addition,the generalization experiments on AI-TOD and SODA-A datasets also show that the improved model achieves 0.055 and 0.048 improvement in mAP@0.5,respectively,which fully verifies the effectiveness and universality of the model.

关 键 词：小目标检测 YOLOv11 特征提取 感受野注意力 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]