Abstract
3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.
Similar content being viewed by others
References
Chin, R. T. and Dyer, C. R.: Model-based recognition in robot vision, ComputingSurveys 18(1) (1986).
Filkins, B. L.: Graphical concepts in image processing – a bridge betweentwo worlds, SPIE on Applications of Digital Image Processing 575 (1985), 18–23.
Roberts, L. G.: Machine perception of three dimensional solids, in: J. T. Tipett et al. (eds), Opticaland Electro-optical Information Processing, MIT Press, Cambridge, MA, 1965.
Brooks, R. A.:Simbolic reasoning among 3D models and 2D images, Artificial Intelligence 17 (1981), 285.
Lowe, D.: Perceptual Organisation and Visual Recognition, Kluwer Academic Publishers, Boston,MA, 1985.
Baumgart, B. G.: Geometric modelling for computer vision, Technical ReportAIM-249, STANCS-74-463, Computer Science Dept., Stanford University, 1974.
Hermen, M.:Representation and incremental construction of a three-dimensional scene model, CMU Report, CMU-CS85-103, 1985.
Koshikawa, K. and Shirai, Y.: A 3D modeller for vision research, in:Proceedings of the International Conference on Advanced Robotics, Tokyo, Japan, 1985.
Bolles, R. C.and Horaud, P.: 3DPO: A three dimensional part orientation system, Robotics Research 5(3) (1986).
Henderson, T., Hansen, C., Samal, A., Ho, C. C., and Bhanu, B.: CAGD-based 3D visualrecognition, in: Proceedings ICPR, Paris, 1986, pp. 230–232.
Bhanu, B. and Ho, C. C.:CAGD-based 3D object representations for computer vision, IEEE Computers 20(8) (1987), 19–36.
Ho, C. C.: CAGD-based 3D object representations for computer vision, Master's Thesis,University of Utah, Salt Lake City, UT, 1987.
Flynn, P. J. and Jain, A. K.: CAD based computervision – From CAD models to relational graphs, IEEE PAMI 13(2) (1992).
Narasimhamurthi, N. and Jain, R.: CAD based object recognition incorporating metric and topologicalinformation, SPIE 938 (1988), 436–443.
Merat, F. L. and Radack, G. M.: Automaticinspection planning within a feature based CAD system, Robotics and Computer Integrated Manufacturing 9(1) (1992), 61–69.
Park, H. D. and Mitchell, O. R.: CAD based planning and execution ofinspection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Ann Arbor, MI, 1988, pp. 858–863.
Majumdar, J., Levi, P., and Rembold, U.: 3D model based robot vision bymatching scene description with the object model from a CAD modeller, Robotics and Autonomous Systems 5 (1989).
Majumdar, J., Levi, P., and Rembold, U.: Algorithm for visible surface pattern generation – atool for 3D object recognition, in: Sensor Based Robots, NATO ASI Series, Vol. F-66, 1991, pp. 93–106.
Magee, M. J. and Aggarwal, J. K.: Determining vanishing points from perspective images,Computer Vision, Graphics and Image Processing 26 (1984), 256–267.
Majumdar, J., Rangarajan, K., and Seethalakshmy, A. G.: Computation and use of planar face normals, Pattern Recognition Letters 14(10) (1993), 809–816.
Canny, J. F.: A computational approach to edgedetection, in: M. A. Fishler and O. Firschein (eds), Readings in Computer Vision, Morgan Kaufmann, 1987.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Majumdar, J., Seethalakshmy, A.G. A CAD Model Based System for Object Recognition. Journal of Intelligent and Robotic Systems 18, 351–365 (1997). https://doi.org/10.1023/A:1007902728509
Issue Date:
DOI: https://doi.org/10.1023/A:1007902728509