基于全局—局部上下文自适应加权融合的红外飞机检测算法  

Infrared aircraft detection algorithm based on adaptive weighted fusion of global-local context

作　　者：徐红鹏 刘刚 习江涛 童军 Xu Hongpeng;Liu Gang;Xi Jiangtao;Tong Jun(College of Information Engineering,Henan University of Science and Technology,Luoyang 471023,China;School of Electrical,Computer and Telecommunications Engineering,University of Wollongong,Wollongong,New South Walse 2522,Australia)

机构地区：[1]河南科技大学信息工程学院,洛阳471023 [2]伍伦贡大学电气计算机与通信工程学院,澳大利亚伍伦贡NSW 2522

出　　处：《中国图象图形学报》2025年第3期710-723,共14页Journal of Image and Graphics

基　　金：国家留学基金资助([2022]20);河南省高等学校重点科研项目(21A520012)。

摘　　要：目的针对远距离红外飞机目标检测中存在的由于成像面积小、辐射强度较弱造成无法充分提取目标特征进而影响检测性能的问题,提出一种基于全局—局部上下文自适应加权融合(adaptive weighted fusion of globallocal context,AWFGLC)机制的红外飞机目标检测算法。方法基于全局—局部上下文自适应加权融合机制,沿着通道维度随机进行划分与重组,将输入特征图切分为两个特征图。一个特征图使用自注意力进行全局上下文建模,建立目标特征与背景特征之间的相关性,突出目标较显著的特征,使得检测算法更好地感知目标的全局特征。对另一特征图进行窗口划分并在每个窗口内进行最大池化和平均池化以突出目标局部特征,随后使用自注意力对池化特征图进行局部上下文建模,建立目标与其周围邻域的相关性,进一步增强目标特征较弱的部分,使得检测算法更好地感知目标的局部特征。根据目标特点,利用可学习参数的自适应加权融合策略将全局上下文和局部上下文特征图进行聚合,得到包含较完整目标信息的特征图,增强检测算法对目标与背景的判别能力。结果将全局—局部上下文自适应加权融合机制引入YOLOv7(you only look once version 7)并对红外飞机目标进行检测,实验结果表明,提出算法在自制和公开红外飞机数据集的mAP50(mean average precision 50)分别达到97.8%、88.7%,mAP50:95分别达到65.7%、61.2%。结论本文所提出的红外飞机检测算法,优于经典的目标检测算法,能够有效实现红外飞机目标检测。Objective An infrared aircraft target detection algorithm based on adaptive weighted fusion of global-local context(AWFGLC)is proposed to address the challenge of insufficient target feature extraction due to the small imaging area and weak radiation intensity in long-range infrared aircraft target detection.The global context focuses on the overall distribution of the target,providing the detection algorithm with global information regarding targets in images with strong radiation intensity and clear contours.In contrast,the local context emphasizes the local details of the target and the surrounding background information,offering the detection algorithm local information regarding targets with weak radiation intensity and blurred contours.Therefore,the global context and local context should be combined in accordance with the target characteristics in practical applications.Method Based on the global-local context adaptive weighted fusion mechanism,the input feature map is randomly divided and reorganized along the channel dimensions,resulting in two separate feature maps.Compared with global and local context modeling for input feature maps based on a specific arrangement or simply dividing the input feature map into two feature maps,the arrangement of the input feature map during iterative training can be diversely changed by randomly reorganizing it with different random numbers in each training round.Global and local context modeling can help the detection algorithm learn additional diversified and comprehensive features by combining feature maps with different arrangements.The global and local context modeling of different combinations of feature maps can enable learning of additional diverse and comprehensive features through the detection algorithm.Moreover,the complexity of contextual modeling is reduced by half by dividing the input feature maps equally in the channel dimension and performing global and local contextual modeling to reduce the complexity of contextual modeling of input feature maps.A f

关 键 词：红外飞机 目标检测 全局上下文 局部上下文 自适应加权 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]