This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Toward Object-Based Heuristics
August 1994 (vol. 16 no. 8)
pp. 794-802

Recovering the 3-D shape of an object from its 2-D image contour is an important problem in computer vision. In this correspondence, the author motivates and develops two object-based heuristics. The structured nature of objects is the motivation for the nonaccidental alignment criterion: parallel coordinate axes within the object's bounding contour correspond to object-centered coordinate axes. The regularity and symmetry inherent in many man-made objects is the motivation for the orthogonal basis constraint. An oblique set of coordinate axes in the image is presumed to be the projection of an orthogonal set of 3-D coordinate axes in the scene. These object-based heuristics are used to recover shape in both real and synthetic images.

[1] S. Barnard, "Choosing a basis for perceptual space,"IEEE Workshop on Comput. Vision: Representation and Control, 1984, pp. 225-230.
[2] J. M. Brady and A. Yuille, "An extremum principle for shape from contour," Tech. Rep. MIT-AIM 711, AI Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA, 1983.
[3] J. M. Brady, J. Ponce, A. Yuille, and H. Asada, "Describing surfaces," in Harasuja and Inoue, Eds.,Proc. 2nd Int. Symp. Robotics Res.Cambridge, MA: MIT Press, 1985.
[4] A. D. Gross and T. E. Boult, "An algorithm to recover generalized cylinders from a single intensity view,"Proc. IEEE Comput. Soc. 1990 Int. Conf. Robotics and Automation, 1990, pp. 790-795.
[5] A. D. Gross and T. E. Boult, "SYMAN: a SYMmetry ANalyzer," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(Maui, HI), 1991, pp. 744-746.
[6] A. D. Gross, "Shape constraints from parametric and nonparametric models," Ph.D. dissertation, School of Eng. and Applied Sci., Columbia Univ., New York, NY, USA, 1992.
[7] T. Kanade, "Recovery of the 3-D shape of an object from a single view,"Artificial Intell., vol. 17, pp. 409-460, 1981.
[8] D. J. Kriegman and J. Ponce, "On recognizing and positioning curved 3-D objects from image contours,"IEEE Trans. Patt. Anal. Mach. Intell., vol. 12, pp. 1127-1137, Dec. 1990.
[9] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[10] R. Mohan, "Perceptual organization for computer vision," Ph.D. Thesis, IRIS Rep., Univ. Southern Calif., 1989.
[11] J. Ponce, D. Chelberg, and W. Mann, "Invariant properties of straight homogeneous generalized cylinders and their contours,"IEEE Trans. Patt. Anal. Mach. Intell., vol. 11, pp. 951-966, Sept. 1989.
[12] F. Ulupinar and R. Nevatia, "Using symmetries for analysis of shape from contour," inProc. 2nd ICCV, Tarpon Springs, FL, 1988, pp. 414-426.

Index Terms:
computer vision; image recognition; object-based heuristics; 3-D shape recovery; 2-D image contour; computer vision; nonaccidental alignment criterion; bounding contour; parallel coordinate axes; object-centered coordinate axes; regularity; symmetry; man-made objects; orthogonal basis constraint; synthetic images; real images
Citation:
A.D. Gross, "Toward Object-Based Heuristics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 8, pp. 794-802, Aug. 1994, doi:10.1109/34.308474
Usage of this product signifies your acceptance of the Terms of Use.