Toward Object-Based Heuristics

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]  Stephen T. Barnard,et al.  Choosing a basis for perceptual space , 1984, Comput. Vis. Graph. Image Process..

[2]  Alan L. Yuille,et al.  An Extremum Principle for Shape from Contour , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ramakant Nevatia,et al.  Using Symmetries For Analysis Of Shape From Contour , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[4]  Jean Ponce,et al.  Describing surfaces , 1985, Comput. Vis. Graph. Image Process..

[5]  Ari D. Gross.  Shape constraints from parametric and non-parametric models , 1993 .

[6]  Terrance E. Boult,et al.  An algorithm to recover generalized cylinders from a single intensity view , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[7]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[8]  David J. Kriegman,et al.  On Recognizing and Positioning Curved 3-D Objects from Image Contours , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  R. Nevatia,et al.  Perceptual organization for computer vision , 1989 .

[10]  Jean Ponce,et al.  Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Terrance E. Boult,et al.  SYMAN: a symmetry analyzer , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..