Robust Landmark Detection and Position Measurement Based on Monocular Vision for Autonomous Aerial Refueling of UAVs
Sun, Siyang1,2; Yin, Yingjie1,2; Wang, Xingang1,2; Xu, De1,2
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267
2019-12-01
卷号49期号:12页码:4167-4179
通讯作者Yin, Yingjie(yingjie.yin@ia.ac.cn)
摘要In this paper, a position measurement system, including drogue's landmark detection and position computation for autonomous aerial refueling of unmanned aerial vehicles, is proposed. A multitask parallel deep convolution neural network (MPDCNN) is designed to detect the landmarks of the drogue target. In MPDCNN, two parallel convolution networks are used, and a fusion mechanism is proposed to accomplish the effective fusion of the drogue's two salient parts' landmark detection. Considering the drogue target's geometric constraints, a position measurement method based on monocular vision is proposed. An effective fusion strategy, which fuses the measurement results of drogue's different parts, is proposed to achieve robust position measurement. The error of landmark detection with the proposed method is 3.9%, and it is obviously lower than the errors of other methods. Experimental results on the two KUKA robots platform verify the effectiveness and robustness of the proposed position measurement system for aerial refueling.
关键词Aerial refueling landmark detection monocular vision multitask parallel deep convolution neural network (MPDCNN) position measurement
DOI10.1109/TCYB.2018.2859422
关键词[WOS]POSE ESTIMATION ; LOCALIZATION ; ALGORITHMS ; STRATEGY ; BOOM
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61573349] ; National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61703398] ; National High Technology Research and Development Program of China (863 Program)[2015AA042308] ; National Natural Science Foundation of China[61573349] ; National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61703398] ; National High Technology Research and Development Program of China (863 Program)[2015AA042308]
项目资助者National Natural Science Foundation of China ; National High Technology Research and Development Program of China (863 Program)
WOS研究方向Automation & Control Systems ; Computer Science
WOS类目Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号WOS:000485687200010
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类机器人感知与决策
引用统计
被引频次:36[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21699
专题精密感知与控制研究中心_精密感知与控制
通讯作者Yin, Yingjie
作者单位1.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位精密感知与控制研究中心
通讯作者单位精密感知与控制研究中心
推荐引用方式
GB/T 7714
Sun, Siyang,Yin, Yingjie,Wang, Xingang,et al. Robust Landmark Detection and Position Measurement Based on Monocular Vision for Autonomous Aerial Refueling of UAVs[J]. IEEE TRANSACTIONS ON CYBERNETICS,2019,49(12):4167-4179.
APA Sun, Siyang,Yin, Yingjie,Wang, Xingang,&Xu, De.(2019).Robust Landmark Detection and Position Measurement Based on Monocular Vision for Autonomous Aerial Refueling of UAVs.IEEE TRANSACTIONS ON CYBERNETICS,49(12),4167-4179.
MLA Sun, Siyang,et al."Robust Landmark Detection and Position Measurement Based on Monocular Vision for Autonomous Aerial Refueling of UAVs".IEEE TRANSACTIONS ON CYBERNETICS 49.12(2019):4167-4179.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Robust Landmark Dete(2687KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Sun, Siyang]的文章
[Yin, Yingjie]的文章
[Wang, Xingang]的文章
百度学术
百度学术中相似的文章
[Sun, Siyang]的文章
[Yin, Yingjie]的文章
[Wang, Xingang]的文章
必应学术
必应学术中相似的文章
[Sun, Siyang]的文章
[Yin, Yingjie]的文章
[Wang, Xingang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Robust Landmark Detection and Position Measurement Based on Monocular Vision for Autonomous Aerial Refueling of UAVs.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。