Model-based recognition of arbitrary surfaces from range data

ABSTRACT

Recognition of arbitrary surfaces is a difficult and largely unsolved problem in computer vision. In this paper, we present a technique to develop a piecewise planar, triangular patch model of an object surface from its range data, and a recognition technique to be used with this model. A large set of object surface data points are segmented into triangular patches using a small number of knot points. The recognition technique extracts and stores in the form of attributed connection graph the features of all known surfaces from their triangular patch models. A similar model can be built from an unknown surface and its features detected. These features and relationships between the features are compared with those of the known surfaces for recognition.

REFERENCES

• 1: Dana Harry Ballard , Christopher M. Brown, Computer Vision, Prentice Hall Professional Technical Reference, 1982
• 2: Paul J. Besl , Ramesh C. Jain, Three-dimensional object recognition, ACM Computing Surveys (CSUR), v.17 n.1, p.75-145, March 1985 [doi>10.1145/4078.4081]
• 3: J. A Bloom and C. Y. Choo, "Extracting Feature Points and Feature Lines from Triangular Surface Models," Sensing and Reconstruction of Three-Dimensional Objects and Scenes, Bernd Girod, Ed., Proc. SPiE 1260, pp. 160-170, 1990.
• 4: Shi-Kuo Chang, Principles of pictorial information systems design, Prentice-Hall, Inc., Upper Saddle River, NJ, 1989
• 5: T. J. Fan, G. Medioni, and R. Nevatia, ~Segmented Descriptions of 3-D Surfaces," IEEE J. Robotics Automation, vol. RA-3, no. 6, pp. 527- 538, 1987.
• 6: T. J. Fan, G. Medioni, and R. Nevatia, "Recongnlzlng 3-D Objects Using Surface Descriptions," Proc. Second Intern. Conf. Computer Vision, Tampa, Florida, December 1988, pp. 474- 481.
• 7: T.C. Henderson, "Efficient 3-D Object Representations for Industrial Vision Systems," IEEE Trans. PAMI, vol. PAMI-5, no. 6, pp. 609-618, 1983.
• 8: S. Inokuchi, T. Nits, F. Matsuday, and Y. Sakurat, UA Three-Dimensional Edge-Region Operatot for Range Pictures," Proc. 6th Intern. Conf. Pattern Recognition, Munich, West Germany, October, 1982, pp. 918--920.
• 9: William I. B. Kwak , Lester A. Gerhardt, Design, analysis, and application of a three-dimensional vision system in computer integrated manufacturing, 1988
• 10: D. J. Langridge, "Detection of Discontinuities in the First Derivatives of Surfaces," Computer Vision, Graphics, and Image Processing, vol. 27, no. 3, pp. 291-308, 1984.
• 11: Franco P. Preparata , Michael I. Shamos, Computational geometry: an introduction, Springer-Verlag New York, Inc., New York, NY, 1985

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Range data

Additional Classification:
  G. Mathematics of Computing
  G.1 NUMERICAL ANALYSIS
      G.1.0 General
          Subjects: Parallel algorithms
  G.2 DISCRETE MATHEMATICS

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Shape; Modeling and recovery of physical attributes
  I.4 IMAGE PROCESSING AND COMPUTER VISION
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Computer vision

General Terms:
Algorithms, Experimentation