搜索

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

引用本文:
Citation:

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

Calibration of D-RGB camera networks by skeleton-based viewpoint invariance transformation

Han Yun, Chung Sheng-Luen, Yeh Jeng-Sheng, Chen Qi-Jun
PDF
导出引用
  • 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.
    Combining depth information and color image, D-RGB cameras provide a ready detection of human and associated 3D skeleton joints data, facilitating, if not revolutionizing, conventional image centric researches in, among others, computer vision, surveillance, and human activity analysis. Applicability of a D-RBG camera, however, is restricted by its limited range of frustum of depth in the range of 0.8 to 4 meters. Although a D-RGB camera network, constructed by deployment of several D-RGB cameras at various locations, could extend the range of coverage, it requires precise localization of the camera network: relative location and orientation of neighboring cameras. By introducing a skeleton-based viewpoint invariant transformation (SVIT), which derives the relative location and orientation of a detected humans upper torso to a D-RGB camera, this paper presents a reliable automatic localization technique without the need for additional instrument or human intervention. By respectively applying SVIT to two neighboring D-RGB cameras on a commonly observed skeleton, the respective relative position and orientation of the detected humans skeleton for these two cameras can be obtained before being combined to yield the relative position and orientation of these two cameras, thus solving the localization problem. Experiments have been conducted in which two Kinects are situated with bearing differences of about 45 degrees and 90 degrees; the coverage can be extended by up to 70% with the installment of an additional Kinect. The same localization technique can be applied repeatedly to a larger number of D-RGB cameras, thus extending the applicability of D-RGB cameras to camera networks in making human behavior analysis and context-aware service in a larger surveillance area.
    • 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.
    • Funds: Project supported by the International ST Cooperation Projects of China (Grant No. 2010DFA12210), the Shanghai Science and Technology Talent Project, China (Grant No. 11XD1404800), and the Key Program for Basic Research of Science and Technology Commission Foundation of Shanghai, China (Grant No. 12JC1408800).
    [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] 周江平, 周媛媛, 周学军. 改进的测量设备无关协议参数优化方法. 物理学报, 2023, 72(12): 120303. doi: 10.7498/aps.72.20230179
    [2] 武文斌, 彭士香, 张艾霖, 周海京, 马腾昊, 蒋耀湘, 李凯, 崔步坚, 郭之虞, 陈佳洱. 微型电子回旋共振离子源的全局模型. 物理学报, 2022, 71(14): 145204. doi: 10.7498/aps.71.20212250
    [3] 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. 物理学报, 2020, 69(9): 090701. doi: 10.7498/aps.69.20200153
    [4] 谭索怡, 祁明泽, 吴俊, 吕欣. 复杂网络链路可预测性: 基于特征谱视角. 物理学报, 2020, 69(8): 088901. doi: 10.7498/aps.69.20191817
    [5] 岳晓乐, 向以琳, 张莹. 形状记忆合金薄板系统全局激变现象分析. 物理学报, 2019, 68(18): 180501. doi: 10.7498/aps.68.20190155
    [6] 谷文苑, 赵尚弘, 东晨, 王星宇, 杨鼎. 参考系波动下的参考系无关测量设备无关量子密钥分发协议. 物理学报, 2019, 68(24): 240301. doi: 10.7498/aps.68.20191364
    [7] 高彦丽, 陈世明. 一种全局同质化相依网络耦合模式. 物理学报, 2016, 65(14): 148901. doi: 10.7498/aps.65.148901
    [8] 上官丹骅, 邓力, 李刚, 张宝印, 马彦, 付元光, 李瑞, 胡小利. 蒙特卡罗临界计算全局计数效率新算法研究. 物理学报, 2016, 65(6): 062801. doi: 10.7498/aps.65.062801
    [9] 鲁磊, 屈绍波, 施宏宇, 张安学, 夏颂, 徐卓, 张介秋. 宽带透射吸收极化无关超材料吸波体. 物理学报, 2014, 63(2): 028103. doi: 10.7498/aps.63.028103
    [10] 赵顾颢, 赵尚弘, 幺周石, 郝晨露, 蒙文, 王翔, 朱子行, 刘丰. 偏振无关的旋光双反射结构的实验研究. 物理学报, 2013, 62(13): 134201. doi: 10.7498/aps.62.134201
    [11] 孟春宁, 白晋军, 张太宁, 刘润蓓, 常胜江. 单摄像机下基于眼动分析的行为识别. 物理学报, 2013, 62(17): 174203. doi: 10.7498/aps.62.174203
    [12] 吕翎, 李钢, 张檬, 李雨珊, 韦琳玲, 于淼. 全局耦合网络的参量辨识与时空混沌同步. 物理学报, 2011, 60(9): 090505. doi: 10.7498/aps.60.090505
    [13] 孙常春, 方勃, 黄文虎. 基于线性状态反馈的混沌系统全局控制. 物理学报, 2011, 60(11): 110503. doi: 10.7498/aps.60.110503
    [14] 罗诗裕, 邵明珠, 罗晓华. 晶体摆动场辐射系统的全局分叉与混沌行为. 物理学报, 2010, 59(4): 2685-2690. doi: 10.7498/aps.59.2685
    [15] 钟文镇, 何克晶, 周照耀, 夏伟, 李元元. 颗粒离散元模拟中的阻尼系数标定. 物理学报, 2009, 58(8): 5155-5161. doi: 10.7498/aps.58.5155
    [16] 王占山, 张化光, 王智良. 一类混沌神经网络的全局同步. 物理学报, 2006, 55(6): 2687-2693. doi: 10.7498/aps.55.2687
    [17] 罗诗裕, 邵明珠, 韦洛霞, 刘曾荣. 位错动力学与系统的全局分叉. 物理学报, 2004, 53(6): 1940-1945. doi: 10.7498/aps.53.1940
    [18] 郭可信, 刘平. 电子衍射图自动标定中初基解的判据. 物理学报, 1980, 29(8): 1080-1083. doi: 10.7498/aps.29.1080
    [19] 郭可信. 电子衍射谱自动标定中的消光处理. 物理学报, 1978, 27(4): 473-475. doi: 10.7498/aps.27.473
    [20] 郭可信. 约化胞与电子衍射谱的标定. 物理学报, 1978, 27(2): 160-168. doi: 10.7498/aps.27.160
计量
  • 文章访问数:  5083
  • PDF下载量:  1401
  • 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

/

返回文章
返回