Abstract
A successful 3D object recognition system must take into account imperfections in the input data, due for example to fragmentation or sensor noise. In this paper we propose a methodology for robust 3D object recognition using uncertain image data. In particular, we present a method capable of achieving acceptable performance in the presence of both segmentation problems and sensor uncertainty, thus eliminating the need for ad hoc heuristics. The proposed method is based upon the use of probabilistic models suggested by the underlying physics processes. These models are statistically validated and tested under controlled experimentation.
This work was supported in part by NSF grant IRI9309100 and in part by a Pennsylvania State University Research Initiation Grant.
Preview
Unable to display preview. Download preview PDF.
References
O. I. Camps, L. G. Shapiro, and R. M. Haralick. Image prediction for computer vision. In Jain A.K. and P.J. Flynn, editors, Three-dimensional Object Recogntion Systems. Elsevier Science Publishers BV, 1993.
O. I. Camps, L. G. Shapiro, and R. M. Haralick. A probabilistic matching algorithm for computer vision. Annals of Mathematics and Artificial Intelligence, 10, 1994.
I. Chakravarty and H. Freeman. Characteristic views as a basis for three-dimensional object recognition. In SPIE 336 (Robot Vision), pages 37–45, 1982.
M. Costa, R.M. Haralick, and L.G. Shapiro. Optimal affine-invariant point matching. In Proc. of the International Conference on Pattern Recognition, pages 233–236, Atlantic City, New Jersey, June 1990.
D. Eggert. Aspect Graphs of Solids of Revolution. PhD thesis, Department of Computer Science and Engineering, University of South Florida, Tampa, Florida, 1991.
P.J. Flynn. CAD-Based Computer Vision: Modeling and Recognition Strategies. PhD thesis, Michigan State University, 1990.
T. L. Gandhi and O. I. Camps. Robust feature selection for object recognition using uncertain 2D image data. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 281–287, June 1994.
W.E.L. Grimson. Object Recognition by Computer: The role of geometric constraints. MIT Press, Cambridge, MA, 1990.
W.E.L. Grimson. Recognizing 3D Objects from 2D Images: An Error Analysis. Technical Report A.I. Memo No. 1362, MIT, Cambridge,MA, November 1992.
Charles D. Hansen. CAGD-Based Computer Vision: The Automatic Generation of Recognition Strategies. PhD thesis, The University of Utah, 1988.
R.M. Haralick and L.G. Shapiro. Computer and Robot Vision. Addison-Wesley, 1992.
J. Henikoff and L. Shapiro. Interesting patterns for model-based matching. In ICCV, 1990.
P. Horaud and R.C. Bolles. 3DPO: A system for matching 3-D objects in range data. In A.P. Pentland, editor, From Pixels to Predicates, pages 359–370. Ablex Publishing Corporation, Norwood, New Jersey, 1986.
D.P. Huttenlocher and S. Ullman. Object recognition using alignment. In Proceedings of the First International Conference on Computer Vision, pages 102–111, 1987.
K. Ikeuchi. Generating an interpretation tree from a CAD model for 3D-Object recognition in bin-picking tasks. Int. J. Comp. Vision, 1(2):145–165, 1987.
K. Ikeuchi and T. Kanade. Modelling sensor detectability and reliability in the configuration space for model-based vision. Technical Report CMU-CS-87-144, Carnegie-Mellon University, Computer Science Department, July 1987.
W.Y. Kim and A.C. Kak. 3D Object Recogntion Using Bipartite Matching Embedded in Discrete Relaxation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(3):224–251, March 1991.
D.E. Knuth. The Art of Computer Programming, vol. 2. Addison-Wesley, 1969.
M. Korn and C. Dyer. 3D-Multiview Object Representations for Model-Based Object Recognition. Pattern Recognition, 20(1):91–103, 1987.
R. Kumar and R. Hanson. Analysis of different robust methods for pose estimation. In Proc. of IEEE Workshop on Robust Computer Vision, October 1990.
C.N. Lee and R.M. Haralick. Exterior orientation from line-to-line correspondences — a Bayesian approach. In Proc. of the IEEE Computer Vision and Pattern Recogntion, June 1993.
D. G. Lowe. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31:355–395, 1987.
R. Mohan and R. Nevatia. Using perceptual organization to extract 3d structures. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(11):1121–1139, November 1989.
A. Papoulis. Probability, Random Variables, and Stochastic Processes. McGraw-Hill, third edition, 1991.
A. Pathak and O. I. Camps. Bayesian view class determination. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 1993.
J. Ponce and D. Kriegman. Computing exact aspect graphs or curved objects: parametric surfaces. In 8th National Conference on AI, pages 340–350, 1987.
J.H. Stewman. Viewer Centered Representations for Polyhedral Objects. PhD thesis, Department of Computer Science and Engineering, University of South Florida, Tampa, Florida, 1991.
H.J. Wolfson. Model based object recognition by geometric hashing. In First Europ. Conf. on Comp. Vis., pages 526–536, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Camps, O.I. (1995). Towards a robust physics-based object recognition system. In: Hebert, M., Ponce, J., Boult, T., Gross, A. (eds) Object Representation in Computer Vision. ORCV 1994. Lecture Notes in Computer Science, vol 994. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60477-4_21
Download citation
DOI: https://doi.org/10.1007/3-540-60477-4_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60477-8
Online ISBN: 978-3-540-47526-2
eBook Packages: Springer Book Archive