复杂背景下的轻量级遥感军用飞机目标检测  

Lightweight remote sensing military aircraft target detection in complex backgrounds

作　　者：周韩莲 叶青[1] 刘文祺 Zhou Hanlian;Ye Qing;Liu Wenqi(School of Computer Science,Yangtze University,Jingzhou,Hubei 434023,China)

机构地区：[1]长江大学计算机科学学院,湖北荆州434023

出　　处：《光电工程》2025年第2期82-96,共15页Opto-Electronic Engineering

基　　金：国家自然科学基金项目(62006028);湖北省自然科学基金项目(2023AFB909)。

摘　　要：针对遥感图像军用飞机中背景复杂、目标尺度小所导致的识别精度低、计算成本高、模型体积大等问题,提出一种融合重参数化和细节增强的轻量级军用飞机目标检测算法YOLOv8-MA。首先,融合重参数化设计多分支梯度流通特征提取模块,提高模型推理速度;其次,结合Efficient RepGFPN舍弃冗余模型结构,融入P2层,构建多尺度特征融合网络,改善因过多下采样带来的小目标信息丢失问题;在此之上,结合群范卷积和细节增强提出轻量级检测头,减少模型参数量和计算量;最后,向Shape-IoU中引入聚焦系数融合成新的损失函数,提升模型检测性能。在公开军用飞机数据集MAR20上,该算法的m AP50高达97.9%,模型体积低至2.1 MB,相较于YOLOv8n参数量下降了74.7%,计算量下降了40.7%,FPS提高了14 f/s,证明其能够有效提升遥感图像中军用飞机的检测效果。Aiming at the issues of low recognition accuracy,high computational cost,and large model size caused by the complex background and small target scale in remote sensing images of military aircraft,a lightweight military aircraft target detection algorithm,namely YOLOv8-MA,integrating reparameterization and detail enhancement is proposed.Firstly,a multi-branch gradient flow feature extraction module is designed through reparameterization to enhance the model's inference speed.Secondly,in combination with efficient RepGFPN,redundant model structures are discarded and the P2 layer is incorporated to construct a multi-scale feature fusion network,mitigating the problem of small target information loss due to excessive downsampling.On this basis,a lightweight detection head is proposed by integrating GN convolution and detail enhancement to reduce the number of model parameters and the amount of computation.Finally,a focus coefficient is introduced into the Shape-IoU to form a new loss function,thereby improving the detection performance of the model.On the public military aircraft dataset MAR20,the mAP50 of this algorithm is as high as 97.9%,and the model size is as low as 2.1 MB.Compared with YOLOv8n,the number of parameters decreases by 74.7%,the amount of computation reduces by 40.7%,and the FPS increases by 14 f/s,demonstrating that it can effectively enhance the detection effect of military aircraft in remote sensing images.

关 键 词：遥感图像 军用飞机 轻量级 聚焦系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]