基于混合算法的点云配准方法研究
|
摘要
为解决ICP(Iterative Closest Point)算法对初始点云位置要求高且易陷入局部最优的问题,提出一种新的配准方法。首先遵从优势互补基本思想,结合将人工萤火虫算法和粒子群算法生成自适应人工萤火虫-粒子群算法(AAGPSO:Adaptive Artificial Glowworm-Particle Swarm Optimization),以使算法的收敛速度变快,解的精度得到提高;其次优化迭代最近点算法(ICP),将已改进的AAGPSO算法引入ICP配准算法中进行点云配准,解决ICP算法因点云的初始位置相差较大而陷入局部最优问题,加快整体的配准效率。通过实验对比原始ICP配准方法和改进的配准方法并对其进行误差分析,结果验证了AAGPSO算法在传统ICP算法的基础上提高了配准精度,并且加快了算法收敛速度,改进的配准方法具有明显优越性。
In order to solve the problem that the ICP(Iterative Closest Point) algorithm has strict requirements on the initial point cloud position and is easy to be trapped in local optimum,a new registration method is proposed. Firstly,based on the idea of complementary advantages,the artificial glowworm algorithm and particle swarm algorithm are combined to propose an AAGPSO(Adaptive Artificial Glowworm-Particle Swarm Optimization),accelerating the convergence speed of the algorithm and improving the accuracy of the solution.Secondly,for a different initial location of the point cloud,the improved AAGPSO algorithm is introduced into the ICP registration algorithm making ICP algorithm optimized,and solving the local optimum problem of the ICP algorithm. The improved algorithm accelerates the overall registration efficiency. Finally,experimental data are used to compare the original ICP registration method with the improved registration method,and the error analysis is carried out. The AAGPSO algorithm improves the registration accuracy,accelerates the algorithm convergence speed.
In order to solve the problem that the ICP(Iterative Closest Point) algorithm has strict requirements on the initial point cloud position and is easy to be trapped in local optimum,a new registration method is proposed. Firstly,based on the idea of complementary advantages,the artificial glowworm algorithm and particle swarm algorithm are combined to propose an AAGPSO(Adaptive Artificial Glowworm-Particle Swarm Optimization),accelerating the convergence speed of the algorithm and improving the accuracy of the solution.Secondly,for a different initial location of the point cloud,the improved AAGPSO algorithm is introduced into the ICP registration algorithm making ICP algorithm optimized,and solving the local optimum problem of the ICP algorithm. The improved algorithm accelerates the overall registration efficiency. Finally,experimental data are used to compare the original ICP registration method with the improved registration method,and the error analysis is carried out. The AAGPSO algorithm improves the registration accuracy,accelerates the algorithm convergence speed.
引文
[1]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):75-77.ZHOU Chunyan,LI Yong,ZOU Zhengrong. Improvement of 3D Point Cloud ICP Algorithm[J]. Computer Technology and Development,2011,21(8):75-77.
[2]夏文玲,顾照鹏,杨唐胜.实时三维重建算法的实现———基于Kinect与单目视觉SLAM的三维重建[J].计算机工程与应用,2014,50(24):199-203.XIA Wenling,GU Zhaopeng,YANG Tangsheng. Realization of Real-Time 3D Reconstruction Algorithm-3D Reconstruction Based on Kinect and Monocular Vision SLAM[J]. Computer Engineering and Applications,2014,50(24):199-203.
[3]BESL P J,MCKAY N D. A Method for Registration of 3-D Shapes[M]. Piscataway,NJ,USA:IEEE Computer Society,1992.
[4]GREENSPAN M,GODIN G. A Nearest Neighbor Method for Efficient ICP[C]∥International Conference on 3-D Digital Imaging and Modeling. Piscataway,NJ,USA:IEEE,2001:161-168.
[5]BATLLE E,MATABOSCH C,SALVI J. Summarizing Image/Surface Registration for 6DOF Robot/Camera Pose Estimation[C]∥Iberian Conference on Pattern Recognition and Image Analysis. Berlin,German:Springer-Verlag,2007:105-112.
[6]DU S,ZHENG N,YING S,et al. Affine Iterative Closest Point Algorithm for Point Set Registration[J]. Pattern Recognition Letters,2010,31(9):791-799.
[7]KENNEDY J,EBERHART R C. Particle Swarm Optimization[C]∥Proc IEEE Int'l Conf on Neural Networks. Piscataway,NJ:IEEE,1995:1945-1950.
[8]HAN Jianghong,LI Zhengrong,WEI Zhenchun. An Adaptive Particle Swarm Optimization Algorithm and Its Simulation Research[J]. Journal of System Simulation,2006,18(10):2969-2971.
[9]KRISHNANAND K N,GHOSE D. Detection of Multiple Source Locations Using a Glowworm Metaphor with Applications to Collective Robotics[C]∥Swarm Intelligence Symposium. Piscataway,NJ,USA:IEEE,2005:84-91.
[10]刘洪霞,周永权.一种基于模式搜索算子的人工萤火虫优化算法[J].小型微型计算机系统,2011,32(10):2130-2133.LIU Hongxia,ZHOU Yongquan. An Artificial Firefly Optimization Algorithm Based on Pattern Search Operator[J]. Small Computer Systems,2011,32(10):2130-2133.
[11]刘军梅.新型混沌粒子群混合优化算法[J].软件导刊,2017,16(2):59-62.LIU Junmei. A New Hybrid Particle Swarm Optimization Algorithm[J]. Software Guide,2017,16(2):59-62.
[12]郗君甫.基于动态自适应萤火虫优化算法[J].邢台职业技术学院学报,2017(5):78-82.XI Junfu. Dynamic Adaptive Firefly Optimization Algorithm[J]. Journal of Xingtai Polytechnic,2017(5):78-82.
[13]曾艳阳,冯云霞,赵文涛.基于Logistic映射的自适应变尺度混沌粒子群算法[J].系统仿真学报,2017,29(10):2241-2246.ZENG Yanyang,FENG Yunxia,ZHAO Wentao. Adaptive Variable Scale Chaotic Particle Swarm Optimization Algorithm Based on Logistic Mapping[J]. Journal of System Simulation,2017,29(10):2241-2246.
[14]林诗洁,董晨,陈明志,等.新型群智能优化算法综述[J].计算机工程与应用,2018,54(12):6-14.LIN Shijie,DONG Chen,CHEN Mingzhi,et al. Overview of New Group Intelligent Optimization Algorithms[J]. Computer Engineering and Applications,2018,54(12):6-14.
[15]周丽娟,于雪晶,魏卓.基于萤火虫群算法的网络入侵优化检测算法[J].吉林大学学报:信息科学版,2015,33(3):338-343.ZHOU Lijuan,YU Xuejing,WEI Zhuo. Network Intrusion Optimization Detection Algorithm Based on Firefly Swarm Algorithm[J]. Journal of Jilin University:Information Science Edition,2015,33(3):338-343.
[16]LIU B,WANG L,JIN Y H,et al. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos Solitons&Fractals,2005,25(5):1261-1271.
[17]吴旺生.基于萤火虫LQG控制算法的半主动悬架研究[D].马鞍山:安徽工程大学机械工程学院,2017.WU Wangsheng. Research on Semi-Active Suspension Based on Firefly LQG Control Algorithm[D]. Maanshan:School of Mechanical Engineering,Anhui University of Engineering,2017.
[18]LIAO W H,KAO Y,LI Y S. A Sensor Deployment Approach Using Glowworm Swarm Optimization Algorithm in Wireless Sensor Networks[J]. Expert Systems with Applications,2011,38(10):12180-12188.
[19]赵夫群,周明全,耿国华.基于局部特征的点云配准算法[J].图学学报,2018,39(3):12-17.ZHAO Fuqun,ZHOU Mingquan,YAN Guohua. Point Cloud Registration Algorithm Based on Local Features[J]. Journal of Graphics,2018,39(3):12-17.
[20]刘振,周先存.基于独立权重和分级变异策略的粒子群算法[J].吉林大学学报:理学版,2017,55(2):333-339.LIU Zhen,ZHOU Xiancun. Particle Swarm Optimization Algorithm Based on Independent Weight and Hierarchical Variation Strategy[J]. Journal of Jilin University:Science Edition,2017,55(2):333-339.
[21]MAKADIA A,PATTERSON A,DANIILIDIS K. Fully Automatic Registration of 3D Point Clouds[C]∥Computer Vision and Pattern Recognition. IEEE Computer Society Conference on. Piscataway,NJ,USA:IEEE,2006:1297-1304.
[22]蔡文娜,刘凤连.一种基于法向量夹角的点云配准方法[J].天津理工大学学报,2018,34(3):17-20.CAI Wenna,LIU Fenglian. A Point Cloud Registration Method Based on the Angle of Normal Vector[J]. Journal of Tianjin University of Technology,2018,34(3):17-20.
[23]王欣,张明明,于晓,等.应用改进迭代最近点方法的点云数据配准[J].光学精密工程,2012,20(9):2068-2077.WANG Xin,ZHANG Mingming,YU Xiao,et al. Point Cloud Data Registration Using Improved Iterative Nearest Point Method[J]. Optics and Precision Engineering,2012,20(9):2068-2077.
[24]王雪,王秋爽.基于混合优化算法的医学图像配准技术[J].吉林大学学报:信息科学版,2016,34(5):703-708.WANG Xue,WANG Qiushuang. Medical Image Registration Technology Based on Hybrid Optimization Algorithm[J].Journal of Jilin University:Information Science Edition,2016,34(5):703-708.
[25]高铭泽.基于深度图像的三维重建技术研究及应用[D].大庆:东北石油大学电器信息工程学院,2018.GAO Mingze. Research and Application of 3D Reconstruction Technology Based on Depth Image[D]. Daqing:School of Electronic Information and Engineering,Northeast Petroleum University,2018.
[2]夏文玲,顾照鹏,杨唐胜.实时三维重建算法的实现———基于Kinect与单目视觉SLAM的三维重建[J].计算机工程与应用,2014,50(24):199-203.XIA Wenling,GU Zhaopeng,YANG Tangsheng. Realization of Real-Time 3D Reconstruction Algorithm-3D Reconstruction Based on Kinect and Monocular Vision SLAM[J]. Computer Engineering and Applications,2014,50(24):199-203.
[3]BESL P J,MCKAY N D. A Method for Registration of 3-D Shapes[M]. Piscataway,NJ,USA:IEEE Computer Society,1992.
[4]GREENSPAN M,GODIN G. A Nearest Neighbor Method for Efficient ICP[C]∥International Conference on 3-D Digital Imaging and Modeling. Piscataway,NJ,USA:IEEE,2001:161-168.
[5]BATLLE E,MATABOSCH C,SALVI J. Summarizing Image/Surface Registration for 6DOF Robot/Camera Pose Estimation[C]∥Iberian Conference on Pattern Recognition and Image Analysis. Berlin,German:Springer-Verlag,2007:105-112.
[6]DU S,ZHENG N,YING S,et al. Affine Iterative Closest Point Algorithm for Point Set Registration[J]. Pattern Recognition Letters,2010,31(9):791-799.
[7]KENNEDY J,EBERHART R C. Particle Swarm Optimization[C]∥Proc IEEE Int'l Conf on Neural Networks. Piscataway,NJ:IEEE,1995:1945-1950.
[8]HAN Jianghong,LI Zhengrong,WEI Zhenchun. An Adaptive Particle Swarm Optimization Algorithm and Its Simulation Research[J]. Journal of System Simulation,2006,18(10):2969-2971.
[9]KRISHNANAND K N,GHOSE D. Detection of Multiple Source Locations Using a Glowworm Metaphor with Applications to Collective Robotics[C]∥Swarm Intelligence Symposium. Piscataway,NJ,USA:IEEE,2005:84-91.
[10]刘洪霞,周永权.一种基于模式搜索算子的人工萤火虫优化算法[J].小型微型计算机系统,2011,32(10):2130-2133.LIU Hongxia,ZHOU Yongquan. An Artificial Firefly Optimization Algorithm Based on Pattern Search Operator[J]. Small Computer Systems,2011,32(10):2130-2133.
[11]刘军梅.新型混沌粒子群混合优化算法[J].软件导刊,2017,16(2):59-62.LIU Junmei. A New Hybrid Particle Swarm Optimization Algorithm[J]. Software Guide,2017,16(2):59-62.
[12]郗君甫.基于动态自适应萤火虫优化算法[J].邢台职业技术学院学报,2017(5):78-82.XI Junfu. Dynamic Adaptive Firefly Optimization Algorithm[J]. Journal of Xingtai Polytechnic,2017(5):78-82.
[13]曾艳阳,冯云霞,赵文涛.基于Logistic映射的自适应变尺度混沌粒子群算法[J].系统仿真学报,2017,29(10):2241-2246.ZENG Yanyang,FENG Yunxia,ZHAO Wentao. Adaptive Variable Scale Chaotic Particle Swarm Optimization Algorithm Based on Logistic Mapping[J]. Journal of System Simulation,2017,29(10):2241-2246.
[14]林诗洁,董晨,陈明志,等.新型群智能优化算法综述[J].计算机工程与应用,2018,54(12):6-14.LIN Shijie,DONG Chen,CHEN Mingzhi,et al. Overview of New Group Intelligent Optimization Algorithms[J]. Computer Engineering and Applications,2018,54(12):6-14.
[15]周丽娟,于雪晶,魏卓.基于萤火虫群算法的网络入侵优化检测算法[J].吉林大学学报:信息科学版,2015,33(3):338-343.ZHOU Lijuan,YU Xuejing,WEI Zhuo. Network Intrusion Optimization Detection Algorithm Based on Firefly Swarm Algorithm[J]. Journal of Jilin University:Information Science Edition,2015,33(3):338-343.
[16]LIU B,WANG L,JIN Y H,et al. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos Solitons&Fractals,2005,25(5):1261-1271.
[17]吴旺生.基于萤火虫LQG控制算法的半主动悬架研究[D].马鞍山:安徽工程大学机械工程学院,2017.WU Wangsheng. Research on Semi-Active Suspension Based on Firefly LQG Control Algorithm[D]. Maanshan:School of Mechanical Engineering,Anhui University of Engineering,2017.
[18]LIAO W H,KAO Y,LI Y S. A Sensor Deployment Approach Using Glowworm Swarm Optimization Algorithm in Wireless Sensor Networks[J]. Expert Systems with Applications,2011,38(10):12180-12188.
[19]赵夫群,周明全,耿国华.基于局部特征的点云配准算法[J].图学学报,2018,39(3):12-17.ZHAO Fuqun,ZHOU Mingquan,YAN Guohua. Point Cloud Registration Algorithm Based on Local Features[J]. Journal of Graphics,2018,39(3):12-17.
[20]刘振,周先存.基于独立权重和分级变异策略的粒子群算法[J].吉林大学学报:理学版,2017,55(2):333-339.LIU Zhen,ZHOU Xiancun. Particle Swarm Optimization Algorithm Based on Independent Weight and Hierarchical Variation Strategy[J]. Journal of Jilin University:Science Edition,2017,55(2):333-339.
[21]MAKADIA A,PATTERSON A,DANIILIDIS K. Fully Automatic Registration of 3D Point Clouds[C]∥Computer Vision and Pattern Recognition. IEEE Computer Society Conference on. Piscataway,NJ,USA:IEEE,2006:1297-1304.
[22]蔡文娜,刘凤连.一种基于法向量夹角的点云配准方法[J].天津理工大学学报,2018,34(3):17-20.CAI Wenna,LIU Fenglian. A Point Cloud Registration Method Based on the Angle of Normal Vector[J]. Journal of Tianjin University of Technology,2018,34(3):17-20.
[23]王欣,张明明,于晓,等.应用改进迭代最近点方法的点云数据配准[J].光学精密工程,2012,20(9):2068-2077.WANG Xin,ZHANG Mingming,YU Xiao,et al. Point Cloud Data Registration Using Improved Iterative Nearest Point Method[J]. Optics and Precision Engineering,2012,20(9):2068-2077.
[24]王雪,王秋爽.基于混合优化算法的医学图像配准技术[J].吉林大学学报:信息科学版,2016,34(5):703-708.WANG Xue,WANG Qiushuang. Medical Image Registration Technology Based on Hybrid Optimization Algorithm[J].Journal of Jilin University:Information Science Edition,2016,34(5):703-708.
[25]高铭泽.基于深度图像的三维重建技术研究及应用[D].大庆:东北石油大学电器信息工程学院,2018.GAO Mingze. Research and Application of 3D Reconstruction Technology Based on Depth Image[D]. Daqing:School of Electronic Information and Engineering,Northeast Petroleum University,2018.