How Useful is Projective Geometry?

In this response, we will weigh two different approaches to shape recognition. On the one hand we have the use of restricted camera models as advocated in the paper of Pizlo et. al. to give a closer approximation to real calibrated cameras. The alternative approach is to use a full projective camera model and take advantage of the machinery of projective geometry

[1]  Long Quan,et al.  Relative 3D Reconstruction Using Multiple Uncalibrated Images , 1995, Int. J. Robotics Res..

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

[3]  O. D. Faugeras,et al.  Camera Self-Calibration: Theory and Experiments , 1992, ECCV.

[4]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[5]  K. Boyer,et al.  Incremental Modelbase Updating : Learning new model sites , 1993 .

[6]  Michel Dhome,et al.  Spatial Localization Of Modelled Objects Of Revolution In Monocular Perspective Vision , 1990, ECCV.

[7]  J. G. Semple,et al.  Algebraic Projective Geometry , 1953 .

[8]  Reiner Lenz,et al.  Correspondence of coplanar features through p/sup 2/-invariant representations , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[9]  R. Hartley.  Cheirality Invariants , 1993 .

[10]  Kalle Åström.  Fundamental Difficulties with Projective Normalization of Planar Curves , 1993, Applications of Invariance in Computer Vision.

[11]  David A. Forsyth,et al.  Canonical Frames for Planar Object Recognition , 1992, ECCV.

[12]  Thierry Viéville,et al.  Computing motion and structure in image sequences without calibration , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[13]  Jiang Yu Zheng,et al.  Acquiring 3-D Models from Sequences of Contours , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Roger Mohr,et al.  Euclidean constraints for uncalibrated reconstruction , 1993, 1993 (4th) International Conference on Computer Vision.

[15]  Long Quan,et al.  Invariants of Six Points and Projective Reconstruction From Three Uncalibrated Images , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Richard I. Hartley,et al.  An algorithm for self calibration from several views , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Long Quan,et al.  Relative 3D Reconstruction Using Multiple Uncalibrated Images , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Eamon B. Barrett,et al.  Some invariant linear methods in photogrammetry and model-matching , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[20]  Richard I. Hartley,et al.  Estimation of Relative Camera Positions for Uncalibrated Cameras , 1992, ECCV.

[21]  S. J. Maybank,et al.  Applications of invariants to model-based vision , 1994 .

[22]  Patrick Gros,et al.  Matching and Clustering: Two Steps Towards Automatic Model Generation in Computer Vision , 1993, AAAI 1993.

[23]  Long Quan,et al.  Invariants of 6 Points from 3 Uncalibrated Images , 1994, ECCV.

[24]  Patrick Gros,et al.  3D projective invariants from two images , 1993, Optics & Photonics.

[25]  Charlie Rothwell,et al.  Hierarchical Object Description Using Invariants , 1993, Applications of Invariance in Computer Vision.

[26]  Azriel Rosenfeld,et al.  Recognition of planar shapes from perspective images using contour-based invariants , 1992, CVGIP Image Underst..