Skip to main content

Advertisement

Springer Nature Link
Log in

B-rep object description from multiple range views

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

We present a system which computes an integrated description of an object from multiple range images. The object description is in the form of B-rep (boundary representation), which has not been achieved by the computer vision community. To do so, we emphasize the inherent difficulties and ambiguities in the low to mid level vision, and present novel techniques of resolving them. In this system, each view of the object is represented as an attributed graph, where nodes correspond to the surfaces (vertices) and links represent the relationship between surfaces. The main issue in surface extraction is contour closure, which is formulated as a dynamic network. The underlying principle for this network is weak smoothness and geometric cohesion, and is modeled as the interaction between long and short term variables. Long term variables represent the initial boundary grouping computed from the low level surface features, and short term variables represent the competing hypotheses that cooperate with the long term variables.

The matching problem involves matching visible surfaces and vertices, and provides the necessary basis for volumetric reconstruction from multiple views. The matching strategy is a two step process, where in each step uses the Hopfield network. At each step, we specify a set of local, adjacency and global constraints, and define an appropriate energy function to be minimized. At the first level of this hierarchy, surface patches are matched and the rigidity transformation is computed. At the second level, the mapping is refined by matching the corresponding vertices, and the transformation is verified.

The multiple-view reconstruction consists of two steps. First, we build a composite graph that contains the bounding surfaces and their corresponding attributes, and then intersect these surfaces so that the edges and vertices corresponding to the B-rep description are identified. We present results on objects with planar, as well as quadratically-curved, surfaces.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  • Asada, H. and Brady, M. 1986. The curvature primal sketch. IEEE Trans. on Pattern Analysis and Machine Intelligence, 8(1): 2–15.

    Google Scholar 

  • Barr, A.H. 1981. Superquadrics and angle preserving transformations. IEEE Computer Graphics and Applications, 1: 1–20.

    Google Scholar 

  • Bartels, R. Beatty, J., and Barsky, B. 1987. An Introduction to Splines for use in Computer Graphics and Geometric Modeling, Morgan Kaufmann Publishers, Inc.

    Google Scholar 

  • Besl, P. and Jain, R. 1985. Three dimensional object recognition. ACM Computing Surveys, 17(1): 75–145.

    Google Scholar 

  • Besl, P. and Jain, R. 1988. Segmentation through symbolic surface description. IEEE Trans. on Pattern Analysis and Machine Intelligence, 10(2): 167–192.

    Google Scholar 

  • Biederman, I. 1987. Recognition by components: A theory of human image understanding. Journal of Psychological Review, 94(2): 115–147.

    Google Scholar 

  • Blake, A. and Zisserman, A. 1987. Visual Reconstruction. MIT Press: Cambridge, Massachusetts.

    Google Scholar 

  • Bolles, R.C. and Horaud, P. 1986. 3DPO: A three dimensional part orientation system. Int. Journal of Robotics Research, 5(3): 3–26, Fall 1986.

    Google Scholar 

  • Boult, T.E. and Gross, A.D. 1987. Recovery of superquadrics from depth information. In Proceedings of AAAI Workshop on Spatial Reasoning and Multi-Sensor Integration, pp. 128–137.

  • Brooks, R.A., 1983. Model based three dimensional interpretations of two dimensional images. IEEE Trans on Pattern Analysis and Machine Intelligence, 5(2): 140–150.

    Google Scholar 

  • Canny, J. 1986. A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 8(6): 679–699.

    Google Scholar 

  • Chen, J.S. 1989. Accurate edge detection from multiple scale processing. Ph.D. Dissertation, University of Southern California.

  • Chen, C. and Kak, A. 1989. A robot vision system for recognizing 3-D objects in low-order polynomial time. IEEE Trans. on System, Man, and Cybernetics, 19(2): 1535–1563.

    Google Scholar 

  • Chen, Y. and Medioni, G. 1991. Object modeling by registration of multiple range images. IEEE Conf. on Robotics and Automation, pp. 2724–2729.

  • Chin, R.T. and Dyer, C.R. 1986. Model based recognition in robot vision. ACM Computing Surveys, 18(1): 67–108.

    Google Scholar 

  • Duda, R.O. and Hart, P.E. 1973. Pattern Classification and Scene Analysis, John Wiley & Sons, Inc: New York.

    Google Scholar 

  • Fan, T.J., Medioni, G., and Nevatia, R. 1987. Segmented descriptions of 3-D surfaces. IEEE Trans. on Robotics and Automation, RA-3(6): 527–538.

    Google Scholar 

  • Fan, T.J., Medioni, G., and Nevatia, R. 1989. Recognizing 3-D objects using surface description. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(11): 1140–1157.

  • Faugeras, O.D. and Hebert, M. 1986. The representation, recognition, and localization of 3-D objects. Int. Journal of Robotics Research 5(3) 27–52.

    Google Scholar 

  • Faux, I. and Pratt, M. 1983. Computational Geometry for Design and Manufacture, John Wiley and Sons: New York, pp. 107–113.

    Google Scholar 

  • Ferrie, F.P. and Levine, M.D. 1987. Integrating information from multiple views. In Proc. of IEEE Workshop on Computer Vision, pp. 117–122.

  • Ferrie, F.P., Lagarde, J., and Whaite, P. 1993. Darboux frames, snake, and super-quadrics: Geometry from bottom-up. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(8): 771–784.

    Google Scholar 

  • Flynn, P.J. and Jain, A.K. 1988. Surface classification: Hypothesis testing and parameter estimation. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 261–267.

  • Flynn, P.J. and Jain, A.K. 1991. BONSAI: 3D object recognition using constrained search. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(10): 1066–1074.

    Google Scholar 

  • Geman, S. and Geman, D. 1984. Stochastic relaxation, Gibbs distribution, and Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 6: 721–741.

    Google Scholar 

  • Grimson, W.L. 1990. The combinatorics of object recognition in cluttered environments using constrained search. Journal of Artificial Intelligence, 44: 121–165.

    Google Scholar 

  • Grimson, W.L. and Lozano-Perez, T. 1987. Localizing overlapping parts by searching the interpretation tree. IEEE Trans. On Pattern Analysis and Machine Intelligence, 9(4).

  • Grossberg, S. and Mingolla, E. 1985. Neural dynamics of perceptual grouping: Texture, boundaries, and emergent segmentation. Perception and Psychophysics, 38(2): 141–171.

    Google Scholar 

  • Haralick, R., Watson, L., and Laffey, T. 1983. The topographic primal sketch. The International Journal of Robotics Research, 2(1): 50–71.

    Google Scholar 

  • Hensen, C. and Henderson, T. 1989. CAGD-based computer vision. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(11): 1181–1193.

    Google Scholar 

  • Hopfield, J., 1984. Neuron with graded response have collective computational properties like those of the two-state neurons. Proc. of National Academy of Science, 81: 3088–3092.

    Google Scholar 

  • Hopfield, J. and Tank, D. 1985. Neural computation of decisions in optimization problems. Biological Cybernetics, 52: 141–152.

    Google Scholar 

  • Hopfield, J. and Tank, D. 1986. Computing with neural circuits: A model, Science, 233: 625–632.

    Google Scholar 

  • Horn, B. 1984. Extended Gaussian images. Proceedings of IEEE, (72): 1656–1678.

  • Hummel, J. and Biederman, I. 1990. Dynamic binding: A basis for representation of shape by neural networks. Proceeding of 12th Annual Meeting of the Cognitive Science Society, pp. 614–621.

  • Ikeuchi, K. and Kanade, T. 1988. Applying sensor models to automatic generation of object recognition program. In Proceedings of Second International Conference on Computer Vision, pp. 228–236.

  • Jain, R. and Jain, A. 1988. Report on range image understanding workshop. In Machine Vision and Applications, East Lansing, Michigan, pp. 45–60.

  • Jain, A. and Hoffman, R. 1988. Evidence based recognition of 3-D objects. IEEE Trans. on Pattern Analysis and Machine Intelligence, 10(6): 783–802.

    Google Scholar 

  • Kirkpatrick, S. Gelatt, C., and Vecchi, M. 1983 Optimization by simulated annealing. Science, 220: 671–674.

    Google Scholar 

  • Konen, W. and von derMalsburg, C. 1993. Learning to generalize from single examples in the dynamic link architecture, Journal of Neural Computation, 5: 719–735.

    Google Scholar 

  • Lowe, D. and Binford, T. 1985. The recovery of three-dimensional structure from image curves. IEEE Trans. on Pattern Analysis and Machine Intelligence, 7(3): 320–326.

    Google Scholar 

  • Malik, J. 1987. Interpreting line drawings of curved objects. Int. Journal of Computer Vision, 1: 73–103.

    Google Scholar 

  • Marroquin, J. 1989. A Markovian random field of piecewise straight lines. Biological Cybernetics, 61: 457–465.

    Google Scholar 

  • Mohan, R. and Nevatia, R. 1989. Using perceptual organization to extract 3D structures. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(11): 1140–1158.

    Google Scholar 

  • Mohan, R. and Nevatia, R. 1989. Segmentation and description of scenes using perceptual organization. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 333–341.

  • Nevatia, R. and Binford, T.O. 1977. Description and recognition of complex-curved objects. Journal of Artificial Intelligence, 8: 77–98.

    Google Scholar 

  • Noborio, H., Fukuda, S., and Arimoto, S. 1988. Construction of the octree approximating three-dimensional objects by using multiple views. IEEE Trans. on Pattern Analysis and Machine Intelligence, 10(6): 769–782.

    Google Scholar 

  • Oshima, M. and Shirai, Y. 1983. Object recognition using three dimensional information. IEEE Trans. on Pattern Analysis and Machine Intelligence, 3(4): 353–361.

    Google Scholar 

  • Parvin, B. 1991. A dynamic system for object description and correspondence. Ph.D. Thesis, University of Southern California.

  • Parvin, B. and Medioni, G. 1989. A constraint satisfaction network for matching 3-D objects. Proc. Int. Joint Conf. on Neural Network, pp. 281–286.

  • Parvin, B. and Medioni, G. 1991a. A layered network for the correspondence of 3D objects, IEEE Conf. on Robotics and Automation, pp. 1808–1813.

  • Parvin, B. and Medioni, G. 1991b. A dynamic system for object description and correspondence. In Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 393–399.

  • Parvin, B. and Medioni, G. 1992. B-rep from unregistered multiple range images. Proc. of IEEE Conf. on Robotics and Automation, 2: 1602–1607.

    Google Scholar 

  • Pentland, A.P. 1986. Part models, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 242–249.

  • Perona, P. and Malik, J. 1990. Scale space and edge detection using anisotropic diffusion. IEEE Trans. on Pattern Analysis and Machine Intelligence, 12(7): 629–640.

    Google Scholar 

  • Poggio, T., Torre, V., and Koch, C. 1985. Computational vision and regularization theory, Nature, 317: 314–319.

    Google Scholar 

  • Ponce, J., Chelberg, D., Kriegman, D., and Mann, W. 1987. Geometric modeling with generalized cylinders. Proc. of IEEE Workshop on Computer Vision, pp. 268–270.

  • Potmesil, M. 1983. Generating models for solid objects by matching 3-D surface segments. Proc. of the International Conference on Artificial Intelligence, pp. 1089–1093.

  • Rao, K., Nevatia, R., and Medioni, G. 1987. Issues in shape description and an approach for working with sparse data. In Proceedings of AAAI Workshop on Spatial Reasoning and Multi-Sensor Integration, pp. 168–177.

  • Requicha, A.A. and Voeleker, H.B. 1985. Boolean operations in solid modeling: Boundary evaluation and merging algorithms. Proceedings of the IEEE, 73(1): 30–44.

    Google Scholar 

  • Saint-Mare, P., Chen, J.S. and Medioni, G. 1991. Adaptive smoothing: A general tool for early vision. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(6): 514–530.

    Google Scholar 

  • Sato, K., Ikeuchi, K., and Kanade, T. 1991. Model based recognition of specular objects using sensor models. In Proceedings of IEEE Workshop on CAD based Vision, pp. 2–10.

  • Sekita, I. et al., 1988. Feature extraction of handwritten Japanese characters by spline functions for relaxation matching. Journal of Pattern Recognition, 21(1): 9–17.

    Google Scholar 

  • Shaashua, A. and Ullman, S. 1988. Structural saliency: The detection of globally salient structures using a locally connected network. Int. Conf. on Computer Vision, pp. 321–327.

  • Solina, F. and Bajcsy, R. 1990. Recovery of parametric models from range images: The case for superquadrics with global deformation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 12(2): 131–147.

    Google Scholar 

  • Soucy, M. and Laurendeau, D. 1992. Multi-resolution surface modeling from multiple range views. In Proceeding of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 348–353.

  • Stein, F. and Medioni, G. 1992. Structural hashing: Efficient three dimensional object recognition. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(2): 125–146.

  • Tanaka, H. and Kishino, F. 1993. Adaptive mesh generation for surface reconstruction. In Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 88–94.

  • Vemori, B. and Aggarwal, J. 1986. 3D model construction from multiple range views using range and intensity data. In Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 435–438.

  • von der Malsburg, C. 1981. The correlation theory of Brian function, Technical Report 81-2, Max-Planck-Institute for Biophysical Chemistry.

  • Yuille, A. 1990. Energy functions for early vision and analog network. Journal of Biological Cybernetics, 61(2): 115–125.

    Google Scholar 

  • Zucker, S., Dobbins, A. and Iverson, L. 1989. Two stages of curve detection suggest two styles of visual computation, Neural Computation, 1: 68–81.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Information and Computing Sciences Division, Lawrence Berkeley National Laboratory, 94702, Berkeley, CA

    B. Parvin

  2. Institute of Robotics and Intelligent Systems, University of Southern California, 90089, Los Angeles, CA

    G. Medioni

Authors
  1. B. Parvin
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. G. Medioni
    View author publications

    You can also search for this author inPubMed Google Scholar

Additional information

This research was supported by the Advanced Research Projects Agency under contract f49620-90-C-0078, monitored by the Air Force Office of Scientific Research, by a grant from the Center for Manufacturing and Automation Research.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Parvin, B., Medioni, G. B-rep object description from multiple range views. Int J Comput Vision 20, 81–112 (1996). https://doi.org/10.1007/BF00144118

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00144118

Keywords