融合多特征与自注意力的室外直升机桨叶旋转目标检测  

Fusion of multi-feature and self-attention for rotating target detection of outdoor helicopter blades

作　　者：徐飞龙 熊邦书[1] 欧巧凤[1] 余磊[1] 饶智博 Xu Feilong;Xiong Bangshu;Ou Qiaofeng;Yu Lei;Rao Zhibo(Provincial Key Laboratory of Image Processing and Pattern Recognition,Nanchang Hangkong University,Nanchang 330063,China)

机构地区：[1]南昌航空大学图像处理与模式识别省重点实验室,南昌330063

出　　处：《中国图象图形学报》2025年第1期240-253,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62473187,61866027);江西省重点研发计划资助(20212BBE53017);江西省研究生创新专项资金项目(YC2022-043)。

摘　　要：目的桨叶运动参数是直升机设计到生产的重要指标,传统的视觉测量方法直接应用于室外环境下,由于受复杂光照背景影响,存在找不到桨叶区域、不能进行准确测量的问题。据此,本文提出一种融合多特征与自注意力的旋转目标检测器(fusion multi-feature and self-attention rotating detector,FMSA-RD)。方法首先,针对YOLOv5s(you only look once)特征提取能力不足和冗余问题,在主干网络中设计了更为有效的多特征提取和融合模块,结合不同时刻位置与尺度下的特征信息以提高网络对室外桨叶的检测精度;并去掉部分无关卷积层以简化模块结构参数。其次,融合多头自注意力机制与CSP(crossstage partial convolution)瓶颈结构,整合全局信息以抑制室外复杂光照背景干扰。最后,引入倾斜交并比(skew intersection over union,SKEWIOU)损失和角度损失,改进损失函数,进一步提升桨叶检测精度。结果本文进行了多组对比实验,分别在自制的室外直升机桨叶数据集和公共数据集DOTA-v1.0(dataset for object detection in aerial images)上进行验证,对比基线YOLOv5s目标检测网络,本文模型平均精度均值(mean average precision,mAP)分别提高6.6%和12.8%,帧速率(frames per second,FPS)分别提高21.8%和47.7%。结论本文设计的旋转目标检测模型,提升了室外复杂光照背景下桨叶的检测精度和速度。Objective The motion parameters of helicopter rotor blades include flapping angle,lead-lag angle,twist angle,and coning angle,which provide an important basis for rotor structure design,upper and lower limit block design of hub,and blade load design.They are important parameters that need to be measured in ground tests before rotorcraft certifica⁃tion and helicopter flight tests.The traditional visual measurement method for rotor blade motion parameters has achieved good results in indoor wind tunnel environments.However,under the influence of complex outdoor backgrounds,some problems exist,such as the inability to detect the rotor blades from the image and measure the parameters accurately.Unlike indoor environments,the outdoors have complex lighting conditions such as different seasons,weather,times,and lighting directions,as well as different sky and background environments.Under these complex background interferences,the features of the rotor blades are weakened,making it difficult to accurately locate the position of the rotor blades.Deep learning is a mainstream object detection method,and how to design deep learning models to enhance the target features of rotor blades and reduce the interference of complex backgrounds is a major challenge.In this paper,on the basis of the net⁃work structure of the YOLOv5s,a prediction angle branch is added,and a rotation object detector(FMSA-RD)that fuses multiple features and self-attention is proposed to facilitate the detection of outdoor helicopter rotor blades.Method First,the FMSA-RD model improves the C3 module used for feature extraction in YOLOv5s by adding multiple shortcuts.The improved feature extraction module is called convolution five(C5),which completes the feature extraction by fusing local features from different positions,thereby reducing the network structure while maintaining the feature extraction ability.Specifically,C5 replaces the BottleNeck module in C3 with two 3×3 convolution kernels to avoid the additional overhead caused by using multipl

关 键 词：室外直升机桨叶 旋转目标检测 多特征 多头自注意力机制(MHSA) 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] V275.1[自动化与计算机技术—计算机科学与技术]