Please wait a minute...
浙江大学学报(工学版)  2020, Vol. 54 Issue (8): 1449-1456    DOI: 10.3785/j.issn.1008-973X.2020.08.001
机械工程     
面向视觉伺服的工业机器人轮廓曲线角点识别
冯毅雄1(),李康杰1,高一聪1,*(),郑浩2
1. 浙江大学 流体动力与机电系统国家重点实验室,浙江 杭州 310027
2. 北京航空航天大学 杭州创新研究院,浙江 杭州 310000
Corner recognition of industrial robot contour curve for visual servoing
Yi-xiong FENG1(),Kang-jie LI1,Yi-cong GAO1,*(),Hao ZHENG2
1. State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China
2. Hangzhou Innovation Institute, Beihang University, Hangzhou 310000, China
 全文: PDF(1398 KB)   HTML
摘要:

为了解决工业机器人视觉伺服中轮廓曲线角点识别效率低进而影响实时定位准确性的问题,提出面向视觉伺服的工业机器人轮廓曲线角点识别算法. 建立基于Freeman链码的机械爪轮廓曲线编码模型,利用差别码对机械爪轮廓曲线的角度变化特征进行统一编码建模. 通过基于差别码和卷积系数的卷积运算,对差别码进行局部非线性加权,计算机械爪轮廓曲线上各点的曲度精确量化辨识机械爪角点. 基于候选角点阈值、点的最远领域间隔和局部范围最多点数进行获选角点的初步选取. 采用平面轮廓曲线毛刺过滤筛选误识角点,实现机械爪角点的精确识别,为视觉伺服中实时定位提供可靠的位置信息. 通过与已有平面轮廓曲线角点识别算法对比,验证本研究所提方法的准确性和高效性,提取角点过程具有较强的鲁棒性.

关键词: 工业机器人视觉伺服机械爪角点识别平面轮廓曲线    
Abstract:

A contour curve corner recognition algorithm was presented to solve the problem of low efficiency of corner recognition of contour curve in visual servoing of industrial robots, which affects the accuracy of real-time positioning. A coding model of gripper contour curve based on Freeman chain code is established, and the differential code is used to unify the coding model of the characteristics of contour curve angle change of gripper. The differential codes are weighted locally and the curvature values of points on the gripper contour curve are calculated to accurately quantify the identification of the corners through convolution operation based on differential codes and convolution coefficients. The preliminary selection of the selected corner points is based on the candidate corner point threshold, the distance between the farthest point of the point and the maximum point value in the local range. A burr filtering for planar contour curve is used to screen mistaken points, moreover an accurate recognition of gripper corner point is realized, which provides reliable location information for real-time positioning in visual servo system. The accuracy and efficiency of the proposed method are verified by comparing with the existing corner recognition algorithms of planar contour curves, and the corner extraction process of the proposed method has strong robustness.

Key words: industrial robot    visual servo    gripper    corner recognition    plane contour curve
收稿日期: 2020-07-09 出版日期: 2020-08-28
CLC:  TP 391.41  
基金资助: 国家重点研发计划资助项目(2017YFB1301201);国家自然科学基金资助项目(51675477,51775489,51805472);浙江省自然科学基金资助项目(LZ18E050001)
通讯作者: 高一聪     E-mail: fyxtv@zju.edu.cn;gaoyicong@zju.edu.cn
作者简介: 冯毅雄(1975—),男,教授,从事现代机械设计理论与方法研究. orcid.org/0000-0001-7397-2482. E-mail: fyxtv@zju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
冯毅雄
李康杰
高一聪
郑浩

引用本文:

冯毅雄,李康杰,高一聪,郑浩. 面向视觉伺服的工业机器人轮廓曲线角点识别[J]. 浙江大学学报(工学版), 2020, 54(8): 1449-1456.

Yi-xiong FENG,Kang-jie LI,Yi-cong GAO,Hao ZHENG. Corner recognition of industrial robot contour curve for visual servoing. Journal of ZheJiang University (Engineering Science), 2020, 54(8): 1449-1456.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2020.08.001        http://www.zjujournals.com/eng/CN/Y2020/V54/I8/1449

图 1  机械爪轮廓提取
图 2  链码的方向符号
图 3  轮廓曲线段编码
图 4  差别码对链码压缩效果
图 5  轮廓直线上点的曲度计算
图 6  轮廓直角点的曲度值计算
图 7  候选角点选取流程图
图 8  曲线毛刺局部放大图
图 9  识别包围盒定义
名称 权值分布 长度 赋值
三角窗函数 线性 9 h1={0.125,0.250,0.500,0.750,
10.750,0.500,0.250,0.125}
逻辑函数 非线性 9 h2={0.12,0.27,0.73,0.88,10.88,
0.73,0.27,0.12}
表 1  卷积系数设计
图 10  卷积系数1的识别
图 11  卷积系数2的识别
图 12  卷积系数1识别包围盒计算
图 13  卷积系数2识别包围盒计算
图 14  机械爪轮廓角点检测结果
s
算法 运行时间
树叶 飞机 桃心 音符
RJ-algo 0.0674 0.1053 0.0317 0.0553
Guo_algo 0.1070 0.0076 0.0075 0.0125
FD_algo 0.0119 0.0134 0.0119 0.0044
DC_algo 21.2706 39.3793 9.5421 22.4091
SAM_algo 19.4806 24.1962 7.9894 13.7385
HS_algo 0.0073 0.0068 0.0019 0.0055
ACF_algo 46.5085 220.4689 18.1019 2371.0000
本研究方法 0.0071 0.0079 0.0096 0.0141
表 2  算法运行时间对比
图 15  算法识别结果对比
1 HAJILOO A, KESHMIRI M, XIE W F, et al Robust on-line model predictive control for a constrained image based visual servoing[J]. IEEE Transactions on Industrial Electronics, 2016, 63 (4): 2242- 2250
2 QIU Z, HU S, LIANG X Model predictive control for constrained image-based visual servoing in uncalibrated environments[J]. Asian Journal of Control, 2018, 21 (2): 783- 799
3 ANJUM F, KANWAL N, CLARK A F, et al Statistical evaluation of corner detectors: does the statistical test have an effect[J]. IET Computer Vision, 2017, 12 (7): 1018- 1030
4 LIN X, ZHU C, ZHANG Q, et al Geometric mesh corner detection using triangle principle[J]. Electronics Letters, 2017, 53 (20): 1354- 1356
doi: 10.1049/el.2017.1353
5 林颖, 龚小谨, 刘济林 基于单位视球的鱼眼相机标定方法[J]. 浙江大学学报: 工学版, 2013, 47 (8): 1500- 1507
LIN Ying, GONG Xiao-jing, LIU Ji-lin Calibration method of fisheye camera based on unit eyeball[J]. Journal of Zhejiang University: Engineering Science, 2013, 47 (8): 1500- 1507
6 YAO G B, CUI J, DENG K Z, et al Robust harris corner matching based on the quasi-homography transform and self-adaptive window for wide-baseline stereo images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56 (1): 559- 574
doi: 10.1109/TGRS.2017.2751567
7 竺乐庆, 陈文智, 幸锐, et al 鲁棒的掌纹图像特征提取方法[J]. 浙江大学学报: 工学版, 2009, 43 (8): 1412- 1418
ZHU Le-qing, CHEN Wen-zhi, XING Rui, et al Robust palmprint image feature extraction method[J]. Journal of Zhejiang University: Engineering Edition, 2009, 43 (8): 1412- 1418
8 KAGAMI S, OMI K, HASHIMOTO K Alignment of a flexible sheet object with position-based and image-based visual servoing[J]. Advanced Robotics, 2016, 30 (15): 1- 14
9 QIN Z, PENG W, JIA S, et al Precise robotic assembly for large-scale objects based on automatic guidance and alignment[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65 (6): 1398- 1411
doi: 10.1109/TIM.2016.2526738
10 SHUI P L, ZHANG W C Corner detection and classification using anisotropic directional derivative representations[J]. IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society, 2013, 22 (8): 3204- 3218
doi: 10.1109/TIP.2013.2259834
11 SANCHEZ J, MONZON N, SALGDO A An analysis and implementation of the harris corner detector[J]. Image Processing on Line, 2018, 9: 325- 328
12 XIAO J, XIA Z, WANG B, et al Adaptive algorithm for corner detecting based on the degree of sharpness of the contour[J]. Optical Engineering, 2011, 50 (4): 047008
doi: 10.1117/1.3569846
13 赵文彬, 张艳宁 角点检测技术综述[J]. 计算机应用研究, 2006, 23 (10): 17- 19
ZHAO Wen-bin, ZHANG Yan-ning Survey on corner detection[J]. Application Research of Computers, 2006, 23 (10): 17- 19
doi: 10.3969/j.issn.1001-3695.2006.10.006
14 ROSENFELD A, JOHNSTON E Angle detection on digital curves[J]. IEEE Transactions on Computers, 1973, 22 (9): 875- 878
15 ROSENFELD A, WESZKA J S An improved method of angle detection on digital curves[J]. IEEE Transactions on Computers, 1975, 24 (9): 940- 941
16 CHETVERIKOV D A simple and efficient algorithm for detection of high curvature points in planar curves[J]. Lecture Notes in Computer Science, 2003, 128: 175- 184
17 FREEMAN H, DAVIS L S A corner-finding algorithm for chain-coded curves[J]. IEEE Transactions on Computers, 1977, 26 (3): 297- 303
doi: 10.1109/TC.1977.1674825
18 BEUS H L, TIU S S H An improved corner detection algorithm based on chain-coded plane curves[J]. Pattern Recognition, 1987, 20 (3): 291- 296
doi: 10.1016/0031-3203(87)90004-5
19 BANDERA A, URDIALES C, ARREBOLA F, et al Corner detection by means of adaptively estimated curvature function[J]. Electronics Letters, 2000, 36 (2): 124- 126
doi: 10.1049/el:20000177
20 SARFRAZ M, MASOOD A, ASIM M R. A new approach to corner detection [M]// Computer vision and graphics. Dordrecht: Springer, 2006: 528-533.
21 HARON H, SHAMSUDDIN S M, MOHAMED D A new corner detection algorithm for chain code representation[J]. International Journal of Computer Mathematics, 2005, 82 (8): 941- 950
doi: 10.1080/00207160410001684271
22 郭晓冬. 图像角点检测算法研究[D]. 长沙: 国防科学技术大学, 2007.
Guo Xiao-dong. A research of corner detection algorithms [D]. Changsha: National University of Defense Technology, 2007.
23 SPONTON H, CARDELINO J A review of classic edge detectors[J]. Image Processing on Line, 2015, 27 (2): 533- 545
24 ZALIK B, MONGUS D, LUKAC N, et al Efficient chain code compression with interpolative coding[J]. Information Sciences, 2018, 439?440: 39- 49
doi: 10.1016/j.ins.2018.01.045
[1] 董大钊,徐冠华,高继良,徐月同,傅建中. 基于机器视觉的机器人装配位姿在线校正算法[J]. 浙江大学学报(工学版), 2021, 55(1): 145-152.
[2] 郭英杰,顾钒,董辉跃,汪海晋. 压脚压紧力作用下的机器人变形预测和补偿[J]. 浙江大学学报(工学版), 2020, 54(8): 1457-1465.
[3] 毛晨涛,陈章位,张翔,祖洪飞. 基于相对精度指标的机器人运动学校准[J]. 浙江大学学报(工学版), 2020, 54(7): 1316-1324.
[4] 蒲陈阳,刘作军,庞爽,张燕. 知识继承型迭代学习控制的研究与应用[J]. 浙江大学学报(工学版), 2019, 53(7): 1340-1348.
[5] 董辉跃, 孙强, 郭英杰, 赵安安, 朱伟东. 机器人孔口倒角加工振动及抑制[J]. 浙江大学学报(工学版), 2018, 52(12): 2243-2252.
[6] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[7] 何雪军,王进,陆国栋,陈立. 岛中含湖型截面的环切刀轨连接方法[J]. 浙江大学学报(工学版), 2016, 50(9): 1654-1661.
[8] 何雪军, 王进, 陆国栋, 陈立. 基于蚁群算法的机器人图像绘制序列优化[J]. 浙江大学学报(工学版), 2015, 49(6): 1139-1145.
[9] 董辉跃,朱灵盛, 章明, 李少波,罗水均. 飞机蒙皮切边的螺旋铣削方法[J]. 浙江大学学报(工学版), 2015, 49(11): 2033-2039.
[10] 刘楚辉, 姚宝国, 柯映林. 工业机器人切削加工离线编程研究[J]. J4, 2010, 44(3): 426-431.