This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Robust Affine Structure Matching for 3D Object Recognition
November 1998 (vol. 20 no. 11)
pp. 1265-1274

Abstract—We consider model-based object localization based on local geometric feature matching between the model and the image data. The method is based on geometric constraint analysis, working in transformation space. We present a formal method which guarantees finding all feasible matchings in polynomial time. From there we develop more computationally feasible algorithms based on conservative approximations of the formal method. Additionally, our formalism relates object localization, affine model indexing, and structure from multiple views to one another.

[1] H. Alt, K. Mehlhorn, H. Wagener, and E. Welzl, "Congruence, Similarity, and Symmetries of Geometric Objects," Discrete and Computational Geometry, vol. 3, pp. 237-256.New York: Springer-Verlag, 1988.
[2] T.D. Alter, "3-D Pose From 3 Points Using Weak-Perspective," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 8, pp. 802-808, Aug. 1994.
[3] T.D. Alter and D.W. Jacobs, "Error Propagation in Full 3-D and 2-D Object Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 892-898, 1994.
[4] H.S. Baird, Model-Based Image Matching Using Location.Cambridge, Mass.: MIT Press, 1985.
[5] T.M. Breuel, "An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition," A.I. Memo No. 1259, Artificial Intelligence Laboratory, Massachusetts Institute of Tech nology, Oct. 1990.
[6] T.A. Cass, "Robust Affine Structure Matching for 3D Object Recognition," SPL Tech Report SPL-96-003 (P9610031), Xerox Palo Alto Research Center, Palo Alto, Calif., 1996.
[7] T.A. Cass, "Parallel Computation in Model-Based Recognition," master's thesis, Massachusetts Institute of Tech nology, 1988.
[8] T.A. Cass, "Polynomial-Time Geometric Matching for Object Recognition," Proc. European Conf. Computer Vision, 1992.
[9] T.A. Cass, "Robust Geometric Matching for 3D Object Recognition," Proc. Int'l Conf. Pattern Recognition, pp. A477-A482,Jerusalem, Israel, Oct. 1994.
[10] T.A. Cass, "Polynomial-Time Geometric Matching for Object Recognition," Int'l J. Computer Vision, vol. 21, no. 1/2, pp. 37-61, Jan. 1997.
[11] L. Chew, M. Goodrich, D. Huttenlocher, K. Kedem, J. Kleinberg, and D. Kravets, "Geometric Pattern Matching Under Euclidean Motion," Proc. Fifth Canadian Conf. Computational Geometry,Waterloo, Ontario, Canada, 1993.
[12] L. Chew and K. Kedem, "Improvements on Geometric Pattern Matching Problems," pp. 343-348,Las Vegas, Nev., 1992.
[13] M. Costa, R.M. Haralick, and L.G. Shapiro, "Optimal Affine-Invariant Point Matching," Proc. Sixth Israel Conf. Artificial Intelligence, pp. 35-61, 1990.
[14] M.A. Fischler and R.C. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting With Applications to Image Analysis and Automated Cartography," Comm. ACM, vol. 24, no. 6, pp. 381-395, 1981.
[15] M. Goodrich, J. Mitchell, and M. Orletsky, "Practical Methods for Approximate Geometric Pattern Matching Under Rigid Motion," Proc. 10th ACM Symp. Computational Geometry, pp. 103-112, 1994.
[16] W. Eric, L. Grimson, D.P. Huttenlocher, and D.W. Jacobs, "Affine Matching With Bounded Sensor Error: A Study of Geometric Hashing&Alignment," Technical Report A.I. Memo 1250, Artificial Intelligence Laboratory, Massachusetts Institute of Tech nology, 1990.
[17] W. Eric, L. Grimson, and T. Lozano-Perez, "Localizing Overlapping Parts by Searching the Interpretation Tree," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, July 1987.
[18] P. Heffernan and S. Schirra, "Approximate Decision Algorithms for Point Set Congruence," Computational Geometry: Theory and Applications, vol. 4, 1994.
[19] M.J. Hopcroft, "A Geometrical Approach to Model-Based Vision," PhD thesis, Cornell Univ., Jan. 1995.
[20] D.P. Huttenlocher, G.A. Klanderman, and W.J. Rucklidge, “Comparing Images Using the Hausdorff Distance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 850-863, Sept. 1993.
[21] D. Huttenlocher and S. Ullman, "Recognizing Solid Objects by Alignment With an Image," Int'l J. Computer Vision, vol. 5, no. 7, pp. 195-212, 1990.
[22] D.W. Jacobs, "Recognizing 3-D Objects Using 2-D Images," PhD thesis, Massachusetts Institute of Tech nology, 1992.
[23] J.J. Koenderink and A.J. van Doorn, "Affine Structure From Motion," J. Optical Soc. Am. A, vol. 8, no. 2, pp. 377-385, 1991.
[24] C.F. Olson, "Efficient Pose Clustering Using a Randomized Algorithm," Int'l J. Computer Vision, vol. 23, no. 2, pp. 131-147, June 1997.
[25] I. Rigoutsos and R. Hummel, "A Bayesian Approach to Model Matching With Geometric Hashing," Int'l J. Computer Vision, vol. 62, no. 1, pp. 11-26, July 1995.
[26] L. Roberts, "Machine Perception of Three-Dimensional Solid Objects," J. Tippett, ed., Optical and Electro-Optical Information Processing.Cambridge, Mass.: MIT Press, 1966.
[27] W.J. Rucklidge, “Locating Objects Using the Hausdorff Distance,” Proc. Int'l Conf. Computer Vision, pp. 457-464, 1995.
[28] D. Thompson and J. Mundy, "Three-Dimensional Model Matching From an Unconstrained Viewpoint," Proc. IEEE Conf. Robotics and Automation, pp. 208-220, 1987.
[29] W.M. Wells III, "Statistical Object Recognition," Technical Report AITR-1398, Artificial Intelligence Laboratory, Massachusetts Institute of Tech nology, Jan. 1993.
[30] H. Wolfson and Y. Lambdan, "Transformation Invariant Indexing," J. Mundy and A. Zisserman, eds., Geometric Invariance in Computer Vision, pp. 335-353.Cambridge, Mass.: MIT Press, 1992.

Index Terms:
Object recognition, geometric feature matching, pose recovery, alignment method, affine structure, model indexing, computational geometry.
Citation:
Todd A. Cass, "Robust Affine Structure Matching for 3D Object Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1265-1274, Nov. 1998, doi:10.1109/34.730560
Usage of this product signifies your acceptance of the Terms of Use.