遗传算法结合自适应阈值约束的ICP算法

石爱军; 白瑞林; 田青华; 李杜

光学技术, 2018, 44 (1): 63, 网络出版: 2018-02-01

遗传算法结合自适应阈值约束的ICP算法

Optimized ICP method combining genetic algorithm with adaptive threshold constraints

论文大纲

石爱军 ^1,*白瑞林 ¹田青华 ¹李杜 ²

作者单位

¹ 江南大学轻工过程先进控制教育部重点实验室, 江苏无锡 214122

² 无锡信捷电气股份有限公司, 江苏无锡 214072

光学测量位姿估计遗传算法自适应阈值 optical measurement pose estimation ICP ICP genetic algorithm adaptive threshold

摘要

根据传统ICP算法存在的缺点, 提出了一种遗传算法结合自适应阈值约束优化的ICP位姿估计方法。采用统计学滤波和区域增长分割算法对原始点云进行预处理, 去除离群点并得到各混乱工件的点云集; 针对ICP易陷于局部最优的问题, 利用遗传优化算法对点云进行粗匹配, 得到目标点集相对于参考点云的初始位姿; 针对迭代速度较慢的缺点, 提出了一种自适应阈值约束法, 利用点对距离约束和法向量夹角约束去除局部大变形点, 在保证实时性的同时提高了位姿估计的精度。实验表明, 该方法能够在84.5ms内定位一个工件, 位姿估计误差达0.39mm, 满足实时性和抓取精度要求, 能够为工业机器人随机箱体抓取提供理论依据与指导。

Abstract

In order to solve the problem of iterative closest point algorithm, an improved pose estimation method based on genetic algorithm combined with adaptive threshold constraints is proposed. Point clouds without noise are obtained by adopting an optimized preprocessing approach combining a statistical outlier removal filter and region growing segmentation algorithm. Considering the disadvantage of local optimization for ICP, genetic algorithm is applied which calculated target clusters’ probable pose to reference point cloud. Adaptive threshold constraints are proposed in consideration of slow speed of iteration. Local large deformation is removed by selecting eligible points according to Euclidean threshold and normal vector angle threshold, which ensured computation speed and improved the precision of pose estimation at the same time. Experiments show that the method can get a pose of a target in 84.5ms, and the pose estimation error is 0.39mm, which meets the real-time and accuracy demands and provides theoretical basis and guidance for the grasp of random bin picking with industrial robot.

参考文献

[1] Consultant R B. Random bin picking: has its time finally come［J］. Assembly Automation, 2014, 34(3): 217-221.

[2] Akizuki S, Hashimoto M. Position and pose recognition of randomly stacked objects using highly observable 3D vector pairs［C］∥IECON 2014-40th Annual Conference of the IEEE Industrial Electronics Society. Montreal: IEEE, 2014: 5266-5271.

[3] 侯东兴, 王耀华, 李宗春. 剔除误同名点的约束改进ICP算法［J］. 测绘科学, 2015, 40(8):103-107.

Hou Dongxing , Wang Yaohua, Li Zongchun. Constraints improved ICP algorithm based on eliminating error correspondence point［J］. Science of Surveying and Mapping, 2015, 40(8):103-107.

[4] 张学昌, 习俊通, 严隽琪,等. 基于遗传算法的点云数据与CAD模型坐标归一化研究［J］. 系统仿真学报, 2006, 18(9):2497-2500.

Zhang Xuechang, Xi Juntong, Yan Junqi. Study of registration point cloud to CAD model based on genetic algorithm［J］. Journal of System Simulation, 2006, 18(9):2497-2500.

[5] 钟莹, 张蒙. 基于改进ICP算法的点云自动配准技术［J］. 控制工程, 2014, 21(1):37-40.

Zhong Ying, Zhang Meng. Automatic registration technology of point cloud based on improved ICP algorithm［J］. Control Engineering of China, 2014, 21(1):37-40.

[6] 钱鹏鹏, 郑德华. 一种新的扫描点云自动配准方法［J］. 水利与建筑工程学报, 2013(3):162-164.

Qian Pengpeng, Zheng Dehua. A new automatic registration method of scanning point cloud［J］. Journal of Water Resources and Architectural Engineering, 2013(3):162-164.

[7] Choi C, Taguchi Y, Tuzel O, et al. Voting-based pose estimation for robotic assembly using a 3D sensor［C］∥Robotics and Automation (ICRA), 2012 IEEE International Conference on. Minnesota: IEEE, 2012: 1724-1731.

[8] 徐万鑫, 许宏丽. 改进的ICP算法在点云配准中的应用［C］∥中国系统仿真技术及其应用学术年会. 北京: 中国自动化学会, 2012: 205-208.

Xu Wanxin, Xu Hongli. The application of improved ICP algorithm in point cloud registration［C］∥Chinese Conference on System Simulation Technology & Application. Beijing: Chinese Association of Automation, 2012: 205-208.

[9] Sharp G C,Lee S W,Wehe D K.ICP registration using invariantfeatures［J］.IEEE Transactions on Pattern Analysis and Ma-chine Intelligence,2002,24(1):90-102.

[10] Bae K H,Lichti D D.A method for automated registration of un-organised point clouds［J］. Journal of Photogrammetry and Re-mote Sensing,2008,63(1):36-54.

[11] 张蕾, 冀治航, 普杰信,等. 约束改进的ICP点云配准方法［J］. 计算机工程与应用, 2012, 48(18):197-200.

Zhang Lei, Ji Zhihang Pu Jiexin, et al. ICP method improved by constraints for point cloud registration［J］. Computer Engineering and Applications, 2012, 48(18):197-200.

[12] Kim J, Nguyen H H, Lee Y, et al. Structured light camera base 3D visual perception and tracking application system with robot grasping task［C］∥Assembly and Manufacturing (ISAM), 2013 IEEE International Symposium on. IEEE, 2013: 187-192.

[13] Xu J, Pu S, Zeng G, et al. 3D pose estimation for bin-picking task using convex hull［C］∥2012 IEEE International Conference on Mechatronics and Automation. IEEE, 2012: 1381-1385.

[14] Ko K H, Maekawa T, Patrikalakis N M, et al. Shape intrinsic properties for free-form object matching［J］. Journal of Computing and Information Science in Engineering, 2003, 3(4): 325-333.

[15] Radu B, Rusu. Removing sparse outliers using statistical outlier removal［EB/OL］.(2016-11-27)［2016-11-27］.http://www.pointclouds.org/documentation/tutorials/statistical_outlier.php#statistical-outlier-removal.

[16] 石爱军, 白瑞林, 田青华. Gray码结合线移的结构光三维测量［J］. 光电工程, 2016, 43(11):26-32.

Shi Aijun, Bai Ruilin, Tian Qinghua. 3D measurement based on structured light using a combination of Gray code and line-shift patterns［J］. Opto-Electronic Engineering, 2016, 43(11):26-32.

[17] 闫利, 谢洪, 胡晓斌,等. 一种新的点云平面混合分割方法［J］. 武汉大学学报信息科学版, 2013, 38(5):517-521.

Yan Li, Xie Hong, Hu Xiaobing, et al. A new hybrid plane segmentation approach of point cloud［J］. Geomatics and Information Science of Wuhan University, 2013, 38(5):517-521.

[18] 倪欢, 张继贤, 林祥国. 三维点云边缘检测和直线段提取进展与展望［J］. 测绘通报, 2016(7):1-4.

Ni Huan, Zhang Jixian , Lin Xiangguo. Edge detection and straight line segment extraction from 3D-point clouds: Review and prospect［J］. Bulletin of Surveying and Mapping, 2016(7):1-4.

[19] Arun K S, Huang T S, Blostein S D. Least-squares fitting of two 3-D point sets［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,1987,9(5):698-700.

石爱军, 白瑞林, 田青华, 李杜. 遗传算法结合自适应阈值约束的ICP算法[J]. 光学技术, 2018, 44(1): 63. SHI Aijun, BAI Ruilin, TIAN Qinghua, LI Du. Optimized ICP method combining genetic algorithm with adaptive threshold constraints[J]. Optical Technique, 2018, 44(1): 63.

遗传算法结合自适应阈值约束的ICP算法

关于本站 Cookie 的使用提示

全站搜索

遗传算法结合自适应阈值约束的ICP算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索