无线电通信技术2025，Vol.51Issue(2)：362-366,5.DOI:10.3969/j.issn.1003-3114.2025.02.018
无人系统传输与在线智能处理实时优化技术研究
Research on Real Time Optimization Technology for Unmanned System Transmission and Online Intelligent Processing
摘要
Abstract
Unmanned aerial vehicle has been widely used in both military and civilian fields.However,the application of un-manned systems faces significant challenges such as limited transmission resources.It is necessary to adaptively adjust the information transmission content of unmanned systems based on the different security requirements of task environments,scenarios,and stages,u-sing intelligent detection and recognition methods for multi-source image targets.This paper proposes a novel multi-source image target detection and recognition method,which optimizes the classic YOLO architecture,including optimization of spatial pyramid architec-ture,Path Aggregation Network(PAN)structure,label smoothing,and loss function optimization.Experimental results demonstrates good performance in multi-source image target detection and recognition.关键词
无人机/目标检测识别/YOLO/空间金字塔/标签平滑/损失函数优化Key words
unmanned aerial vehicle/object detection and recognition/YOLO/spatial pyramid/label smoothing/loss function optimization分类
计算机与自动化引用本文复制引用
李忠涛,陈彦桥,苏阳,杨建永..无人系统传输与在线智能处理实时优化技术研究[J].无线电通信技术,2025,51(2):362-366,5.基金项目
国家自然科学基金青年科学基金(62101517) Youth Science Fund of the National Natural Science Foundation of China(62101517) （62101517）
