On View Likelihood and Stability

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]  D. Weinshall,et al.  Measures for Silhouettes Resemblance and Representative Silhouettes of Curved Objects , 1996, ECCV.

[2]  Herbert Freeman,et al.  Characteristic Views As A Basis For Three-Dimensional Object Recognition , 1982, Other Conferences.

[3]  William T. Freeman,et al.  Exploiting the generic view assumption to estimate scene parameters , 1993, 1993 (4th) International Conference on Computer Vision.

[4]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Ellen C. Hildreth,et al.  The perceptual buildup of three-dimensional structure from motion , 1989, Perception & psychophysics.

[6]  金谷 健一.  Group-theoretical methods in image understanding , 1990 .

[7]  Michael Werman,et al.  Similarity and Affine Invariant Distances Between 2D Point Sets , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Robert A. Hummel,et al.  Distributed Bayesian object recognition , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  William T. Freeman,et al.  The generic viewpoint assumption in a framework for visual perception , 1994, Nature.

[10]  H. Bülthoff,et al.  INTERACTION OF DIFFERENT MODULES IN DEPTH PERCEPTION. , 1987, ICCV 1987.

[11]  A. Witkin,et al.  On the Role of Structure in Vision , 1983 .

[12]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[13]  F ATTNEAVE,et al.  The quantitative study of shape and pattern perception. , 1956, Psychological bulletin.

[14]  Jezekiel Ben-Arie.  The Probabilistic Peaking Effect of Viewed Angles and Distances with Application to 3-D Object Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  J.B. Burns,et al.  View Variation of Point-Set and Line-Segment Features , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[18]  Michael Werman,et al.  Similarity and Aane Distance between Point Sets , 1994 .

[19]  Daphna Weinshall,et al.  Distance metric between 3D models and 2D images for recognition and classification , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.