一种新的点云拼接算法
|
摘要
迭代最近点(ICP)算法广泛运用于三维点云数据的多视拼接,其精度和迭代收敛性严重依赖于待拼接数据的初始拼接位置,这就决定ICP只能是一个性能优越的精确拼接算法。粗拼接算法旨在为ICP提供一个良好的初始拼接位置。基于信息论中熵的概念,分析了点云的空间分布规律与所处位置的关系,在此基础上提出了一种新的粗拼接算法—迭代最小空间分布熵法。实验表明,该算法有效可行,可以提供很好的初始拼接位置,在误差允许范围内,该算法可以直接实现点云拼接。
Iterative closest point(ICP) algorithm is widely used in multi-view fine registration of 3D point clouds,while its accuracy and convergence to global optimization depend on initial registration position.It fails when a great difference exists to initial position of the waited registered point clouds.Coarse registration aims to provide a good initial registration position for ICP.A new coarse registration algorithm—iterative least space distribution entropy is proposed based on the space distribution of point clouds,and the concept of entropy is used for describing this distribution law according to information theory.Experiments show that the proposed algorithm can offer a good initial registration position for ICP and it owns a high efficiency and can realize registration without using ICP under precision permission.
Iterative closest point(ICP) algorithm is widely used in multi-view fine registration of 3D point clouds,while its accuracy and convergence to global optimization depend on initial registration position.It fails when a great difference exists to initial position of the waited registered point clouds.Coarse registration aims to provide a good initial registration position for ICP.A new coarse registration algorithm—iterative least space distribution entropy is proposed based on the space distribution of point clouds,and the concept of entropy is used for describing this distribution law according to information theory.Experiments show that the proposed algorithm can offer a good initial registration position for ICP and it owns a high efficiency and can realize registration without using ICP under precision permission.
引文
1Chen Tian.Data processing methodology for laser measurementpoint cloud[J].Laser&Optoelectronics Progress,2011,48(9):091202陈田.激光测量点云的数据处理方法研究[J].激光与光电子学进展,2011,48(9):091202
2P.J.Bsel,N.D.Mckay.A method of registration of 3Dshapes[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1992,14(2):239～256
3S.Y.Park,M.Subbarao.An accurate and fast point to planeregistration technique[J].Pattern Recognition Letters,2003,24(16):2967～2976
4Wei Xin,J.X.Pu.An improved ICP algorithm for point cloudregistration[C].International conference on Computational andInformation Sciences,2010.565～568
5H.Fukai,G.Xu.Fast and robust registration of multiple 3Dpoint clouds[C].IEEE International Symposium on Robot andHuman Interactive Communication,2011.331～336
6J.N.Liu,Z.Y.Ren.The research and application of the multi-view registration[C].The 3rd International Congress on Imageand Signal Processing,2010.1258～1262
7L.Silva,O.R.P.Bellon,K.L.Boyer.Precision range imageregistration using a robust surface interpenetration measure andenhanced genetic algorithms[J].IEEE Trans.Pattern Analysisand Machine Intelligence,2005,27(5):762～776
8Wang Rui,Li Junshan,Liu Lingxia et al..Registration of pointclouds based on gemotric properties[J].J.East ChinaUniversity of Science and Technology(Natural ScienceEdition),2009,35(5):768～773王蕊,李俊山,刘玲霞等.基于几何特征的点云配准算法[J].华东理工大学学报(自然科学版),2009,35(5):768～773
9T.Takeguchi,S.Kaneko,T.Kondo et al..Robust objectrecognition based on depth aspect image matching[J].IEICETrans.Information and Systems,2001,J84-D-2(8):1710～1721
10Luo Xianbo,Zhong Yuexian,Li Renju.Data registration in 3Dscanning systems[J].J.Tsinghua University(Science andTechnology),2004,44(8):1104～1106罗先波,钟约先,李仁举.三维扫描系统中的数据配准技术[J].清华大学学报(自然科学版),2004,44(8):1104～1106
11Zhu Xuelong.Fundamentals of Applied Information Theory[M].Beijing:Tsinghua University Press,2000朱雪龙.应用信息论基础[M].北京:清华大学出版社,2000
12Guo Yulan,Lu Min,Tan Zhiguoet al..A novel method for ladartarget orientation estimation[J].Chinese J.Lasers,2011,38(4):0414002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):0414002
13Guo Yulan,Lu Min,Tan Zhiguo et al..Fast target recognitionin ladar using projection contour features[J].Chinese J.Lasers,2012,39(2):0209003郭裕兰,鲁敏,谭志国等.采用投影轮廓特征的激光雷达快速目标识别[J].中国激光,2012,39(2):0209003
2P.J.Bsel,N.D.Mckay.A method of registration of 3Dshapes[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1992,14(2):239～256
3S.Y.Park,M.Subbarao.An accurate and fast point to planeregistration technique[J].Pattern Recognition Letters,2003,24(16):2967～2976
4Wei Xin,J.X.Pu.An improved ICP algorithm for point cloudregistration[C].International conference on Computational andInformation Sciences,2010.565～568
5H.Fukai,G.Xu.Fast and robust registration of multiple 3Dpoint clouds[C].IEEE International Symposium on Robot andHuman Interactive Communication,2011.331～336
6J.N.Liu,Z.Y.Ren.The research and application of the multi-view registration[C].The 3rd International Congress on Imageand Signal Processing,2010.1258～1262
7L.Silva,O.R.P.Bellon,K.L.Boyer.Precision range imageregistration using a robust surface interpenetration measure andenhanced genetic algorithms[J].IEEE Trans.Pattern Analysisand Machine Intelligence,2005,27(5):762～776
8Wang Rui,Li Junshan,Liu Lingxia et al..Registration of pointclouds based on gemotric properties[J].J.East ChinaUniversity of Science and Technology(Natural ScienceEdition),2009,35(5):768～773王蕊,李俊山,刘玲霞等.基于几何特征的点云配准算法[J].华东理工大学学报(自然科学版),2009,35(5):768～773
9T.Takeguchi,S.Kaneko,T.Kondo et al..Robust objectrecognition based on depth aspect image matching[J].IEICETrans.Information and Systems,2001,J84-D-2(8):1710～1721
10Luo Xianbo,Zhong Yuexian,Li Renju.Data registration in 3Dscanning systems[J].J.Tsinghua University(Science andTechnology),2004,44(8):1104～1106罗先波,钟约先,李仁举.三维扫描系统中的数据配准技术[J].清华大学学报(自然科学版),2004,44(8):1104～1106
11Zhu Xuelong.Fundamentals of Applied Information Theory[M].Beijing:Tsinghua University Press,2000朱雪龙.应用信息论基础[M].北京:清华大学出版社,2000
12Guo Yulan,Lu Min,Tan Zhiguoet al..A novel method for ladartarget orientation estimation[J].Chinese J.Lasers,2011,38(4):0414002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):0414002
13Guo Yulan,Lu Min,Tan Zhiguo et al..Fast target recognitionin ladar using projection contour features[J].Chinese J.Lasers,2012,39(2):0209003郭裕兰,鲁敏,谭志国等.采用投影轮廓特征的激光雷达快速目标识别[J].中国激光,2012,39(2):0209003