基于TLD算法的加油锥套跟踪

高宇, 孔星炜, 董新民, 王海涛, 王健

高宇, 孔星炜, 董新民, 王海涛, 王健. 基于TLD算法的加油锥套跟踪[J]. 应用光学, 2016, 37(3): 385-391. DOI: 10.5768/JAO201637.0302004
引用本文: 高宇, 孔星炜, 董新民, 王海涛, 王健. 基于TLD算法的加油锥套跟踪[J]. 应用光学, 2016, 37(3): 385-391. DOI: 10.5768/JAO201637.0302004
shu
Gao Yu, Kong Xingwei, Dong Xinmin, Wang Haitao, Wang Jian. Refueling drogue tracking based on trackinglearningdetection algorithm[J]. Journal of Applied Optics, 2016, 37(3): 385-391. DOI: 10.5768/JAO201637.0302004
Citation: Gao Yu, Kong Xingwei, Dong Xinmin, Wang Haitao, Wang Jian. Refueling drogue tracking based on trackinglearningdetection algorithm[J]. Journal of Applied Optics, 2016, 37(3): 385-391. DOI: 10.5768/JAO201637.0302004
shu

基于TLD算法的加油锥套跟踪

  • 空军工程大学 航空航天工程学院,陕西 西安 710038

基金项目: 

国家自然科学基金资助项目（61473307）; 空军工程大学优秀博士论文扶持基金（KGD081114006）

详细信息
    作者简介:

    高宇（1992-），男，江苏南通人，硕士研究生，研究方向为飞行控制与仿真技术。 E-mail:15114854294@163.com

  • 中图分类号: TN29;V249.1

Refueling drogue tracking based on trackinglearningdetection algorithm

  • Aeronautics and Astronautics Engineering College,Air Force Engineering University,Xi’an 710038,China

摘要

    摘要
  • 摘要: 针对自主空中加油对接阶段锥套跟踪问题，提出了一种基于trackinglearningdetection (TLD)的锥套跟踪算法。该算法将加油锥套的跟踪任务分解成跟踪、学习、检测3个部分。跟踪模块在LK光流法的基础上添加跟踪失败自检测，筛选出好的跟踪点，跟踪加油锥套；检测模块构建级联分类器，对滑动窗遍历得到的图像块进行分类并返回含有目标的图像块，融合跟踪模块的跟踪框，给出最终跟踪结果；学习模块引入PN约束修正错误样本并学习更新检测模块。利用Creator/Vega Prime软件对空中加油进行视景仿真，在视景仿真视频上测试锥套跟踪算法。结果表明：TLD算法跟踪加油锥套成功率达95.5%，处理每帧平均耗时31.4 ms，能够满足加油锥套跟踪鲁棒性、准确率、实时性的要求。
    Abstract: To solve the drogue tracking problem during the capture phase of autonomous aerial refueling, a trackinglearningdetection (TLD) algorithm was proposed. The algorithm decomposes the drogue tracking task into 3 subtasks: tracking, learning and detection. The tracking component is based on the LucasKanade (LK) method extended with failure detection and chooses tracking points with good performance to track the refueling drogue; and the detector constructs cascaded classifier to sort the picture patches scanned by scanningwindow and returns patches containing object, which integrates with tracking component result and gives final tracking result; and then the PN constraints are introduced into the learning component to correct wrong samples and then learn and update the detector. A scene simulation for aerial refueling was developed based on Creator/Vega Prime. The experimental results of the test on the video of scene simulation show that the success rate of tracking drogue is 95.5%, the average time consumption is about 31.4 ms, and the algorithm can meet well requirements of drogue tracking, such as robustness, precision and real time performance.
    • HTML全文
    • 参考文献(1)
  • [1]Dong Xinmin, Xu Yuejian, Chen Bo. Process and challenges in automatic aerial refueling [J]. Journal of Air Force Engineering University (Natural Science Edition), 2008, 9(6): 15.
    董新民, 徐跃鉴, 陈博. 自动空中加油技术研究进展与关键问题[J]. 空军工程大学学报：自然科学版, 2008, 9 (6)：15.
    [2]Bolkcom C, Klaus J D. Air force aerial refueling methods: flying boom versus hoseanddrogue[R].[S.l.]:[s.n.]， 2005.
    [3]Thomas P R ,  Bhandari U,  Bullock S, et al. Advances in air to air refueling[J]. Progress in Aerospace Science. 2014, 71：1435.
    [4]Hansen J L, Murray J E, Campos N V. The NASA Dryden AAR project: a flight test approach to an aerial refueling system: AIAA Atmospheric Flight Mechanics Conference and Exhibit, Providence, RI,Aug 1619, 2004[C].[S.l.]:[s.n.]，c2005.
    [5]Valasek J, Gunnam K, Kimmett J , et al, Visionbased sensor and navigation system for autonomous air refueling[J]. Guidance Control Dyn. ,2005, 28(5): 832844.
    [6]Pollini L, Innocenti M, Mati R. AIAA modeling and simulation technologies conference and exhibi[C].[S.l.]:[s.n.]，2005:115.
    [7]Wilson D B ,Gktoan A H ,  Sukkarieh S. 2015 IEEE international conference on robotics and automation[C]. USA:IEEE,2015:53185323.
    [8]Gao Shibo, Cheng Yongmei, Song Chuanhua. Drogue detection for visionbased autonomous aerial refueling via low rank and sparse decomposition with multiple features [J]. Infrared Physics and Technology,  2013, 60(9)：266274.
    [9]Martinez C, Richardson T, Thomas P, et al. A visionbased strategy for autonomous aerial refueling tasks [J]. Robotics and Autonomous Systems. 2013, 61(8)：876895.
    [10]Kalal Z , Mikolajczyk K,  Matas J. Trackinglearningdetecti on[J].IEEE Trans. PAMI 2012，34(7)，14091422.
    [11]Kalal Z, Mikolajczyk K. Matas J. 12th IEEE international conference on computer vision workshops(ICCV Workshops)[C].USA:IEEE,2009：14171424.
    [12]Kalal Z, Mikolajczyk K. Matas J. IEEE international conference on computer vision and pattern recognition[C].USA:IEEE, 2010：14171424.
    [13]Kalal Z. Matas J. Mikolajczyk K. IEEE conference on computer vision and pattern recognition(CVPR)[C].USA:IEEE,2010：14171424.
    [14]Wang Xufeng, Dong Xinmin, Kong Xingwei, et al. MSKF fusion algorithm for drogue tracking [J]. Journal of Applied Optics, 2013, 34(6)：951956.
    王旭峰, 董新民, 孔星炜, 等. MSKF 锥套融合算法用于锥套跟踪[J]. 应用光学, 2013, 34(6)：951956.
    [15]Yang Bowen, Sun Yongrong, Huang Bin, et al. HoughLS rapid detection for longdistance refueling drogue image[J]. OptoElectronic Engineering, 2015,42(4):4448.
    杨博文, 孙永荣, 黄斌, 等. 加油锥套远距图像的HoughLS快速检测[J].光电工程, 2015, 42(4)：4448.
    [16]Zhao Yinling, Wu Chengfu, Chen Huaimin. Application and research of UAV scene simulation based on Vega[J]. Measurement & Control Technology, 2008, 27(1): 9699.
    赵银玲, 吴成富, 陈怀民. 基于Vega的无人机视景仿真应用研究[J]. 测控技术, 2008, 27(1): 9699.
    [17]Wang Haitao, Dong Xinmin, Guo Jun, et al. Dynamic modeling and analysis of hose whipping phenomenon of aerial refueling hosedrogue assembly[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(9):31163127.
    王海涛，董新民，郭军，等. 空中加油软管锥套组合体甩鞭现象动力学建模与分析[J]. 航空学报, 2015, 09: 31163127.
    • 相关文章
    • 施引文献(11)

  • 期刊类型引用(7)

    1. 张瑜，张峰，郭芮，苏瑛，张云龙，许增奇，王阜超. 磁流变抛光二次非球面工件位置对刀校正. 应用光学. 2022(03): 518-523 . 本站查看
    2. 刘春阳，李洛克. 基于轮廓测量的集料表面粗糙度表征方法试验研究. 工业安全与环保. 2021(03): 15-19+25 . 百度学术
    3. 夏良静. 工艺参数对光学元件加工精度影响的数学模型研究. 激光杂志. 2020(08): 201-204 . 百度学术
    4. 张晋烨，张海云，赵玉刚，张军，王显达. 磨料振动对曲轴抛光的影响. 组合机床与自动化加工技术. 2019(01): 46-48 . 百度学术
    5. 高丰，李琦，向阳，宁旭. 高清折反式视频显微镜. 光学技术. 2019(02): 136-141 . 百度学术
    6. 刘红丽. 散粒磨料振动光饰技术专利分析. 科技风. 2019(14): 141 . 百度学术
    7. 马旭德，张东梅，尚春民. 固着磨料球面高速研磨加工技术研究. 新型工业化. 2018(04): 34-42 . 百度学术

    其他类型引用(4)

    • 资源附件(0)
计量
  • 文章访问数:  1130
  • HTML全文浏览量:  66
  • PDF下载量:  77
  • 被引次数: 11
出版历程
  • 收稿日期:  2015-11-04
  • 修回日期:  2016-01-06
  • 刊出日期:  2016-05-14

目录

摘要
HTML全文
    参考文献(1)
    相关文章
    施引文献
    资源附件(0)

    /

    返回文章
    返回

    相关数据库

    广告合作

    友情链接

    帮助中心

    扫描关注本刊微信平台

    您是第  2900215位访问者，欢迎！

    地址: 西安市电子三路西段9号 邮政编码: 710065 联系电话: 029-88288172

    版权所有 © 《应用光学》编辑部

    陕公网安备 61011302001501号       陕ICP备19002862号-1

    北京仁和汇智信息技术有限公司 开发  技术支持: info@rhhz.net   百度统计