侯永宏1, 叶秀峰1, 张亮2,3, 李照洋1, 董嘉蓉1
AuthorsHTML:侯永宏1, 叶秀峰1, 张亮2,3, 李照洋1, 董嘉蓉1
AuthorsListE:Hou Yonghong1, Ye Xiufeng1, Zhang Liang2,3, Li Zhaoyang1, Dong Jiarong1
AuthorsHTMLE:Hou Yonghong1, Ye Xiufeng1, Zhang Liang2,3, Li Zhaoyang1, Dong Jiarong1
Unit:1. 天津大学电气自动化与信息工程学院,天津 300072;2. 天津市先进电气工程与能源技术重点实验室,天津 300387;3. 天津工业大学电气工程与自动化学院,天津 300387
Unit_EngLish:1. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
2.Tianjin Key Laboratory of Advanced Electrical Engineering and Energy Technology, Tianjin 300387, China
3. School of Electrical Engineering and Automation, Tianjin Polytechnic University, Tianjin 300387, China
Abstract_Chinese:现行的无人机控制(UAV)主要依靠专业的设备, 由经过专业训练的人来完成.为了更方便的人机交互, 本文提出了一种基于双目视觉和深度学习的手势控制无人机(HRI)方法.用双目视觉提取深度图, 跟踪提取人物所在区域并且设置阈值将人物与背景分离开来, 从而得到只含有人物的深度图.其次, 通过对深度图序列的处理并叠加, 将视频转换为同时含有时间与空间信息的彩色纹理图.本文用深度学习工具Caffe对所得到的彩色纹理图进行了训练与识别, 根据识别结果生成无人机的控制指令.本文所述方法在室内和室外均可使用, 有效范围达到10 m, 可以简化无人机控制复杂度, 对促进无人机普及及拓展无人机应用范围都具有重要意义.
Abstract_English:Traditionally,interacting with unmanned aerial vehicle(UAV)required specialized instrument and well trained operators. In order to reduce the difficulty interacting with UAV,a gesture based human robot interface(HRI)method based on stereo vision and deep learning was proposed in this paper. Firstly,the depth map was extracted using stereo vision. By utilizing tracking algorithm and setting a threshold,the pilot was spilt from background and a depth image with only the pilot in it was obtained. Secondly,a series of depth images were overlaid to generate a colored texture image which includes time and space information at the same time. Then,colored texture images were well learned and classified by a deep convolution neural network with the implementation of Caffe. Finally,UAV controlling command was generated according to the classified results. The proposed method is robust for both indoor and outdoor situations and is effective in 10 m. The study simplifies the control of UAV,and makes significant sense to the popularization of UAV and the extention of its application field.
Keyword_Chinese:人机交互; 双目视觉; 深度学习
Keywords_English:human robot interaction; stereo vision; deep learning
PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=5913
删除或更新信息,请邮件至freekaoyan#163.com(#换成@)
基于深度学习的无人机人机交互系统
本站小编 Free考研考试/2022-01-16
相关话题/系统 无人机
油菜-水稻复种系统一次性施肥对CH4和N2O净排放的影响
徐驰,谢海宽,丁武汉,戴震,张婧,王立刚,李虎.油菜-水稻复种系统一次性施肥对CH4和N2O净排放的影响[J].中国农业科学,2018,51(20):3972-3984https://doi.org/10.3864/j.issn.0578-1752.2018.20.015XUChi,XIEHaiKu ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26施氮和木薯-花生间作对木薯养分积累和系统养分利用的影响
林洪鑫,潘晓华,袁展汽,肖运萍,刘仁根,汪瑞清,吕丰娟.施氮和木薯-花生间作对木薯养分积累和系统养分利用的影响[J].中国农业科学,2018,51(17):3275-3290https://doi.org/10.3864/j.issn.0578-1752.2018.17.004LINHongXin, ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26融合无人机光谱信息与纹理信息的冬小麦生物量估测
刘畅,杨贵军,李振海,汤伏全,王建雯,张春兰,张丽妍.融合无人机光谱信息与纹理信息的冬小麦生物量估测[J].中国农业科学,2018,51(16):3060-3073https://doi.org/10.3864/j.issn.0578-1752.2018.16.003LIUChang,YANGGui ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26大气CO2浓度和温度升高对稻麦轮作生态系统N2O排放的影响
王从,李舒清,刘树伟,邹建文.大气CO2浓度和温度升高对稻麦轮作生态系统N2O排放的影响[J].中国农业科学,2018,51(13):2535-2550https://doi.org/10.3864/j.issn.0578-1752.2018.13.009WANGCong,LIShuQing,LIU ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26小麦根中NADP-脱氢酶系统关键酶活性与根系活力和产量的关系分析
周燕,杨习文,周苏玫,王言景,杨蕊,徐凤丹,梅晶晶,申冠宇,李秋杰,贺德先.小麦根中NADP-脱氢酶系统关键酶活性与根系活力和产量的关系分析[J].中国农业科学,2018,51(11):2060-2071https://doi.org/10.3864/j.issn.0578-1752.2018.11 ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26利用酵母同源重组系统快速构建柑橘叶斑驳病毒的 侵染性克隆
崔甜甜,晏建红,宾羽,李中安,周常勇,宋震.利用酵母同源重组系统快速构建柑橘叶斑驳病毒的侵染性克隆[J].中国农业科学,2018,51(9):1695-1705https://doi.org/10.3864/j.issn.0578-1752.2018.09.007CUITianTian,YANJia ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26一款无人机高光谱传感器的验证及其在玉米叶 面积指数反演中的应用
陈鹏飞,李刚,石雅娇,徐志涛,杨粉团,曹庆军.一款无人机高光谱传感器的验证及其在玉米叶面积指数反演中的应用[J].中国农业科学,2018,51(8):1464-1474https://doi.org/10.3864/j.issn.0578-1752.2018.08.004CHENPengFei,LI ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26中国农牧系统养分管理研究的意义与重点
马林,柏兆海,王选,曹玉博,马文奇,张福锁.中国农牧系统养分管理研究的意义与重点[J].,2018,51(3):406-416https://doi.org/10.3864/j.issn.0578-1752.2018.03.002MALin,BAIZhaoHai,WANGXuan,CAOYuBo,M ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26农牧系统养分管理
马林,马文奇,张福锁.农牧系统养分管理[J].,2018,51(3):401-405https://doi.org/10.3864/j.issn.0578-1752.2018.03.001MALin,MAWenQi,ZHANGFuSuo.NutrientManagementinSoil-Crop-A ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26东北地区农牧系统氮、磷养分流动特征
张晓萌,王寅,焉莉,冯国忠,高强.东北地区农牧系统氮、磷养分流动特征[J].,2018,51(3):417-429https://doi.org/10.3864/j.issn.0578-1752.2018.03.003ZHANGXiaoMeng,WANGYin,YANLi,FENGGuoZhong, ...中国农业科学院科研学术 本站小编 Free考研考试 2021-12-26