This Article 
 Bibliographic References 
 Add to: 
View Variation of Point-Set and Line-Segment Features
January 1993 (vol. 15 no. 1)
pp. 51-68

The variation, with respect to view, of 2D features defined for projections of 3D point sets and line segments is studied. It is established that general-case view-invariants do not exist for any number of points, given true perspective, weak perspective, or orthographic projection models. Feature variation under the weak perspective approximation is then addressed. Though there are no general-case weak-perspective invariants, there are special-case invariants of practical importance. Those cited in the literature are derived from linear dependence relations and the invariance of this type of relation to linear transformation. The variation with respect to view is studied for an important set of 2D line segment features: the relative orientation, size, and position of one line segment with respect to another. The analysis includes an evaluation criterion for feature utility in terms of view-variation. This relationship is a function of both the feature and the particular configuration of 3D line segments. The use of this information in objection recognition is demonstrated for difficult discrimination tasks.

[1] D. V. Ahuja and S. A. Coons, "Geometry for construction and display,"IBM Syst. J., vol. 7, nos. 3-4, pp. 188-205, 1968.
[2] Y. Aliomonos and M. Swain, "Paraperspective projection: Between orthography and perspective," CAR-TR-320, Univ. of Maryland, 1987.
[3] J. Ben-Aire, "The probabilistic peaking effect of viewed angles and distances with application to 3D object recognition,"IEEE Patt. Anal. Machine Intell., vol. 12, no. 8, pp. 760-774, 1990.
[4] J. R. Beveridge and R. Weiss, and E. M. Riseman, "Combinatorial optimization applied to variable scale 2-D model matching," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 18-22.
[5] J. R. Beveridge, "Shape matching, combinatorial optimization and local search," Forthcoming Ph.D. thesis, Comput. Inform. Sci. Dept., Univ. Massachusetts, Amherst, 1993.
[6] T. O. Binford, T. S. Levitt, and W. B. Mann, "Baysian inference in model-based machine vision," inProc. AAAI Uncert. Work., 1987.
[7] R. A. Brooks, "Symbolic reasoning among 3D models and 2D images,"Artificial Intell., vol. 17, pp. 285-348, 1981.
[8] J. B. Burns and L. J. Kitchen, "Recognition in 2D images of 3D objects from large model bases using perdiction hierarchies," inProc. IJCAI-10, 1987.
[9] J. B. Burns and E. M. Riseman, "Matching complex images to multiple 3D objects using view description networks," inProc. CVPR, 1992, pp. 328-334.
[10] J. B. Burns, "Matching 2D images to multiple 3D objects using view description networks," Ph.D. thesis, Univ. Massachusetts, Amherst, 1992.
[11] R. Duda and P. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[12] D. A. Forsyth, J. L. Mundy, A. Zisserman, and C. M. Brown, "Projectively invariant representations using implicit algebraic curves," inProc. European Conf. Computer Vision, June 1990.
[13] W.E.L. Grimson,Object Recognition by Computer: The Role of Geometric Constraints, MIT Press, Cambridge, Mass., 1990.
[14] B. K. P. Horn,Robot Vision. Cambridge, MA: M.I.T. Press, 1986.
[15] D. P. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. ICCV, 1987, pp. 102-111.
[16] K. Ikeuchi, "Precompiling a geometrical model into an interpretation tree for object recognition in bin-picking tasks," inProc. DARPA IUW, 1987, pp. 321-339.
[17] K. Kanatani, Group Theoretical Methods in Image Understanding, New York: Springer, 1990.
[18] J. J. Koenderink and A. J. van Doom, "How an ambulent observer can construct a model of the environment from the geometrical structure of visual flow," inKybernetik 1977(G. Rauske and E. Butenandt, Eds.). Munich: Oldenbourg, 1978.
[19] M. R. Korn and C. R. Dyer, "3-D multiview object representations for model-based object recognition,"Pattern Recog., vol. 20, no. 1, pp. 91-103, 1987.
[20] Y. Lamdan, J. T. Schwartz, and H. J. Wolfson, "Object recognition by affine invariant matching," inProc. CVPR 88, 1988.
[21] Y. Lamdan and H. J. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," inProc. 2nd Int. Conf. Computer vision, 1988.
[22] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[23] D. Marr,Vision. San Francisco: W. H. Freeman, 1982.
[24] R. Mohr, L. Morin, C. Inglebert, and L. Quan, "Geometric solutions to 3D vision problems," to be published.
[25] J. L. Mundy and A. Zisserman,Geometric Invariance in Computer Vision. Boston, MA: MIT Press, 1992.
[26] G. Sparr, "Depth computations from polyhedral images," inProc. Second Euro. Conf. Comput. Vision, 1992, pp. 378-386.
[27] D. Thompson and J. Mundy, "Three dimensional model matching from an unconstrained viewpoint,"Proc. Int. Conf. Robotics Automation, 1987, pp. 208-220.
[28] L. W. Tucker, C. R. Feynman, and D. M. Fritzsche, "Object recognition using the connection machine, inProc. IEEE Comput. Vision Patt. Recogn.(Ann Arbor, MI), June 1988, pp. 871-878.
[29] I. Weiss, "Projective invariants of shapes," inProc. DARPA Image Understanding Workshop, 1988, pp. 1125-1134.

Index Terms:
feature variation; image recognition; view variation; 3D point sets; weak perspective approximation; 2D line segment features; feature extraction; image recognition
J. Brian Burns, R.S. Weiss, E.M. Riseman, "View Variation of Point-Set and Line-Segment Features," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 51-68, Jan. 1993, doi:10.1109/34.184774
Usage of this product signifies your acceptance of the Terms of Use.