摘要
针对无人机航拍视角下对小目标的检测仍存在漏检现象严重、检测精度低等问题,提出一种改进的YOLOX网络,用于无人机航拍图像的检测。为了增强网络的特征学习能力,在特征融合部分引入自适应空间特征融合(ASFF)模块,并在网络的颈部(Neck)嵌入坐标注意力机制(CA)。为了加强网络对正样本的学习,将二元交叉熵损失函数替换为变焦距损失函数。实验结果表明:改进后的YOLOX网络具有更好的检测效能,其mAP@50和mAP@50_95分别达到了91.50%和79.65%。在多种交通场景下的可视化结果表明:相较于其他算法,优化后的网络具有更低的漏检率以及更高的检测精度,能够胜任小目标车辆的检测任务,可为高空视角下的车辆多目标跟踪应用提供参考。
Aiming at the issues of severe missed detections and low detection accuracy for small targets in the perspective of drone aerial photography,an improved YOLOX network is proposed for the detection of drone aerial images.To enhance the feature learning ability of the network,the ASFF module is introduced in the feature fusion part,and the CA mechanism is embedded in the neck of the network.To enhance the network's learning of positive samples,the binary cross-entropy loss function is replaced with the varifocal loss function.Experimental results show that the improved YOLOX network has better detection efficiency,and its mAP@50 reaches 91.50%and mAP@50_95 reached 79.65%.The visualization results in various traffic scenarios show that compared with other algorithms,the optimized network has a lower missed detection rate and higher detection accuracy,which can be competent for the detection task of small target vehicles,and can provide a reference for vehicle multi-target tracking applications from a highaltitude perspective.
作者
张河山
范梦伟
谭鑫
郑展骥
寇立明
徐进
ZHANG He-shan;FAN Meng-wei;TAN Xin;ZHENG Zhan-ji;KOU Li-ming;XU Jin(School of Traffic&Transportation,Chongqing Jiaotong University,Chongqing 400074,China;Chongqing Key Laboratory of"Human-Vehicle-Road"Cooperation and Safety for Mountain Complex Environment,Chongqing Jiaotong University,Chongqing 400074,China;Chongqing Transportation Planning and Research Institute,Chongqing 400074,China)
出处
《吉林大学学报(工学版)》
北大核心
2025年第4期1307-1318,共12页
Journal of Jilin University:Engineering and Technology Edition
基金
教育部人文社会科学研究青年基金项目(24YJCZH412)
国家自然科学基金项目(52172340)
重庆市教育委员会青年项目(KJQN202200710)
重庆市博士后科学基金项目(CSTB2022NSCQ-BHX0731)
重庆交通大学研究生科研创新项目(CYS23498).
关键词
交通运输系统工程
小目标车辆检测
损失函数
坐标注意力机制
自适应空间特征融合
YOLOX
engineering of communications and transportation system
small target vehicle detection
loss function
coordinate attention mechanism
adaptive spatial feature fusion
YOLOX
