Characterizing the Stability of 3D Invariants Derived from 3D Translational Symmetry

Translational symmetry provides a powerful constraint that enables recognition of three-dimensional (3D) objects from a single view. Under ideal conditions, affine invariants of 3D points reconstructed from corresponding points would serve as accurate indices for object recognition. In real images, however, inaccurate 2D coordinates of corresponding points can lead to erroneous invariants. In this paper, we investigate the effects of such errors on the 3D invariants, and discuss some approaches to successful indexing in the presence of these errors.

[1]  Olivier D. Faugeras,et al.  What can be seen in three dimensions with an uncalibrated stereo rig , 1992, ECCV.

[2]  Rajiv Gupta,et al.  Stereo from uncalibrated cameras , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  David A. Forsyth,et al.  Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Andrew Zisserman,et al.  Extracting structure from an affine view of a 3D point set with one or two bilateral symmetries , 1994, Image and Vision Computing.

[5]  Joseph L. Mundy,et al.  Repeated Structures: Image Correspondence Constraints and 3D Structure Recovery , 1993, Applications of Invariance in Computer Vision.

[6]  Andrew Zisserman,et al.  Extracting structure from an affine view of a 3D point set with one or two bilateral symmetries , 1994, Image Vis. Comput..