基于超二次曲面模型的3维目标定位算法

doi:10.3724/SP.J.1218.2013.00439

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (4075 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
汪霖, 曹建福, 韩崇昭. 基于超二次曲面模型的3维目标定位算法[J]. 机器人, 2013, 35(4): 439-448.DOI: 10.3724/SP.J.1218.2013.00439. WANG Lin, CAO Jianfu, HAN Chongzhao. Superquadrics Model-based 3D Object Localization Algorithm. ROBOT, 2013, 35(4): 439-448. DOI: 10.3724/SP.J.1218.2013.00439.

摘要

针对散乱点云中3维目标的位姿参数估计问题，提出一种基于超二次曲面模型的3维目标定位算法．该算法利用3维目标的超二次曲面部件化模型，定义了空间点与任意位姿下3维目标的归一化径向欧氏距离．根据点云中目标表面各点到目标的均方距离，以及目标表面点数和内部点数等信息，建立了3维目标位姿估计的非线性目标函数，从而将目标定位问题转化为该目标函数的优化问题．采用入侵性杂草优化（IWO）算法优化该目标函数，将获得的最优解作为3维目标的位姿参数估计值．实验结果表明，该算法的目标定位精度高，位姿参数估计的一致性好，且能有效抑制测量噪声对定位结果的影响．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	汪霖
	曹建福
	韩崇昭

关键词 ：散乱点云, 3维目标定位, 超二次曲面, 非线性目标函数, 入侵性杂草优化

Abstract：

For the pose parameter estimation problem of 3D objects in an unorganized point cloud, a 3D object localization algorithm based on superquadrics model is proposed. A normalized radial Euclidean distance of a space point from the 3D object under arbitrary pose is defined by using the part-based superquadrics model of the 3D object. Then a nonlinear objective function for the 3D object pose estimation is established according to the mean square distance between the object surface points and the object in the point cloud, as well as the surface point number and interior point number of the object. By this means, the object localization problem is transformed into an optimization problem of the objective function. Then the invasive weed optimization (IWO) algorithm is adopted to optimize this objective function, and the obtained optimal solution is used as the estimation value of the 3D object pose. Experimental results demonstrate that the proposed algorithm can yield accurate object localization results with a good consistency of pose parameters, and effectively suppress the influence of measurement noises on measurement results.

Key words： unorganized point cloud 3D object localization superquadrics nonlinear objective function invasive weed optimization (IWO)

收稿日期: 2012-11-02 录用日期: 2013-04-19

TP24

基金资助:

国家863计划资助项目（2006AA01Z126）．

通讯作者: 曹建福 E-mail: cjf@mail.xjtu.edu.cn

作者简介: 汪霖（1983-），男，博士．研究领域：多传感器信息融合，高速数控技术．
曹建福（1963-），男，博士，教授．研究领域：非线性系统理论，先进机器人控制技术，高速高精度数控技术．
韩崇昭（1943-），男，教授，博士生导师．研究领域：多传感器信息融合，随机控制与自适应控制，工业过程控制与优化，非线性频谱分析．

链接本文:

https://robot.sia.cn/CN/10.3724/SP.J.1218.2013.00439 或 https://robot.sia.cn/CN/Y2013/V35/I4/439

[1] Katsoulas D, Bastidas C C, Kosmopoulos D. Superquadric segmentation in range images via fusion of region and boundary information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(5): 781-795.

[2] Pathak K, Birk A, Vaskevicius N, et al. Fast registration based on noisy planes with unknown correspondences for 3-D mapping[J]. IEEE Transactions on Robotics, 2010, 26(3): 424-441.

[3] 庄严,卢希彬,李云辉,等.移动机器人基于三维激光测距的室内场景认知[J].自动化学报,2011,37(10):1232-1240. Zhuang Y, Lu X B, Li Y H, et al. Mobile robot indoor scene cognition using 3D laser scanning[J]. Acta Automatica Sinica, 2011, 37(10): 1232-1240.

[4] Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3d scenes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(5): 433-449.

[5] Rusu R B, Bradski G, Thibaux R, et al. Fast 3D recognition and pose using the viewpoint feature histogram[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2010: 2155-2162.

[6] Binford T O. Visual perception by computer[C]//IEEE Conference on Systems and Control. Piscataway, USA: IEEE, 1971: 116-123.

[7] Barr A H. Superquadrics and angle-preserving transformations[J]. IEEE Computer Graphics and Applications, 1981, 1(1): 11-23.

[8] Solina F, Bajcsy R. Recovery of parametric models from range images: The case for superquadrics with global deformations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(2): 131-147.

[9] Schnabel R, Wahl R, Klein R. Efficient RANSAC for point-cloud shape detection[J]. Computer Graphics Forum, 2007, 26(2): 214-226.

[10] Krivic J, Solina F. Part-level object recognition using superquadrics[J]. Computer Vision and Image Understanding, 2004, 95(1): 105-126.

[11] Biegelbauer G, Vincze M, Wohlkinger W. Model-based 3D object detection: Efficient approach using superquadrics[J]. Machine Vision and Applications, 2010, 21(4): 497-516.

[12] Mehrabian A R, Lucas C. A novel numerical optimization algorithm inspired from weed colonization[J]. Ecological Informatics, 2006, 1(4): 355-366.

[13] 周林,袁保宗.扩展超二次曲面:一种新的光滑变形曲面模型[J].电子学报,1998,26(8):47-50,64. Zhou L, Yuan B Z. Extended superquadric: A new smoothly deformable surface model[J]. Acta Electronica Sinica, 1998, 26(8): 47-50,64.

[14] Chevalier L, Jaillet F, Baskurt A. Segmentation and superquadric modeling of 3D objects[J]. Journal of Winter School of Computer Graphics, 2003, 11(2): 232-239.

[15] Goldfeder C. Data-driven grasping[D]. New York, USA: Columbia University, 2010.

[16] Krishnanand K R, Nayak S K, Panigrahi B K, et al. Comparative study of five bio-inspired evolutionary optimization techniques[C]//World Congress on Nature & Biologically Inspired Computing. Piscataway, USA: IEEE, 2009: 1231-1236.

[17] 张氢,陈丹丹,秦仙蓉,等.杂草算法收敛性分析及其在工程中的应用[J].同济大学学报:自然科学版,2010,38(11):1689-1693. Zhang Q, Chen D D, Qin X R, et al. Convergence analysis of invasive weed optimization algorithm and its application in engineering[J]. Journal of Tongji University: Natural Science, 2010, 38(11): 1689-1693.

[18] 汪霖,曹建福,韩崇昭.基于粒子群优化的机器人多传感器自标定方法[J].机器人,2009,31(5):391-396. Wang L, Cao J F, Han C Z. A robot multi-sensor self-calibration method based on particle swarm optimization[J]. Robot, 2009, 31(5): 391-396.

[19] SICK AG. LMS400 laser measurement system: Pole position for robotics and material handling[DB/OL]. (2006-10-31) [2012-10-31]. https://www.mysick.com/saqqara/pdf.aspx?id= im0010698.

[20] Kennedy J, Eberhart R. Particle swarm optimization[C]//IEEE International Conference on Neural Networks. Piscataway, USA: IEEE, 1995: 1942-1948.