零件的角点提取及匹配定位

高礼圳; 刘书桂; 韩振华

doi:10.3788/CO.20160904.0397

零件的角点提取及匹配定位

doi: 10.3788/CO.20160904.0397

天津大学精密测试技术及仪器国家重点实验室, 天津 300072

基金项目:

天津市自然科学基金重点资助项目 No.13JCZDJC34500

详细信息

作者简介:
高礼圳：髙礼圳(1991-),男,江西吉安人,硕士研究生,主要从事图像处理和计算机视觉方面的研究。E-mail:gaolz1002@163.com

通讯作者:
刘书桂(1954-),男,湖南人,教授,博士,博士生导师,主要从事智能坐标测量技术、自动测量与控制技术方面的研究。E-mail:sgliu@tju.edu.cn

中图分类号: TH744.3
计量
- 文章访问数: 2354
- HTML全文浏览量: 799
- PDF下载量: 946
- 被引次数: 0
出版历程
- 收稿日期: 2016-04-05
- 修回日期: 2016-04-26
- 刊出日期: 2016-08-01

Corner extraction and matching location of parts

State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China

Funds:

Key Project of Natural Science Foundation of Tianjin City No.13JCZDJC34500

More Information

Corresponding author: E-mail:sgliu@tju.edu.cn

摘要

摘要: 本文基于三坐标测量机（CMM）设计了一套视觉检测系统，该系统能够对零件实际空间特征信息进行比较全面地提取。针对位于CMM平台上带有角点的零件，利用Harris算子提取从CMM三个不同方位获取的零件图像的角点。对于Harris算子提取到的角点，本文提出一种八链码搜索法和SUSAN区域法相结合的伪角点剔除方法，最后基于立体视觉的原理，提出“距离空间图”匹配算法，将以上3幅图像一一建立匹配关系。实验中多次改变零件在CMM中姿态时，多次实验数据表明本文的角点提取精度与真实角点间仅存在1~2像素的偏差，零件的定位误差为1~3mm。通过实验验证，角点匹配和定位的稳定性和精度满足要求，具有一定的抗干扰性和实用性。
- 三坐标测量机 /
- Harris算子 /
- 角点匹配 /
- 立体视觉 /
- 距离空间图
Abstract: In this paper, a set of visual inspection system is designed based on three coordinate measuring machine(CMM), and the new visual system can extract the actual spatial feature information of the parts. For the parts with corner which is on the platform of CMM, the Harris operator is used to extract corners in the images obtained from three different orientation of the CMM. For the corner points extracted by the Harris operator, this paper proposes a method of eliminating the false corners, which combines eight-chain-code false corner search method and SUSAN method. Finally, based on the principle of stereo vision, the "Distance spatial map" matching algorithm is put forward, and then the three images are matched one by one. Although the position and orientation of parts are changed for many times in the experiment, the experiment results show that there are 1-2 pixels difference between extracted corners and the real corner points, and the position error of parts is 1-3 mm. Through the experiment, the accuracy and stability of corner matching and positioning can meet the requirements, and with anti-interference and practicability as well as.
- CMM /
- Harris operator /
- corner matching /
- stereo vision /
- distance spatial map

HTML全文

图 1 八链码的方向图

中文注解

Figure 1. Eight-chain-code direction

英文注解

下载: 全尺寸图片幻灯片

图 2 相机与CMM的方位图

中文注解

Figure 2. Orientation diagram of camera and CMM

英文注解

下载: 全尺寸图片幻灯片

图 3 对极几何约束图

中文注解

Figure 3. Diagram of epipolar geometry

英文注解

下载: 全尺寸图片幻灯片

图 4 多视图确定空间点

中文注解

Figure 4. Multiple views to determine the point

英文注解

下载: 全尺寸图片幻灯片

图 5 距离空间图

中文注解

Figure 5. Diagram of distance space

英文注解

下载: 全尺寸图片幻灯片

图 6 角点图像

中文注解

Figure 6. Corner detection image

英文注解

下载: 全尺寸图片幻灯片

图 7 特征匹配结果

中文注解

Figure 7. Matching result

英文注解

下载: 全尺寸图片幻灯片

表 1 相机内部参数

Table 1. Camera internal parameter

	μ₀/mm	v₀/mm	f/mm	k₂
Camera1	658.884	533.363	16.193 040	0.000 289
Camera2	647.305	498.355	6.042 961	0.006 233
Camera3	647.598	498.715	16.235 531	0.000 288

下载: 导出CSV

表 2 角点在各视图中的像素坐标

Table 2. Pixel coordinates of corners in each view image

	Camera1(像素)	Camera2(像素)	Camera3(像素)
1	(544,957)	-	(758,840)
2	(533,805)	(763,591)	-
3	-	(783,560)	(791,690)
4	(815,723)	(546,310)	(526,631)

下载: 导出CSV

表 3 相机与CMM之间的坐标转换关系

Table 3. Relation of coordinate transformation between camera and CMM

	α/rad	β/rad	γ/rad	t_x/mm	t_y/mm	t_z/mm
Camera1-CMM	-1.503 283	0.064 378	-0.046 754	227.974 026	-1 050.507 167	-400.084 751
Camera2-CMM	0.044 251	-0.248 223	-1.523 188	308.677 97	870.639 171	30.065 223
Camera3-CMM	-1.543 118	-0.080 176	-1.524 048	-1529.503 317	624.449 218	-522.936 725

下载: 导出CSV

表 4 定位精度检测

Table 4. Positioning accuracy detection

	计算坐标/mm			CMM测量坐标/mm			误差/mm
	x	y	z	x′	y′	z′	Δx	Δy	Δz
1	229.98	607.47	-752.80	228.26	608.13	-753.52	1.72	-0.79	0.72
2	229.13	607.06	-667.91	229.84	608.94	-668.76	-0.71	-1.88	0.85
3	232.87	602.95	-667.16	233.64	604.06	-668.52	-0.77	-1.11	1.36
4	402.91	777.03	-658.04	401.29	778.21	-658.92	1.62	-1.18	0.88

下载: 导出CSV

参考文献(18)

[1]	马一凡.防碰撞系统中零件识别研究[D].天津:天津大学,2014. MA Y F. Research on recognition of parts in anti-collision system[D]. Tianjin:Tianjin University,2014.(in Chinese)
[2]	王怀瑜.防碰撞系统中体素相交检测算法的研究[D].天津:天津大学,2014. WANG H Y. Research on an algorithm of primitive intersection detection in an anti-collision system[D]. Tianjin:Tianjin University,2014.(in Chinese)
[3]	刘书桂,赵金才,李建苹,等.智能坐标测量系统中零件位姿自动识别[J].天津大学学报,2006,39(10):1241-1246. LIU SH G,ZHAO J C,LI J P,et al.. Automatic recognition for position and orientation of parts in intelligent coordinate measuring system[J]. J. Tianjin University,2006,39(10):1241-1246.(in Chinese)
[4]	马新辉,张国雄,王建利,等.智能三坐标测量机中零件位置自动识别系统[J].仪器仪表学报,2003,24(2):165-170. MA X H,ZHANG G X,WANG J L,et al.. Autamatic recognition for the position and orientation of parts in intelligent CMM[J]. Chinese J. Scientific Instrument,2003,24(2):165-170.(in Chinese)
[5]	房超,王小鹏,牛云鹏,等.基于改进Harris算法的角点检测[J].计算机与数字工程,2011,39(5):142-144. FANG CH,WANG X P,NIU Y P,et al.. Corner detection based on an improved Harris algorithm[J]. Computer and Digital Engineering,2011,39(5):142-144.(in Chinese)
[6]	乔警卫,胡少兴.三维重建中特征点提取与匹配算法研究[J].系统仿真学报,2008,20:400-403. QIAO J W,HU SH X. Research on feature point extraction and matching in 3D reconstruction[J]. J. System Simulation,2008,20:400-403.(in Chinese)
[7]	黄凤山,刘恩福,方忆湘,等.基于智能三坐标测量机的零件位姿单目立体视觉识别[J].光学精密工程,2013,21(5):1326-1332. HUANG F SH,LIU E F,FANG Y X,et al.. Single camera stereo vision recognization for parts pose based on intelligent three coordinate measuring machine[J]. Opt. Precision Eng.,2013,21(5):1326-1332.(in Chinese)
[8]	许佳佳.结合Harris与SIFT 算子的图像快速配准算法[J].中国光学,2015,8(4):574-581. XU J J. Fast image registration method based on Harris and SIFT algorithm[J]. Chinese Optics,2015,8(4):574-581.(in Chinese)
[9]	高晶,吴育峰,吴昆,等.基于角点检测的图像匹配算法[J].仪器仪表学报,2013,34(8):1717-1725. GAO J,WU Y F,WU K,et al.. Image matching method based on corner detection[J]. Chinese J. Scientific Instrument,2013,34(8):1717-1725.(in Chinese)
[10]	程德志,李言俊,余瑞星.基于改进SIFT算法的图像匹配方法[J].计算机仿真,2011,28(7):285-289. CHENG D Z,LI Y J,YU R X. Image matching method based on improved SIFT algorithm[J]. Computer Simulation,2011,28(7):285-289.(in Chinese)
[11]	全燕鸣,黎淑梅,麦青群.基于双目视觉的工件尺寸在机三维测量[J].光学精密程,2013,21(4):1054 -1061. QUAN Y M,LI S M,MAI Q Q. On-machine 3D measurement of workpiece dimensions based on binocular vision[J]. Opt. Precision Eng.,2013,21(4):1054-1061.(in Chinese)
[12]	田浩南,张叶.基于边缘及特征点匹配的立体图像质量评价[J].液晶与显示,2015,30(4):666-672. TIAN H N,ZHANG Y. Quality evaluation of stereo image based on edge and characteristic point matching[J]. Chinese J. Liquid Crystals and Displays,2015,30(4):666-672.(in Chinese)
[13]	刘书桂,余飞,韩振华.基于OpenCasCade的虚拟三坐标测量机碰撞检测方法[J].纳米技术与精密工程,2016. LIU SH G,YU F,HAN ZH H. Collision detection of virtual coordinate measuring machine based on OpenCasCade[J]. Nanotechnology and Precision Engineering,2016.(in Chinese)
[14]	张国雄.三坐标测量机[M].天津:天津大学出版社,1999. ZHANG G X. Coordinate Measuring Machine[M]. Tianjin:Tianjin University Press,1999.(in Chinese)
[15]	HARRIS C G,STEPHENS M. A combined corner and edge detector[C]. Proceedings of the 4^th A Ivey Vision Conference,Manchester,UK,1988:147-151.
[16]	SMITH S M. Feature based image sequence understanding[D]. Oxford,UK:Oxford University, 1992.
[17]	王付新,黄毓瑜,孟偲,等.三维重建中特征点提取算法的研究与实现[J].工程图学学报,2007,3:91-96. WANG F X,HUANG Y Y,MENG C,et al. Research and realization of the feature point extraction algorithm in 3D reconstruction[J]. J. Engineering Graphics,2007,3:91-96(in Chinese)
[18]	HARTLEY R,ZISSERMAN H.计算机视觉中的多视图几何[M].安徽:安徽大学出版社,2002,8:216-217,178-179. HARTLEY R,ZISSERMAN H. Multiple View Geometry in Computer Vision[M]. Anhui:Anhui University Press, 2002,8:216-217,178-179.(in Chinese)