Synthetic template methodology for CAD directed robot vision

Abstract A methodology is presented for CAD directed inspection and control in the machine vision domain. Robot vision systems employ template matching for many applications in flexible manufacturing. Image templates are currently generated by training a vision processor on several snap shots of representative parts. Template training is time consuming and must usually be performed on-line. In low-to-medium volume applications this becornes impractical. To overcome this problem the CAD solid model database is used directly to predict and simulate the camera's actual view of the part during manufacture. Perspective projection transformation with scene rendering is used in combination with an illumination model to create a synthetic template. A robot mounted camera is then directed to appropriate views and orientations for successful part inspection. Replacing part training with this new approach saves time in two main ways: a physical part is not required for generating the template, and the template computation can be done in parallel with inspection tasks, thus avoiding production disruptions.

[1]  Andrew M. Wallace,et al.  Industrial applications of computer vision since 1982 , 1988 .

[2]  K. Torrance,et al.  Polarization, Directional Distribution, and Off-Specular Peak Phenomena in Light Reflected from Roughened Surfaces , 1966 .

[3]  Turner Whitted,et al.  An improved illumination model for shaded display , 1979, CACM.

[4]  Andrew Kusiak,et al.  Intelligent Manufacturing Systems , 1990 .

[5]  P. M. Dew,et al.  CAD based inspection: using a vision cell demonstrator , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[6]  Shivakumar Raman,et al.  A framework for knowledge representation and interpretation of industrial objects , 1992 .

[7]  James F. Blinn,et al.  Computer display of curved surfaces. , 1978 .

[8]  James F. Blinn,et al.  Scan line methods for displaying parametrically defined surfaces , 1988, CACM.

[9]  Konstantinos A. Tarabanis,et al.  The MVP sensor planning system for robotic vision tasks , 1995, IEEE Trans. Robotics Autom..

[10]  James D. Foley,et al.  Fundamentals of interactive computer graphics , 1982 .

[11]  Robert M. Haralick,et al.  Automatic sensor and light source positioning for machine vision , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[12]  HENRI GOURAUD,et al.  Continuous Shading of Curved Surfaces , 1971, IEEE Transactions on Computers.

[13]  J. M. Galm,et al.  The strategic design driven inspection of machined parts , 1988, [Proceedings] 1988 International Conference on Computer Integrated Manufacturing.

[14]  Michael Puttre.  Picture this: Visualization tools for CAD drawings , 1993 .

[15]  Bui Tuong Phong.  Illumination for computer generated pictures , 1975, Commun. ACM.

[16]  Konstantinos A. Tarabanis,et al.  A survey of sensor planning in computer vision , 1995, IEEE Trans. Robotics Autom..

[17]  Anil K. Jain,et al.  CAD-Based Computer Vision: From CAD Models to Relational Graphs , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  C. Alec Chang,et al.  Efficient measurement procedures for compound part profile by computer vision , 1991 .