Volume 32 Issue 10
Oct.  2006
Turn off MathJax
Article Contents
Sun Junhua, Zhang Guangjun, Wei Zhenzhonget al. Multi-view point clouds registration method based on planar target[J]. Journal of Beijing University of Aeronautics and Astronautics, 2006, 32(10): 1231-1234. (in Chinese)
Citation: Sun Junhua, Zhang Guangjun, Wei Zhenzhonget al. Multi-view point clouds registration method based on planar target[J]. Journal of Beijing University of Aeronautics and Astronautics, 2006, 32(10): 1231-1234. (in Chinese)

Multi-view point clouds registration method based on planar target

  • Received Date: 02 Dec 2005
  • Publish Date: 31 Oct 2006
  • Multi-view point clouds registration is one of the key techniques in 3D vision measurement for large object. A planar target with some corners as feature points was designed. The distances between those feature points were accurately known. The target was placed at the common region which was measured by a vision sensor at two different view-points, and the vision sensor measured the 3D coordinates of the feature points twice. By establishing unit orthogonal basis using 3 arbitrary non-colinear points on the target, the original coordinate frame transformation matrix for multi-view point clouds was found. An objective function for the sum of distances′ squares between the correspondent feature points was established after original registration, and the distances control was introduced to increase constraint. The optimal results were finally estimated by Levenberg-Marquardt optimization algorithm taking original coordinate frame transformation matrix as the initial value. A plaster model was measured by a binocular vision sensor at two positions. The experimental results show that the proposed registration method is simple and reliable, and the registration accuracy after optimizing is improved by about 31%.

     

  • loading
  • [1] 李鑫,张广军,魏振忠. 基于RBF神经网络的结构光三维视觉检测方法[J].北京航空航天大学学报,2002,28(3):265-268 Li Xin, Zhang Guangjun, Wei Zhenzhong. Method for structured light based 3D vision inspection based on RBF neural network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2002, 28(3):265-268(in Chinese) [2] 韩耘,马利,何世平,等.回转体形状检测的数据拼接法研究[J].中国科学技术大学学报,2003,33(6):282-286 Han Yun, Ma Li, He Shiping, et al. A study on data combination method in topography measurement of revolving objects[J]. Journal of University of Science and Technology of China, 2003, 33(6):282-286(in Chinese) [3] 龙玺,钟约先,李仁举,等.结构光三维扫描测量的三维拼接技术[J]. 清华大学学报, 2002, 42(4):477-480 Long Xi, Zhong Yuexian, Li Renju, et al. 3-D surface integration in structured light 3-D scanning[J]. Journal of Tsinghua University, 2002,42(4):477-480(in Chinese) [4] 张顺德,卢秉恒,丁玉成.光学三维型面分区域测量数据的拼接研究[J].中国激光, 2001, 28(6):533-536 Zhang Shunde, Lu Bingheng, Ding Yucheng. Study on data registration of subdivided shapes in optical 3-D profilometry [J]. Chinese Journal of Lasers, 2001, 28(6):533-536(in Chinese) [5] 李晓星,康绍峥,周贤宾.立体视觉与空间编码技术相结合的非接触三维曲面测量系统[J].中国机械工程, 2004,15(9):806-809 Li Xiaoxing, Kang Shaozheng, Zhou Xianbin. Non-contact 3D surface measurement system based on binocular vision and spatial code[J]. China Mechanical Engineering, 2004, 15(9):806-809(in Chinese) [6] Besl P J, McKay N D. A method for registration of 3-D shapes . IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2):239-256 [7] Bergevin R, Soucy M, Gagnon H, et al. Towards a general multi-view registration technique[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(5):540-547 [8] Fan K C, Tsai T H. Optimal shape error analysis of the matching image for a free-form surface[J]. Robotics and Computer Integrated Manufacturing, 2001,17:215-222 [9] 席少霖.非线性最优化方法[M].北京:高等教育出版社,1992 Xi Shaolin. Non-linear optimization method[M]. Beijing:Higher Education Press, 1992(in Chinese)
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views(2950) PDF downloads(985) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return