This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
On View Likelihood and Stability
February 1997 (vol. 19 no. 2)
pp. 97-108

Abstract—We define two measures on views: view likelihood and view stability. View likelihood measures the probability that a certain view of a given 3D object is observed; it may be used to identify typical, or "characteristic," views. View stability measures how little the image changes as the viewpoint is slightly perturbed; it may be used to identify "generic" views. Both definitions are shown to be identical up to the prior probability of camera orientations, and determined by the 2D metric used to compare images. We analytically derive the stability and likelihood measures for two feature-based 2D metrics, where the most stable and most likely view is shown to be the flattest view of the 3D shape.

Incorporating view likelihood or stability in 3D object recognition and 3D reconstruction increases the chance of robust performance. In particular, we propose to use these measures to enhance 3D object recognition and 3D reconstruction algorithms, by adding a second step where the most likely solution is selected among all feasible solutions. These applications are demonstrated using simulated and real images.

[1] F. Attneave, "Some Informational Aspects of Visual Perception," Psychol. Review, pp. 183-193, 1954.
[2] R. Basri and D. Weinshall, "Distance Metric Between 3D Models and 2D Images for Recognition and Classification," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 4, pp. 465-470, Apr. 1996.
[3] J. Ben-Arie, "The Probabilistic Peaking Effect of Viewed Angles and Distances With Application to 3D Object Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 760-774, August 1990.
[4] T.O. Binford and T.S. Levitt, "Quasi-Invariants: Theory and Exploitation," Image Understanding Workshop, pp. 819-829, 1993.
[5] H.H. Bülthoff and H.A. Mallot, "Interaction of Different Modules in Depth Perception," Proc. First Int'l Conf. Computer Vision, pp. 295-305, June 1987.
[6] J.B. Burns, R.S. Weiss, and E.M. Riseman, "View Variation of Point-Set and Line-Segment Features," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 51-68, Jan. 1993.
[7] I. Chakravarty and H. Freeman, "Characteristic Views as a Basis for Three-Dimensional Object Recognition," Proc. SPIE Conf. Robot Vision, vol. 336, pp. 37-45, 1982.
[8] S.J. Dickinson, A.P. Pentland, and A. Rosenfeld, "3D Shape Recovery Using Distributed Aspect Matching," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 174-198, Feb. 1992.
[9] F. Attneave and M.D. Arnoult, "The Quantitative Study of Shape and Pattern Perception," Psychol. Bulletin, pp. 452-471, 1956.
[10] W.T. Freeman, "Exploiting the Generic View Assumption to Estimate Scene Parameters," Proc. Fourth Int'l Conf. Computer Vision, pp. 347-356,Berlin, Germany, 1993. Washington, D.C.: IEEE.
[11] W.T. Freeman, "The Generic Viewpoint Assumption in a Framework for Visual Perception," Nature, vol. 368, no. 6,471, pp. 542-545, Apr.7, 1994.
[12] Y. Gdalyahu and D. Weinshall, "Measures for Silhouettes Resemblance and the Most Representative Silhouette of a Curved Object," Proc. Fourth European Conf. Computer Vision,Cambridge, UK, 1996. Springer-Verlag.
[13] E.C. Hildreth, N.M. Grzywacz, E.H. Adelson, and V.K. Inada, "The Perceptual Buildup of Three-Dimensional Structure from Motion," Perception&Psychophysics, vol. 48, no. 1, pp. 19-36, 1990.
[14] D.P. Huttenlocher and S. Ullman, "Recognizing Solid Objects by Alignment with an Image," Int'l J. Computer Vision, vol. 5, pp. 195-212, 1990.
[15] K. Kanatani, Group Theoretical Methods in Image Understanding.Berlin: Springer, 1990.
[16] Y. Lamdan and H.J. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," Second Int'l Conf. Computer Vision, pp. 238-249, 1988.
[17] I. Rigoutsos and R. Hummel, "Distributed Bayesian Object Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 180-186, 1993.
[18] S. Ullman and R. Basri, "Recognition by Linear Combinations of Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 992-1006, 1991.
[19] D. Weinshall and R. Basri, "Distance Metric Between 3D Models and 2D Images for Recognition and Classification," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 220-225,New-York City, 1993. Washington, D.C.: IEEE.
[20] M. Werman and D. Weinshall, “Similarity and Affine Invariant Distances between 2D Point Sets,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 810-814, Aug. 1995.
[21] A.P. Witkin and J.M. Tenenbaum, "On the Role of Structure in Vision," J. Beck, B. Hope, and A. Rosenfeld, eds., Human and Machine Vision, pp. 481-544.New York: Academic Press, 1983.

Index Terms:
Generic views, characteristic views, canonical views, view likelihood, view stability, object recognition, 3D reconstruction, Bayesian vision.
Citation:
Daphna Weinshall, Michael Werman, "On View Likelihood and Stability," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 2, pp. 97-108, Feb. 1997, doi:10.1109/34.574783
Usage of this product signifies your acceptance of the Terms of Use.