|本期目录/Table of Contents|

[1]黄立平,左骏秋,张 磊.基于机器人视觉伺服的确定下一最优视点的方法研究[J].工业仪表与自动化装置,2015,(02):7-11.
　HUANG Liping,ZUO Junqiu,ZHANG Lei.Studies to determine the next best view of the robot visual servo-based approach[J].Industrial Instrumentation & Automation,2015,(02):7-11.
点击复制

基于机器人视觉伺服的确定下一最优视点的方法研究(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2015年02期
页码:
7-11
栏目:
出版日期:
2015-04-15

文章信息/Info

Title:
Studies to determine the next best view of the robot visual servo-based approach
作者:
黄立平1; 左骏秋2; 张 磊2
（1. 南通职业大学 技师学院，江苏 南通 226007；2. 南通大学 机械工程学院，江苏 南通 226019）
Author(s):
HUANG Liping1;  ZUO Junqiu2;  ZHANG Lei2
(1.Technician College, Nantong Vocational University, Jiangsu Nantong 226007, China;2. College of Mechanical Engineering, Nantong University, Jiangsu Nantong 226019, China)
关键词:
视点规划; 下一最优视点; 自动三维重构; 视觉伺服; 机器人
Keywords:
view planning;  next best view;  automatic 3D reconstruction;  visual servo
分类号:
-
DOI:
-
文献标志码:
A
摘要:
机器人自动视点规划是目标物自动三维重构研究中的首要问题，而自动确定下一最优视点的位置和方向是自动视点规划的关键。经典群矢量链法只能确定下一最优视点的方向，该文提出一种简化的2-1/2-D视觉伺服新方法，确定下一最优视点的空间位置。新方法使用群矢量链法以开环的方式控制末端执行器的方向；通过图像质心坐标与目标物图像面积等图像特征，采用基于图像的视觉伺服控制末端执行器的位置。方向控制与位置控制相结合形成2-1/2-D的控制策略，使机器人达到下一最优视点的期望位姿。新方法图像雅可比矩阵维数低，控制方法相比经典2-1/2-D视觉伺服更简单易实现。实验结果显示，该方法可使机器人运动到期望的方向和位置实现自动视点规划。最终生成的目标物曲线表面基本上是完整的，只有因目标物表面有些凹小区域引起的很小盲区。
Abstract:
In automatic 3D reconstruction, automatic view planning is a primary task, where determining next best view (NBV) is the key problem. A visual servo-based approach is proposed in this paper for determining the NBV spatial position, where the 2-1/2-D visual servoing is involved. The classical mass vector chain (MVC) is used for determining the NBV direction. The orientation of the end effector is controlled by MVC method in an open-loop, which decreases the dimensionality of the image Jacobian. Some image features are extracted for position control of the end effector in 2-1/2-D visual servoing. The experimental results show that the proposed method can guide the robot to the desired orientation and position for automatic multi-view planning. The final produced curve surface is basically complete, only with a few tiny blind areas possibly because of many concave small surface patches on surface.

参考文献/References:

[1] Maver J, Leonardis A & Solina F. Planning the next view using the max-min principle[C]. International Conference on Computer Analysis of Images and Patterns. Lecture Notes in Computer Science, 1993, 719: 543-547.

[2] Yuan X. A mechanism of automatic 3D object modeling[J]. IEEE Transactions Pattern Analysis and Machine Intelligence. 1995, 17(3): 307-311.
[3] S Larsson, J A P Kjellander. Path planning for laser scanning with an industrial robot[J]. Robotics and Autonomous Systems, 2008, 56(7): 615-624.
[4] W R Scott, G Roth, J F Rivest. View planning for automatic three dimensional object reconstruction and inspection[J]. ACM Computer Surveys, 2003, 35(1): 64-96.
[5] W R Scott. Model based view planning [J]. Machine Vision and Applications, 2009, 20(1): 47- 69.
[6] B W He, Zhou Xiao Long, Y F Li. The research of an automatic object reconstruction method based on limit visible region of the laser-scanning vision system[J]. Robotics and Computer-Integrated Manufacturing, 2010 (26):711-719.
[7] 何炳蔚,周小龙.面向未知物体自动测量和重建的视点规划方法[J].计算机辅助设计与图形学学报,2008,22(5): 1374-1382.
[8] He Bingwei, Zhou Xiaolong. Research of Sensor Planning Method in Line Laser Three Dimensional Measurement System (in Chinese) [J]. Chinese Journal of Lasers (Chinese
[9] 姚兴田,吴亮亮,马永林,等.自动三维重构中确定下一最优视点的方法研究[J].江西师范大学:然科学版,2013, 37(6): 569-573.
[10] Connolly C. The determination of next best views[C]. IEEE International Conference on Robotics and Automation. 1985: 432 – 435.
[11] Ezio Malis, Fran?cois Chaumette, and Sylvie Boudet. 2-1/2-D Visual Servoing[J].IEEE Transactions On Robotics And Automation, 1999, 15(2): 238-250.
[12] 于水生,蔡勇,饶锦锋.具有对称特征的三维模型重构技术研究[J].机械设计与制造, 2012, 9(9):80-82.
[13] 何炳蔚.未知对象自动三维重建过程自终止判别方法研究[J].工程图学学报,2007, 3(5): 76-82.

相似文献/References:

备注/Memo

备注/Memo:

收稿日期 ： 2014-08-15

基金项目 ：南通市应用研究计划项目（ BK2012002 ） ;2012 年江苏省 “ 优秀青年骨干教师培养对象项目”

作者简介 ：黄立平（ 1968 ），江苏海安人，南通职业大学高级讲师，主要研究方向是三维造型设计、数控应用与三维重构。近年来开始研究机器人视觉的应用。

更新日期/Last Update: 1900-01-01