Abstract
This paper treats the application of statistical principles for 3D computer vision purposes. Both the automatic generation of probabilistic object models, and the localization as well as the classification of objects in compound scenes result in complex optimization problems within the introduced statistical framework. Different methods are discussed for solving the associated optimization problems: the Expectation-Maximization algorithm forms the basis for the learning stage of stochastic object models; global optimization techniques—like adaptive random search, deterministic grid search or simulated annealing—are used for localization. The experimental part utilizes the abstract formalism for normally distributed object features, proves the correctness of 3D object recognition algorithms, and demonstrates their computational complexity in combination with real gray-level images.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
T. W. Anderson. An Introduction to Multivariate Statistical Analysis. Wiley Publications in Statistics. John Wiley & Sons, Inc., New York, 1958.
C. G. E. Boender, A. H. G. Rinnoy Kan, G. T. Timmer, and L. Stougie. A stochastic method for global optimization. Mathematical Programming, 22:125–140, 1982.
M. E. Bohachevsky, M. E. Johnson, and M. L. Stein. Generalized simulated annealing for function optimization. Technometrics, 28(3):209–217, 1986.
T. Caellei, M. Johnston, and T. Robinson. 3D object recognition: Inspirations and lessons from biological vision. In Jain and Flynn [19], pages 1–16.
B. Cernuschi-Frias, D. P. Cooper, Y. P. Hung, and P. N. Belhumeur. Toward a model-based Bayesian theory for estimating and recognizing parameterized 3-D objects using two or more images taken from different positions. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(10): 1028–1052, October 1989.
P. B. Chou and C. M. Brown. The theory and practice of Bayesian image labeling. International Journal of Computer Vision, 4(3): 185–210, June 1990.
A. Corana, M. Marchesi, and S. Ridella. Minimizing multimodal functions of continuous variables with the “simulated annealing” algorithm. ACM Transactions on Mathematical Software, 13(3):209–217, 1987.
A.P. Dempster, N.M. Laird, and D.B. Rubin. Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society, Series B (Methodological), 39(1):1–38, 1977.
J. Denzler, R. Be\ J. Hornegger, H. Niemann, and D. Paulus. Learning, tracking and recognition of 3D objects. In V. Graefe, editor, International Conference on Intelligent Robots and Systems-Advanced Robotic Systems and Real World, volume 1, pages 89–96, 1994.
L. C. W. Dixon and G. P. Szegö, editors. Towards Global Optimisation, volume 2, Amsterdam, 1978. North-Holland.
R.O. Duda and P.E. Hart. Pattern Classification and Scene Analysis. John Wiley & Sons, Inc., New York, 1973.
S. M. Ermakov and A. A. Zhiglyavskij. On random search of global extremum. Probability Theory and Applications, 28(1): 129–136, 1983.
F. Gallwitz. Lokalisierung von 3D-Objekten in Grauwertbildern. Technical report, Diploma thesis, Lehrstuhl für Mustererkennung (Informatik 5), UniversitÄt Erlangen-Nürnberg Erlangen, 1994.
S. Geman and C. Graffigne. Markov random field image models and their applications to computer vision. Proceedings of the International Congress of Mathematicians, pages 1496–1517, August 1986.
J. Hornegger. Statistische Modellierung, Klassifikation und Lokalisation von Objekten. Shaker, Aachen, 1996.
J. Hornegger and H. Niemann. Statistical learning, localization, and identification of objects. In Proceedings of the 5 th International Conference on Computer Vision (ICCV), pages 914–919, Boston, June 1995. IEEE Computer Society Press.
R. Hummel and S. Zucker. On the foundations of relaxation labeling processes. IEEE Trans. on Pattern Analysis and Machine Intelligence, 5:267–287, 1983.
A. K. Jain. Advances in statistical pattern recognition. In P. A. Devijver and J. Kittler, editors, Pattern Recognition Theory and Applications, volume 30 of NATO ASI Series F: Computer and System Sciences, pages 1–19. Springer, Heidelberg, 1987.
A. K. Jain and P. J. Flynn, editors. Three-Dimensional Object Recognition Systems, Amsterdam, 1993. Elsevier.
J. Kittler, W. J. Christmas, and M. Petrou. Probabilistic relaxation for matching problems in computer vision. In Proceedings of the 4 th International Conference on Computer Vision (ICCV), pages 666–673, Berlin, May 1993. IEEE Computer Society Press.
W. B. Mann and T. O. Binford. An example of 3-D interpretation of images using Bayesian networks. In Proceedings of Image Understandig Workshop, pages 793–801, San Diego, California, January 1992. Morgan Kaufmann Publishers, Inc.
D. Marr. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information, W.H. Freeman and Company, San Francisco, 1982.
J.W. Modestino and J. Zhang. A Markov random field model-based approach to image interpretation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(6):606–615, June 1992.
H. Niemann, H. Brünig, R. Salzbrunn, and S. Schröder. A knowledge-based vision system for industrial applications. In Machine Vision and Applications, pages 201–229, New York, 1990. Springer Verlag.
W.H. Press, B.P. Flannery, S. Teukolsky, and W.T. Vetterling. Numerical recipes — the art of numerical computing, c version. Technical report, 35465-X, 1988.
S. Sarkar and K. L. Boyer. Integration, inference, and management of spatial information using Bayesian networks: Perceptual organization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(3):256–274, March 1993.
J. Segen. Model learning and recognition of nonrigid objects. In Proceedings of Computer Vision and Pattern Recognition, pages 597–602, San Diego, June 1989. IEEE Computer Society Press.
Y. Shang and B. W. Wah. Global optimization for neural network training. Computer, 29(3):45–54, 1996.
P. Suetens, P. Fua, and A. J. Hanson. Computational strategies for object recognition. ACM Computing Surveys, 24(1):5–61, March 1992.
M. A. Tanner. Tools for Statistical Inference: Methods for the Exploration of Posterior Distributions and Likelihood Functions. Springer Series in Statistics. Springer, Heidelberg, 1993.
G. T. Timmer. Global optimization: A stochastic approach. PhD thesis, Rotterdam, 1984.
A. A. Törn. A programm for global optimization, multistart with clustering (msc). In P. A. Samet, editor, European Conference on Applied Information Technology, International Federation for Information Processing (EURO IFIP), pages 427–434, London, September 1979. Amsterdam North-Holland Publ. Co.
W. M. Wells III. Statistical Object Recognition. PhD thesis, MIT, Department of Electrical Engineering and Computer Science, Massachusetts, February 1993.
C. F. J. Wu. On the convergence properties of the EM algorithm. The Annals of Statistics, 11(1):95–103, 1983.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hornegger, J., Niemann, H. (1997). Optimization problems in statistical object recognition. In: Pelillo, M., Hancock, E.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1997. Lecture Notes in Computer Science, vol 1223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62909-2_88
Download citation
DOI: https://doi.org/10.1007/3-540-62909-2_88
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62909-2
Online ISBN: 978-3-540-69042-9
eBook Packages: Springer Book Archive