结合重参数化与多层次特征融合的航拍图像小目标检测  

Small Target Detection for Aerial Image Combining Reparameterization and Multi-level Feature Fusion

作　　者：曹洁[1,2] 李立晶 梁浩鹏 CAO Jie;LI Li-Jing;LIANG Hao-Peng(School of Computing and Communications,Lanzhou University of Science and Technology,Lanzhou 733050,China;School of Information Engineering,Lanzhou City University,Lanzhou 733070,China)

机构地区：[1]兰州理工大学计算机与通信学院,兰州733050 [2]兰州城市学院信息工程学院,兰州733070

出　　处：《计算机系统应用》2025年第4期218-227,共10页Computer Systems & Applications

基　　金：甘肃省重点研发计划(22YF7GA130)。

摘　　要：针对无人机航拍图像目标尺寸小、分布密集且被遮挡造成误检漏检等问题,提出一种结合重参数化思想与多层次特征融合的航拍图像小目标检测算法.首先,利用重参数化思想设计了重参数化卷积模块(reparameterized convolution module,RCM),与C2f模块结合设计了C2f-RCM模块,通过扩大感受野有效绘制上下文信息,更好地提取图像中的细微特征.其次,为解决颈部网络在特征融合部分造成的信息丢失问题,提出一种多层次特征融合模块(multi-level feature fusion module,MFFM),该模块利用跨层次间的信息融合,有效减少了在遮挡情况下的漏检现象,使得网络在检测大、中、小目标时能够显著提升准确度.最后,提出一种Inner-Shape IoU边界框回归损失函数,通过构建辅助边框和关注边界框的自身形状,以增强模型的收敛速度.实验结果表明,与基线模型相比,本文方法在VisDrone2019中,mAP@0.5、Precision、Recall分别提高了5.7%、5.7%、2.4%,在AI-TOD中,mAP@0.5、Precision、Recall提升了3.7%、3.9%、5.3%,验证了本文方法在航拍图像小目标检测方面的有效性.To address the problems of small target size,dense distribution,and occlusion caused false detection and missed detection in unmanned aerial vehicle(UAV)aerial images,this study proposes a small target detection algorithm for aerial images which combines reparameterization and multi-level feature fusion.Firstly,the reparameterized convolution module(RCM)is designed by using the idea of reparameterization,and the C2f-RCM module is designed by combining the RCM with the C2f module,which can effectively draw contextual information by enlarging the sensory field and better extract the subtle features in the images.Secondly,to solve the problem of information loss caused by the neck network in the feature fusion part,this study proposes a multi-level feature fusion module(MFFM),which utilizes cross-level information fusion to effectively reduce the missed detection phenomenon in the case of occlusion,so that the network is able to detect large,medium,and small targets with a significant improved accuracy.Finally,an Inner-Shape IoU bounding box regression loss function is proposed to enhance the convergence speed of the model by constructing auxiliary borders and focusing on the shape of the bounding box.Compared with the baseline model,the proposed method improves mAP@0.5,Precision,and Recall by 5.7%,5.7%,and 2.4%in VisDrone2019 and 3.7%,3.9%,and 5.3%in AI-TOD,respectively,which verifies that the proposed method is effective in detecting small targets in aerial images.

关 键 词：小目标检测 重参数化 特征融合 损失函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]