一种新的激光成像数据多视粗拼接算法
|
摘要
针对激光成像数据的多视拼接问题,采用先粗后细的拼接策略,提出了一种新的粗拼接算法。该算法首先估计出待拼接点云数据存在的旋转偏移角,再通过相应的旋转来消除这种偏移,从而实现粗拼接。在此基础上,采用精确拼接ICP算法作最终拼接。实验表明,本文提出的粗拼接算法能够有效地实现不同视点下激光成像数据的粗拼接,该方法简单、高效,且适用于不同分辨率的数据拼接。
For the problem of the multi-view registration of laser imaging data,the coarse-to-fine strategy is adopted so that a novel coarse registration method is proposed.The proposed method first estimates the rotation excursion angles of various-view point clouds,and then eliminates the existed excursion by corresponding rotation,thus realizing the coarse registration.Finally,ICP(Iterative Closest Point)is employed for fine registration.Experimental results show that the proposed method can realize coarse registration of various-view laser imaging data effectively and demonstrate that the method is simple and high-efficient so as to be suitable to different-resolution data.
For the problem of the multi-view registration of laser imaging data,the coarse-to-fine strategy is adopted so that a novel coarse registration method is proposed.The proposed method first estimates the rotation excursion angles of various-view point clouds,and then eliminates the existed excursion by corresponding rotation,thus realizing the coarse registration.Finally,ICP(Iterative Closest Point)is employed for fine registration.Experimental results show that the proposed method can realize coarse registration of various-view laser imaging data effectively and demonstrate that the method is simple and high-efficient so as to be suitable to different-resolution data.
引文
[1]Bsel P J,Mckay N D.A method of registration of 3Dshapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[2]Chen Y,Medioni G.Object modeling by registration of multiple range images[J].Image and Vision Computing,1992,10(3):145-155.
[3]Blais G,Levine M.Registering multiview range data to create 3Dcomputer object[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):820-824.
[4]Park S Y,Subbarao M.An accurate and fast point to plane registration technique[J].Pattern Recognition Letters,2003,24(16):2967-2976.
[5]Xin Wei,Pu Jie-xin.An improved ICP algorithm for point cloud registration[C]∥Proc of International Conference on Computational and Information Sciences,2010:565-568.
[6]Fukai H,Xu Gang.Fast and robust registration of multiple3Dpoint clouds[C]∥Proc of IEEE International Symposium on Robot and Human Interactive Communication,2011:331-336.
[7]Liu Jing-na,Ren Zheng-yi.The research and application of the multi-view registration[C]∥Proc of the 3rd International Congress on Image and Signal Processing,2010:1258-1262.
[8]Zhou Chun-yan,Li Yong,Zou Zheng-rong.Three-dimensinal cloud ICP algorithm improvement[J].Computer Technology and Development,2011,21(8):75-81.(in Chinese)
[9]Pulli K.Multiview registration for large data sets[C]∥Proc of the 2nd International Conference on 3D Digital Imaging and Modeling,1999:160-168.
[10]Takeguchi T,Kaneko S,Kondo T,et al.Robust object recognition based on depth aspect image matching[J].IEICE,2001,J84-D-II(8):1710-1721.
[11]Tangelder J W H,Veltkamp R C.A survey of content based3Dshape retrieval methods[C]∥Proc of Shape Modeling Application,2004:145-456.
[12]Yang Y,Lin H,Zhang Y.Content-based 3-D model retrieval:A survey[J].IEEE Transactions on Systems,Man and Cybernetics-Part C:Applications and Reviews,2007,37(6):1081-1099.
[13]Zhu D Q,Chu C C.Characterization of irregularly shaped bodies[C]∥Proc of SPIE’95,1995:17-22.
[14]Gronwall C,Chevalier T,Persson A.Methods for recognition of natural and man-made objects using laser radar data[C]∥Proc of SPIE on Laser Radar Technology and Applications IX,2004:310-320.
[15]Gronwall C,Andersson P,Gustafsson F.Least squares fitting of articulated objects[C]∥Proc of the 2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:5-9.
[16]Gronwall C,Gustafsson F,Millnert M,et al.Ground target recognition using rectangle estimation[J].IEEE Transactions on Image Processing,2006,15(11):3401-3409.
[17]Guo Yu-lan,Lu Min,Tan Zhi-guo,et al.A novel method for lader target orientation estimation[J].Chinese Journal of Lasers,2011,38(4):242-248.(in Chinese)
[8]周春艳,李勇,邹峥嵘.三维点云ICP算法改进研究[J].计算机技术与发展,2011,21(8):75-81.
[17]郭裕兰,鲁敏,谭志国,等.一种新的激光雷达目标姿态估计算法[J].中国激光,2011,38(4):242-248.
[2]Chen Y,Medioni G.Object modeling by registration of multiple range images[J].Image and Vision Computing,1992,10(3):145-155.
[3]Blais G,Levine M.Registering multiview range data to create 3Dcomputer object[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):820-824.
[4]Park S Y,Subbarao M.An accurate and fast point to plane registration technique[J].Pattern Recognition Letters,2003,24(16):2967-2976.
[5]Xin Wei,Pu Jie-xin.An improved ICP algorithm for point cloud registration[C]∥Proc of International Conference on Computational and Information Sciences,2010:565-568.
[6]Fukai H,Xu Gang.Fast and robust registration of multiple3Dpoint clouds[C]∥Proc of IEEE International Symposium on Robot and Human Interactive Communication,2011:331-336.
[7]Liu Jing-na,Ren Zheng-yi.The research and application of the multi-view registration[C]∥Proc of the 3rd International Congress on Image and Signal Processing,2010:1258-1262.
[8]Zhou Chun-yan,Li Yong,Zou Zheng-rong.Three-dimensinal cloud ICP algorithm improvement[J].Computer Technology and Development,2011,21(8):75-81.(in Chinese)
[9]Pulli K.Multiview registration for large data sets[C]∥Proc of the 2nd International Conference on 3D Digital Imaging and Modeling,1999:160-168.
[10]Takeguchi T,Kaneko S,Kondo T,et al.Robust object recognition based on depth aspect image matching[J].IEICE,2001,J84-D-II(8):1710-1721.
[11]Tangelder J W H,Veltkamp R C.A survey of content based3Dshape retrieval methods[C]∥Proc of Shape Modeling Application,2004:145-456.
[12]Yang Y,Lin H,Zhang Y.Content-based 3-D model retrieval:A survey[J].IEEE Transactions on Systems,Man and Cybernetics-Part C:Applications and Reviews,2007,37(6):1081-1099.
[13]Zhu D Q,Chu C C.Characterization of irregularly shaped bodies[C]∥Proc of SPIE’95,1995:17-22.
[14]Gronwall C,Chevalier T,Persson A.Methods for recognition of natural and man-made objects using laser radar data[C]∥Proc of SPIE on Laser Radar Technology and Applications IX,2004:310-320.
[15]Gronwall C,Andersson P,Gustafsson F.Least squares fitting of articulated objects[C]∥Proc of the 2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:5-9.
[16]Gronwall C,Gustafsson F,Millnert M,et al.Ground target recognition using rectangle estimation[J].IEEE Transactions on Image Processing,2006,15(11):3401-3409.
[17]Guo Yu-lan,Lu Min,Tan Zhi-guo,et al.A novel method for lader target orientation estimation[J].Chinese Journal of Lasers,2011,38(4):242-248.(in Chinese)
[8]周春艳,李勇,邹峥嵘.三维点云ICP算法改进研究[J].计算机技术与发展,2011,21(8):75-81.
[17]郭裕兰,鲁敏,谭志国,等.一种新的激光雷达目标姿态估计算法[J].中国激光,2011,38(4):242-248.