大尺寸工业视觉测量系统

刘建伟; 梁晋; 梁新合; 曹巨明; 张德海

光学精密工程, 2010, 18 (1): 126, 网络出版: 2010-08-31

大尺寸工业视觉测量系统

Industrial vision measuring system for large dimension work-pieces

论文大纲

刘建伟 ^1,*梁晋 ¹梁新合 ¹曹巨明 ²张德海 ¹

作者单位

¹ 西安交通大学机械工程学院，陕西西安 710049

² 西安交通大学电子与信息工程学院，陕西西安 710049

立体视觉标志点识别立体匹配三维重建点云配准 stereo vision reference point recognition stereo matching 3D reconstruction point cloud registration

摘要

针对工业制造领域中大型工件很难进行全尺寸测量的问题，提出并实现了一种基于立体视觉技术的便携式工业测量系统。对该系统所采用的特征识别、相机定向、立体匹配、三维重建、多视点云配准等关键算法进行了研究。提出了改进的CANNY边缘亚像素检测算法，使用先验规则去除误识别的标志点，多次拟合定位标志点中心，对标志点环带多次采样取中值求取编码点的ID。根据ID号找出不同照片中的同名编码点，顺次对照片进行相对定向和绝对定向。然后，根据多幅图像的多极线几何约束，实现非编码点的匹配，消除误匹配。采用前方交会法重建标志点的三维坐标，利用光束平差对计算出的结果和内外部参数做迭代修正。最后，设计了双目结构光扫描系统，提出了一种改进的双目像机标定算法，描述了利用全局和局部标志点的子图同构实现多视点云配准的新算法。实验结果表明，该系统可在生产现场对大型工件进行快速测量，整体测量精度达到0.112 mm/3 m，可以满足工业现场大尺寸测量对精度和效率的要求。

Abstract

In order to realize the rapid measurement for large dimension work-pieces in industrial fields, a new measuring system based on a stereo vision was proposed and implemented. The key algorithms used in the system, such as feature recognition, camera orientation, stereo matching, object coordinate 3D reconstruction and multi-view point cloud registration, were studied. Firstly, an improved ‘CANNY’ edge detecting method was presented to achieve the sub-pixel localization,and the experiential knowledge was used to eliminate miss-recognized reference points.By fitting point centers of the position, the ring of the reference points was sampled in multi-time to obtain a median and to constructed its ID. Then, the homonymous coded points in each photo pair were searched according to their unique IDs,and the relative orientation and absolute orientation were carried out.Secondly, the multi-image epipolar constraint method was utilized to implement the un-coded point matching and to remove the mismatching.Furthermore, the 3D coordinates of all reference points were calculated by the spatial intersection,and the interior and exterior parameters, image and object coordinates are corrected by the bundle adjustment synchronously. Finally, a binocular structure-light scanner was constructed to acquire the surface detail information of the work-pieces. An improved camera calibration approach was introduced and its calibration accuracy was compared with those of traditional methods.The multi-view point cloud global registration algorithm was also discussed in detail. Experiment results indicate that the new measuring system is suitable for the large work-piece measurement with an accuracy of 0.112 mm/3 m,and it can satisfy the precision and efficiency demands of the large dimension measurement.

参考文献

[1] . CAD/CAM/CAE representation of 3D objects measured by fringe projection[J]. SPIE, 1998, 3479: 70-75.

[2] . Practical 3D computer vision techniques for full-field surface measurement[J]. Optical Engineering, 2000, 39(1): 143-149.

[3] . Calibration and performance evaluation of a 3D imaging sensor based on the projection of structured light[J]. IEEE Transactions on Instrumentation and Measurement, 2000, 49(3): 628-636.

[4] . 3D shape measurement of complex objects by combining photogrammetry and fringe projector[J]. Optical Engineering, 2000, 39(1): 224-231.

[5] 邹定海,叶声华,王春和,等.用于在线测量的视觉检测系统［J］.仪器仪表学报,1995,16(4):337-340.

ZOU D H, YE SH H, WANG CH H, et al.. A visual inspection system for on-line measurement ［J］. Chinese Journal of Scientific Instrument, 1995,16(4):337-340. (in Chinese)

[6] . 基于非量测CCD摄像机的钣金件误差检测[J]. 测绘学报, 2004, 33(2): 132-137.

. . Imprecision inspection of sheet-metal parts with non-metric CCD camera[J]. Acta Geodaetica et Cartographica Sinica, 2004, 33(2): 132-137.

[7] OZTURK A O, HALICI U, ULUSOY I, et al.. 3D face reconstruction using stereo images and structured light［C］. IEEE 16th Signal Processing and Communications Applications Conference, Didim, Turkey:IEEE,2008,1-2:878-881.

[8] 张维忠. 基于多幅图像的空间点定位与曲线结构三维重建［D］. 南京:南京航空航天大学, 2007.

ZHANG W ZH. Reconstruction of 3D points and curve structures based on multiple images［D］. Nanjing:Nanjing University of Aeronautics and Astronautics,2007. (in Chinese)

[9] LUHMANN T. Close Range Photogrammetry［M］. Dunbeath: Whittles Publishing, 2006.

[10] 韩建栋,吕乃光,王锋,等. 采用光学定位跟踪技术的三维数据拼接方法［J］.光学精密工程,2009,17(1):45-51.

HAN J D, L N G, WANG F, et al.. 3D data registration method based on optical location tracking technology［J］. Opt. Precision Eng., 2009,17(1):45-51. (in Chinese)

[11] . Model and algorithms for point cloud construction using digital projection patterns[J]. Transactions of the ASME, 2007, 7: 372-381.

[12] 叶海加,陈罡,邢渊. 双目CCD结构光三维测量系统中的立体匹配［J］.光学精密工程,2004,12(1):71-75.

YE H J, CHEN G, XING Y. Stereo matching in 3D measurement system using double CCD structured light［J］. Opt. Precision Eng., 2004,12(1):71-75. (in Chinese)

[13] SAGAWA R, YAGI Y. Accurate calibration of intrinsic camera parameters by observing parallel light pairs［C］. 2008 IEEE International Conference on Robotics and Automation, Pasadena, CA, USA:IEEE,2008:1390-1397.

[14] . A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.

[15] 陈刚,姚英学. 多视点大空间三维坐标数据归一化方法［J］.光学精密工程,2008,16(7):1309-1314.

CHEN G, YAO Y X. 3D datum mosaic method of multi-view and large scale based on optical coding［J］. Opt. Precision Eng., 2008,16(7):1309-1314. (in Chinese)

[16] . Accurate integration of multi-view range images using k-means clustering[J]. Pattern Recognition, 2008, 41(1): 152-175.

刘建伟, 梁晋, 梁新合, 曹巨明, 张德海. 大尺寸工业视觉测量系统[J]. 光学精密工程, 2010, 18(1): 126. LIU Jian-wei, LIANG Jin, LIANG Xin-he, CAO Ju-ming, ZHANG De-hai. Industrial vision measuring system for large dimension work-pieces[J]. Optics and Precision Engineering, 2010, 18(1): 126.

大尺寸工业视觉测量系统

关于本站 Cookie 的使用提示

全站搜索

大尺寸工业视觉测量系统

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索