[1]黄祎闻,甄子洋,何佳璐.基于 YOLOv8 的无人机编队领航者检测算法[J].机械与电子,2024,42(08):40-45.
　UANG Yiwen,ZHEN Ziyang,HE Jialu.UAV Formation Leader Detection Algorithm Based on YOLOv8[J].Machinery & Electronics,2024,42(08):40-45.
点击复制

基于 YOLOv8 的无人机编队领航者检测算法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年08期
页码:
40-45
栏目:
自动控制与检测
出版日期:
2024-08-31

文章信息/Info

Title:
UAV Formation Leader Detection Algorithm Based on YOLOv8
文章编号:
1001-2257 ( 2024 ) 08-0040-06
作者:
黄祎闻; 甄子洋; 何佳璐
南京航空航天大学自动化学院,江苏 南京 211106
Author(s):
UANG Yiwen ;  ZHEN Ziyang ;  HE Jialu
( College of Automation Engineering , Nanjing University of Aeronautics and Astronautics , Nanjing 211106 , China )
关键词:
无人机编队;  YOLOv8 ; 可变形卷积; 多头自注意力机制
Keywords:
UAV formation ;  YOLOv8 ;  deformable convolution ;  multi head attention mechanism
分类号:
TP242.6
文献标志码:
A
摘要:
基于视觉的无人机编队方法具有不受通信拒止影响的优点,与传统编队算法相比有更强的鲁棒性,逐渐成为了领域内的研究热点。在 Leader-Follower 无人机视觉编队模式中,跟随者通过对领航者执行实时目标检测,并解算出领航跟随者之间的相对位置关系来完成编队控制任务。基于 YOLOv8n 目标检测模型提出了一种改进的实时目标检测算法:在 Neck 模块中加入可变形卷积模块;加入多头注意力机制增强特征提取;在训练过程中进行数据增强。为验证所提算法的性能优势,进行了 2 次对比测试,实验结果表明,改进算法比原始算法的特征提取效果更强,检测精度更高。最后,将改进的领航者检测算法应用于无人机编队任务中,证明了所提算法的实际应用价值。
Abstract:
The vision-based unmanned aerial vehicle ( UAV ) formation method has the advantage of being unaffected by communication disruptions and exhibits greater robustness compared to traditional formation algorithms , gradually becoming a research hotspot in the field.In the Leader Follower UAV visual formation mode , followers achieve formation control by performing real-time target detection on the leader and calculating the relative positional relationship between the leader and the followers.This paper proposes an improved real-time object detection algorithm based on the YOLOv8n object detection model : convolution modules were added in the Neck module , a multi head attention mechanism was added to enhance feature extraction , apply data augmentation was applied? in the training process.To validate the performance advantages of the algorithm proposed , two comparative tests were conducted.The experimental results indicate that the improved algorithm exhibits stronger feature extraction and higher detection accuracy compared to the original algorithm.Finally , the improved object detection algorithm is applied to drone formation tasks , demonstrating the practical utility of the algorithm in this context.

参考文献/References:

[ 1 ] N?GELI T , CONTE C , DOMAHIDI A , et al.Environment-independent formation flight for micro aerial vehicles [ C ] ∥2014 IEEE / RSJ International Conference on Intelligent Robots and Systems.New York : IEEE , 2014 : 1141-1146.

[ 2 ] SUBBOTIN M V , SMITH R S.Distributed estimator design for a formation with markovian communication topology [ C ] ∥2007 American Control Conference.New York : IEEE , 2007 : 5046-5051.
[ 3 ] SASKA M , VON?SEK V , CHUDOBA J , et al.Swarm distribution and deployment for cooperative surveillance by micro-aerial vehicles [ J ] .Journal of intelligent and robotic systems , 2016 , 84 : 469-492.
[ 4 ] NITSCHE M , KRAJNIK T , CIZEK P , et al.WhyCon : an efficient , marker-based localization system [ C ] ∥IROS Workshop on Open Source Aerial Robotics , 2015.
[ 5 ] 闵欢,卢虎,史浩东 . 采用深度神经网络的无人机蜂群视觉协同控制算法[ J ] . 西安交通大学学报,2020 , 54( 9 ): 173-179 , 196.
[ 6 ] 管任多 . 基于视觉跟踪的四旋翼无人机编队研究与实现[ D ] . 南昌:南昌大学,2021.
[ 7 ] JIANG P Y , ERGU D , LIU F Y , et al.A review of YOLO algorithm developments [ J ] .Procedia computer science , 2022 , 199 : 1066-1073.
[ 8 ] REDMON J , DIVVALA S , GIRSHICK R , et al.You only look once : unified , real-time object detection [ C ] ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2016 : 779-788.
[ 9 ] REDMON J , FARHADI A.YOLO9000 : better , faster , stronger [ C ] ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 6517-6525.
[ 10 ] ZHU X K , LYU S C , WANG X , et al.TPH YOLOv5 : improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios [ C ] ∥Proceedings of the IEEE / CVF International Conference on Computer Vision , 2021 :2778-2788.
[ 11 ] WANG C Y , BOCHKOVSKIY A , LIAO H Y M. YOLOv7 : trainable bag-of-freebies sets new state of-the-art for real-time object detectors [ C ] ∥Proceedings of the IEEE / CVF Conference on Computer Vision and Pattern Recognition , 2023 : 7464-7475.

备注/Memo

备注/Memo:
收稿日期: 2023-10-12
作者简介:黄祎闻 ( 1998- ),男,江苏无锡人,硕士研究生,研究方向为视觉伺服控制;甄子洋 ( 1981- ),男,浙江金华人,博士,教授,研究方向为舰载机/无人机着舰引导与控制、无人机集群编队协同控制与决策等。
更新日期/Last Update: 2024-09-02