搜索

文章查询

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于视角无关转换的深度摄像机定位技术

韩云 钟圣伦 叶正圣 陈启军

基于视角无关转换的深度摄像机定位技术

韩云, 钟圣伦, 叶正圣, 陈启军
PDF
导出引用
导出核心图
  • 通过整合深度和颜色信息,深度摄像机Kinect能够稳健的侦测出人体及人体骨架关节点,为计算机视觉、人体行为识别、机器人学的发展带来了革命性的进步. 然而单台深度摄像机的侦测范围有限. 虽然采用多台深度摄像机所构建的摄像机网可有效的扩大侦测范围,但是必须依赖深度摄影机之间的相对位置与朝向的精确标定. 论文采用作者之前提出的以人体骨架为基础的视角无关转换技术,能快速稳健的标定出深度摄像机之间的位置关系. 通过利用相邻两台深度摄影机同时侦测到的人体骨架,论文能直接利用深度摄影机所量测的人体上半身中稳定的关节点为新坐标系的参考点,实时的计算出两摄影机之间的平移向量和旋转矩阵,而不依赖其他额外的校正设备或人为介入处理. 通过在室内环境中安装两台摆放于不同位置与朝向的深度摄影机,从而,验证了该方法的实时性与易用性. 该实时标定方法解决了深度摄影机侦测范围有限的限制,同时,可由两两相邻的标定扩展到多台深度相机的全局标定,从而,可以被广泛的应用于人体行为识别、情境感知服务等领域.
    • 基金项目: 科技部国际合作项目(批准号:2010DFA12210)、上海科技人才项目(批准号:11XD1404800)和上海科委科学基础研究重点项目(批准号:12JC1408800)资助的课题.
    [1]

    Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬2010 物理学报59 980]

    [2]

    Zhang W, Cheng B, Zhang B 2012 Acta Phys. Sin. 61 060701 (in Chinese)[张伟, 成波, 张波2012 物理学报61 060701]

    [3]
    [4]

    Sung J, Ponce C, Selman B, Saxena A 2012 IEEE International Conference on Robotics and Automation Saint Paul, USA, May 14-18 2012 p842

    [5]
    [6]
    [7]

    Xia L, Chen C C, Aggarwal J K 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops Providence, United states, June 16-21, 2012 p8

    [8]

    Yun K, Honorio J, Chattopadhyay D, Berg T L, Samaras D 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops Providence, United states, June 16-21, 2012 p28

    [9]
    [10]

    Zhang Z Y 1999 Proceedings of the IEEE International Conference on Computer Vision Kerkyra, Greece, September 20-27, 1999 p666

    [11]
    [12]

    Tsai R Y 1986 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Miami Beach, United states, June 22-26, 1986 p364

    [13]
    [14]
    [15]

    Jia Q Q, Wang B X, Shi H, Luo X Z 2009 Journal of Tsinghua University 49 676 (in Chinese) [贾倩倩, 王伯雄, 史辉, 罗秀芝2009 清华大学学报49 676]

    [16]
    [17]

    Zhang Z Y 2004 IEEE Transactions on Pattern Analysis and Machine Intelligence 26 892

    [18]

    Thomas E, Andreas S 2012 7th German Conference on RoboticsMunich, Germany, May 21-22 2012 p1

    [19]
    [20]
    [21]

    Han Y, Chung S L, Yeh J S, Chen Q J 2013 IEEE International Conference on Systems, Man, and Cybernetics Manchester, UK, October 13-16, 2013 p1525

    [22]

    Mi T, An P, Liu S X, Zhang Z Y 2008 Journal of Image and Graphics 13 1921

    [23]
    [24]

    Zhang T N, Meng C N, Liu R B, Chang S J 2013 Acta Phys. Sin. 62 134204 (in Chinese)[张太宁, 孟春宁, 刘润蓓, 常胜2013 物理学报62 134204]

    [25]
    [26]
    [27]

    Grimson W E L 1985 IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-7 17

    [28]

    Wang F, Zhao X, Yang Y, Fang Z L, Yuan X C 2012 Acta Phys. Sin. 61 084212 (in Chinese)[王芳, 赵星, 杨勇, 方志良, 袁小聪2012 物理学报61 084212]

    [29]
    [30]
    [31]

    Atiya S, Hager G D 1993 IEEE Transactions on Robotics and Automation 9 785[17] Hoppen P, Knieriemen T, von Puttkamer E 1990 IEEE International Conference on Robotics and Automation Cincinnati, USA, May 13-18 1990 p948

    [32]
    [33]

    Hoppen P, Knieriemen T, von Puttkamer E 1990 IEEE International Conference on Robotics and Automation Cincinnati, USA, May 1318 1990 p948

    [34]

    Weiss A, Hirshberg D, Black M J 2011 IEEE International Conference on Computer Vision Barcelona, Spain, November 6-13, 2011 p1951

    [35]
    [36]

    Moeslund T B, Hilton A, Krger V 2006 Computer Vision and Image Understanding 104 90

    [37]
    [38]

    Poppe R 2007 Computer Vision and Image Understanding 108 4

    [39]
    [40]

    Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A 2011 IEEE Conference on Computer Vision and Pattern Recognition Colorado Springs, United states, June 20-25, 2011 p1297

    [41]
    [42]
    [43]

    PrimeSense www. primesense. com [June 5, 2013]

    [44]
    [45]

    Han J G, Shao L, Xu D, Shotton J 2013 IEEE Transactions on Cybernetics 43 1318

  • [1]

    Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬2010 物理学报59 980]

    [2]

    Zhang W, Cheng B, Zhang B 2012 Acta Phys. Sin. 61 060701 (in Chinese)[张伟, 成波, 张波2012 物理学报61 060701]

    [3]
    [4]

    Sung J, Ponce C, Selman B, Saxena A 2012 IEEE International Conference on Robotics and Automation Saint Paul, USA, May 14-18 2012 p842

    [5]
    [6]
    [7]

    Xia L, Chen C C, Aggarwal J K 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops Providence, United states, June 16-21, 2012 p8

    [8]

    Yun K, Honorio J, Chattopadhyay D, Berg T L, Samaras D 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops Providence, United states, June 16-21, 2012 p28

    [9]
    [10]

    Zhang Z Y 1999 Proceedings of the IEEE International Conference on Computer Vision Kerkyra, Greece, September 20-27, 1999 p666

    [11]
    [12]

    Tsai R Y 1986 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Miami Beach, United states, June 22-26, 1986 p364

    [13]
    [14]
    [15]

    Jia Q Q, Wang B X, Shi H, Luo X Z 2009 Journal of Tsinghua University 49 676 (in Chinese) [贾倩倩, 王伯雄, 史辉, 罗秀芝2009 清华大学学报49 676]

    [16]
    [17]

    Zhang Z Y 2004 IEEE Transactions on Pattern Analysis and Machine Intelligence 26 892

    [18]

    Thomas E, Andreas S 2012 7th German Conference on RoboticsMunich, Germany, May 21-22 2012 p1

    [19]
    [20]
    [21]

    Han Y, Chung S L, Yeh J S, Chen Q J 2013 IEEE International Conference on Systems, Man, and Cybernetics Manchester, UK, October 13-16, 2013 p1525

    [22]

    Mi T, An P, Liu S X, Zhang Z Y 2008 Journal of Image and Graphics 13 1921

    [23]
    [24]

    Zhang T N, Meng C N, Liu R B, Chang S J 2013 Acta Phys. Sin. 62 134204 (in Chinese)[张太宁, 孟春宁, 刘润蓓, 常胜2013 物理学报62 134204]

    [25]
    [26]
    [27]

    Grimson W E L 1985 IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-7 17

    [28]

    Wang F, Zhao X, Yang Y, Fang Z L, Yuan X C 2012 Acta Phys. Sin. 61 084212 (in Chinese)[王芳, 赵星, 杨勇, 方志良, 袁小聪2012 物理学报61 084212]

    [29]
    [30]
    [31]

    Atiya S, Hager G D 1993 IEEE Transactions on Robotics and Automation 9 785[17] Hoppen P, Knieriemen T, von Puttkamer E 1990 IEEE International Conference on Robotics and Automation Cincinnati, USA, May 13-18 1990 p948

    [32]
    [33]

    Hoppen P, Knieriemen T, von Puttkamer E 1990 IEEE International Conference on Robotics and Automation Cincinnati, USA, May 1318 1990 p948

    [34]

    Weiss A, Hirshberg D, Black M J 2011 IEEE International Conference on Computer Vision Barcelona, Spain, November 6-13, 2011 p1951

    [35]
    [36]

    Moeslund T B, Hilton A, Krger V 2006 Computer Vision and Image Understanding 104 90

    [37]
    [38]

    Poppe R 2007 Computer Vision and Image Understanding 108 4

    [39]
    [40]

    Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A 2011 IEEE Conference on Computer Vision and Pattern Recognition Colorado Springs, United states, June 20-25, 2011 p1297

    [41]
    [42]
    [43]

    PrimeSense www. primesense. com [June 5, 2013]

    [44]
    [45]

    Han J G, Shao L, Xu D, Shotton J 2013 IEEE Transactions on Cybernetics 43 1318

  • [1] 王凤阳, 胡仁志, 谢品华, 王怡慧, 陈浩, 张国贤, 刘文清. 基于同步光解的OH自由基标定方法研究. 物理学报, 2020, (): . doi: 10.7498/aps.69.20200153
    [2] 汪静丽, 陈子玉, 陈鹤鸣. 基于Si3N4/SiNx/Si3N4三明治结构的偏振无关1 × 2多模干涉型解复用器的设计. 物理学报, 2020, 69(5): 054206. doi: 10.7498/aps.69.20191449
    [3] 徐贤达, 赵磊, 孙伟峰. 石墨烯纳米网电导特性的能带机理第一原理. 物理学报, 2020, 69(4): 047101. doi: 10.7498/aps.69.20190657
    [4] 张雅男, 詹楠, 邓玲玲, 陈淑芬. 利用银纳米立方增强效率的多层溶液加工白光有机发光二极管. 物理学报, 2020, 69(4): 047801. doi: 10.7498/aps.69.20191526
  • 引用本文:
    Citation:
计量
  • 文章访问数:  563
  • PDF下载量:  1378
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-10-23
  • 修回日期:  2013-11-27
  • 刊出日期:  2014-04-05

基于视角无关转换的深度摄像机定位技术

  • 1. 同济大学电子与信息工程学院, 上海 201804;
  • 2. 台湾科技大学电机工程系, 台北 10607;
  • 3. 铭传大学计算机与通信工程学院, 台北 150001
    基金项目: 

    科技部国际合作项目(批准号:2010DFA12210)、上海科技人才项目(批准号:11XD1404800)和上海科委科学基础研究重点项目(批准号:12JC1408800)资助的课题.

摘要: 通过整合深度和颜色信息,深度摄像机Kinect能够稳健的侦测出人体及人体骨架关节点,为计算机视觉、人体行为识别、机器人学的发展带来了革命性的进步. 然而单台深度摄像机的侦测范围有限. 虽然采用多台深度摄像机所构建的摄像机网可有效的扩大侦测范围,但是必须依赖深度摄影机之间的相对位置与朝向的精确标定. 论文采用作者之前提出的以人体骨架为基础的视角无关转换技术,能快速稳健的标定出深度摄像机之间的位置关系. 通过利用相邻两台深度摄影机同时侦测到的人体骨架,论文能直接利用深度摄影机所量测的人体上半身中稳定的关节点为新坐标系的参考点,实时的计算出两摄影机之间的平移向量和旋转矩阵,而不依赖其他额外的校正设备或人为介入处理. 通过在室内环境中安装两台摆放于不同位置与朝向的深度摄影机,从而,验证了该方法的实时性与易用性. 该实时标定方法解决了深度摄影机侦测范围有限的限制,同时,可由两两相邻的标定扩展到多台深度相机的全局标定,从而,可以被广泛的应用于人体行为识别、情境感知服务等领域.

English Abstract

参考文献 (45)

目录

    /

    返回文章
    返回