由粗到细的颅骨点云模型配准方法
|
摘要
颅骨配准是颅面复原的一个重要步骤,其配准精度对复原结果有着重要的影响。为了提高颅骨配准的精度,并解决分辨率差异较大颅骨的配准问题,本文提出了一种由粗到细的三维颅骨点云模型配准方法。首先,采用基于神经网络(NN)的点云配准算法实现颅骨粗配准;然后,通过添加尺度因子和模拟退火系数以改进迭代最近点(ICP)算法并实现颅骨细配准,大大提高了颅骨细配准的精度和速度,从而实现颅骨的精确配准。将一个未知颅骨与颅骨库中的300个颅骨进行配准试验,结果表明,基于NN的点云配准算法可以实现颅骨的初始配准,并且改进ICP算法在细配准阶段的配准精度和速度,比ICP算法分别提高了约30%和50%。因此,提出的由粗到细的点云配准算法是一种有效的颅骨配准算法,可以实现三维颅骨点云模型的精确配准。
Skull registration is an important step of craniofacial restoration,the accuracy of which plays a key role to the recovered results.To improve the registration accuracy of skulls and solve the registration problem of different solutions,a 3 D skull point cloud registration method from coarse to fine is proposed in the paper.Firstly,coarse registration of skulls is completed using the point cloud registration method based on neural network(NN).Then the iterative closest point(ICP) is improved by integrating scale factor and simulated annealing coefficient into it and used to complete skull fine registration. The improved ICP algorithm could improve the accuracy and speed of fine registration and achieve the final registration of skulls with high accuracy. An unknown skull is registered with 300 skulls in database in the experiment,the results show that the NN-based point cloud registration method could align the skulls coarsely,and the registration accuracy and convergence rate of improved ICP algorithm increase by about 30% and 50% respectively compared with ICP algorithm.So the proposed skull registration method from coarse to fine is an effective skull registration method which could complete accurate registration of 3 D skull model.
Skull registration is an important step of craniofacial restoration,the accuracy of which plays a key role to the recovered results.To improve the registration accuracy of skulls and solve the registration problem of different solutions,a 3 D skull point cloud registration method from coarse to fine is proposed in the paper.Firstly,coarse registration of skulls is completed using the point cloud registration method based on neural network(NN).Then the iterative closest point(ICP) is improved by integrating scale factor and simulated annealing coefficient into it and used to complete skull fine registration. The improved ICP algorithm could improve the accuracy and speed of fine registration and achieve the final registration of skulls with high accuracy. An unknown skull is registered with 300 skulls in database in the experiment,the results show that the NN-based point cloud registration method could align the skulls coarsely,and the registration accuracy and convergence rate of improved ICP algorithm increase by about 30% and 50% respectively compared with ICP algorithm.So the proposed skull registration method from coarse to fine is an effective skull registration method which could complete accurate registration of 3 D skull model.
引文
[1] ZHOU C,ANSCHUETZ L,WESER S,et al. Surface Matching for High-accuracy Registration of the Lateral Skull Base[J]. International Journal of Computer Assisted Radiology and Surgery,2016,11(11):1-7.
[2] SONG Z,JIANG H,YANG Q,et al. A Registration Method Based on Contour Point Cloud for 3D Wholebody PET and CT Images[J]. Bio Med Research International,2017(2):1-11.
[3] GRODZICKI P,CAPUT M.Entropy-based Registration of Point Clouds Using Terrestrial Laser Scanning and Smartphone GPS[J].Sensors,2017,17(1):229-239.
[4] CUI T,JI S,SHAN J,et al.Line-based Registration of Panoramic Images and Li DAR Point Clouds for Mobile Mapping[J].Sensors,2017,17(1):70-89.
[5]郑敏辉,臧玉府,梁福逊,等.不同场景的地面激光点云配准方法研究[J].测绘通报,2015(8):30-34.
[6]盛庆红,陈姝文,柳建锋,等.基于Plücker直线Li DAR点云配准法[J].测绘学报,2016,45(1):58-64.
[7]冯筠,陈雨,仝鑫龙,等.三维颅骨特征点的自动标定[J].光学精密工程,2014,22(5):1388-1394.
[8] LINDEBERG T.Scale Selection Properties of Generalized Scale-space Interest Point Detectors[J]. Journal of Mathematical Imaging and Vision,2013,46(2):177-210.
[9] CAO Z C,MA F L,FU Y L,et al. A Scale Invariant Interest Point Detector in Gabor Based Energy Space[J].Acta Automatica Sinica,2014,40(10):2356-2363.
[10] IZUMIYA S,NABARRO A C,SACRAMENTO A D J.Pseudo-spherical Normal Darboux Images of Curves on a Timelike Surface in Three Dimensional Lorentz Minkowski Space[J].Journal of Geometry and Physics,2015,97:105-118.
[11] LIN C C,TAI Y C,LEE J J,et al.A Novel Point Cloud Registration Using 2D Image Features[J].Eurasip Journal on Advances in Signal Processing,2017(1):5-15.
[12] BESL P J,MCKAY N D.A Method for Registration of 3-D Shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,14(2):239-256.
[13] MARANI R,RENO V,NITTI M,et al. A Modified Iterative Closest Point Algorithm for 3D Point Cloud Registration[J].Computer-Aided Civil and Infrastructure Engineering,2016,31(7):515-534.
[14] WANG X,ZHAO Z L,CAPPS A G,et al. An Iterative Closest Point Approach for the Registration of Volumetric Human Retina Image Data Obtained by Optical Coherence Tomography[J]. Multimedia Tools and Applications,2017,76(5):6843-6857.
[15] DONG J,CAI Z,DU S.Improvement of Affine Iterative Closest Point Algorithm for Partial Registration[J]. IET Computer Vision,2017,11(2):135-144.
[16] EDLUND O. Robust Registration of Surfaces Using a Refined Iterative Closest Point Algorithm with a Trust Region Approach[J]. Numerical Algorithms,2016,74(3):1-25.
[17]李广云,李明磊,王力,等.地面激光扫描点云数据预处理综述[J].测绘通报,2015(11):1-3.
[18] LI W,SONG P. A Modified ICP Algorithm Based on Dynamic Adjustment Factor for Registration of Point Cloud and CAD Model[J]. Pattern Recognition Letters,2015,65(11):88-94.
[2] SONG Z,JIANG H,YANG Q,et al. A Registration Method Based on Contour Point Cloud for 3D Wholebody PET and CT Images[J]. Bio Med Research International,2017(2):1-11.
[3] GRODZICKI P,CAPUT M.Entropy-based Registration of Point Clouds Using Terrestrial Laser Scanning and Smartphone GPS[J].Sensors,2017,17(1):229-239.
[4] CUI T,JI S,SHAN J,et al.Line-based Registration of Panoramic Images and Li DAR Point Clouds for Mobile Mapping[J].Sensors,2017,17(1):70-89.
[5]郑敏辉,臧玉府,梁福逊,等.不同场景的地面激光点云配准方法研究[J].测绘通报,2015(8):30-34.
[6]盛庆红,陈姝文,柳建锋,等.基于Plücker直线Li DAR点云配准法[J].测绘学报,2016,45(1):58-64.
[7]冯筠,陈雨,仝鑫龙,等.三维颅骨特征点的自动标定[J].光学精密工程,2014,22(5):1388-1394.
[8] LINDEBERG T.Scale Selection Properties of Generalized Scale-space Interest Point Detectors[J]. Journal of Mathematical Imaging and Vision,2013,46(2):177-210.
[9] CAO Z C,MA F L,FU Y L,et al. A Scale Invariant Interest Point Detector in Gabor Based Energy Space[J].Acta Automatica Sinica,2014,40(10):2356-2363.
[10] IZUMIYA S,NABARRO A C,SACRAMENTO A D J.Pseudo-spherical Normal Darboux Images of Curves on a Timelike Surface in Three Dimensional Lorentz Minkowski Space[J].Journal of Geometry and Physics,2015,97:105-118.
[11] LIN C C,TAI Y C,LEE J J,et al.A Novel Point Cloud Registration Using 2D Image Features[J].Eurasip Journal on Advances in Signal Processing,2017(1):5-15.
[12] BESL P J,MCKAY N D.A Method for Registration of 3-D Shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,14(2):239-256.
[13] MARANI R,RENO V,NITTI M,et al. A Modified Iterative Closest Point Algorithm for 3D Point Cloud Registration[J].Computer-Aided Civil and Infrastructure Engineering,2016,31(7):515-534.
[14] WANG X,ZHAO Z L,CAPPS A G,et al. An Iterative Closest Point Approach for the Registration of Volumetric Human Retina Image Data Obtained by Optical Coherence Tomography[J]. Multimedia Tools and Applications,2017,76(5):6843-6857.
[15] DONG J,CAI Z,DU S.Improvement of Affine Iterative Closest Point Algorithm for Partial Registration[J]. IET Computer Vision,2017,11(2):135-144.
[16] EDLUND O. Robust Registration of Surfaces Using a Refined Iterative Closest Point Algorithm with a Trust Region Approach[J]. Numerical Algorithms,2016,74(3):1-25.
[17]李广云,李明磊,王力,等.地面激光扫描点云数据预处理综述[J].测绘通报,2015(11):1-3.
[18] LI W,SONG P. A Modified ICP Algorithm Based on Dynamic Adjustment Factor for Registration of Point Cloud and CAD Model[J]. Pattern Recognition Letters,2015,65(11):88-94.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |